CN109388708B - Personalized customized writing system - Google Patents
Personalized customized writing system Download PDFInfo
- Publication number
- CN109388708B CN109388708B CN201810619317.1A CN201810619317A CN109388708B CN 109388708 B CN109388708 B CN 109388708B CN 201810619317 A CN201810619317 A CN 201810619317A CN 109388708 B CN109388708 B CN 109388708B
- Authority
- CN
- China
- Prior art keywords
- information
- user
- reading
- module
- push
- 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
Images
Abstract
The invention provides a personalized customized writing system, which comprises: the acquisition module is used for acquiring the reading habit and the reading content of the current user and acquiring information from a network channel; the analysis module is used for analyzing the reading habits and the reading contents and forming the reading characteristics of the user according to the analysis; the storage module is used for storing the reading characteristics and the reading contents of the user and storing the information acquired from a network channel; the extraction module is used for extracting information matched with the reading characteristics of the user from the storage module according to the reading characteristics of the user; the classification module is used for classifying the extracted information content according to the reading characteristics of the user; the comprehensive writing module is used for respectively carrying out comprehensive writing processing on the classified information and respectively generating a comprehensively written article aiming at each type of information; and the pushing module is used for pushing and displaying the comprehensively written article. The method is beneficial to realizing that the user can quickly, effectively and automatically acquire the information according with the reading characteristics.
Description
Technical Field
The invention relates to the field of information, in particular to a personalized customized writing system.
Background
Currently, there are two general ways for users to obtain information, one is a passive acceptance way: receiving and looking up the pushed information; the other is an active search mode: acquiring desired information through keyword search; however, the two information acquisition methods have the defect that the users in the two methods need to open a plurality of different links at a time for looking up. And the active searching mode also requires a certain searching capability of the user. Therefore, it is not easy for the user to quickly, effectively and automatically obtain the information conforming to the personality of the user.
Therefore, there is a need for a personalized customized authoring system to enable a user to quickly, efficiently and automatically obtain information that meets the reading characteristics of the user.
Disclosure of Invention
In view of this, the present application provides a personalized customized writing system, which is beneficial to the user to quickly, effectively and automatically obtain the information according with the reading characteristics.
The application provides a personalized customization writing system, includes:
the acquisition module is used for acquiring the reading habit and the reading content of the current user and acquiring information from a network channel;
the analysis module is used for analyzing the reading habits and the reading contents and forming the reading characteristics of the user according to the analysis;
the storage module is used for storing the reading habit and the reading content of the user and storing information acquired from a network channel;
the extraction module is used for extracting information matched with the reading characteristics of the user from the storage module according to the reading characteristics of the user;
the classification module is used for classifying the extracted information content according to the reading characteristics of the user;
the comprehensive writing module is used for respectively carrying out comprehensive writing processing on the classified information and respectively generating a comprehensively written article aiming at each type of information;
and the pushing module is used for pushing and displaying the comprehensively written article.
Therefore, the method and the device for automatically acquiring the information according with the reading characteristics of the user acquire the related information types and the information contents according with the reading characteristics of the user, respectively generate the comprehensively written articles for each type of information, and push the articles to the user, so that the user can quickly, effectively and automatically acquire the information according with the reading characteristics of the user.
Preferably, the system further comprises:
the selection module is used for providing selectable information types; the information acquisition module is also used for acquiring information respectively related to the information types according to the selected information types; and sending the information related to the information type to a classification module.
Therefore, the user can select the preferred information type, the information corresponding to the selected information type is transmitted to the classification module, and the extracted information content is classified through the classification module according to the reading characteristics of the user; and the comprehensive writing module is used for carrying out comprehensive writing and then pushing the comprehensive writing to the user through the pushing module.
Preferably, the selection module is further configured to receive information selected by the user and send the information selected by the user to the classification module.
Therefore, the user can directly select the favorite information, the selected information is transmitted to the classification module, and the extracted information content is classified through the classification module according to the reading characteristics of the user; and the comprehensive writing module is used for pushing the comprehensive writing to the user through the pushing module.
Preferably, the system further comprises:
the updating module is used for acquiring the latest reading habit and reading content of the user in real time and sending the latest reading habit and reading content to the analysis module; and the information acquisition module is used for acquiring information from a network channel in real time and sending the information to the storage module.
Therefore, the latest reading habit and reading content of the user can be obtained in real time through the updating module and are sent to the analysis module, so that the reading characteristic of the user can be updated in real time (the reading characteristic of the user is prevented from being solidified), the updating module is also used for obtaining information from a network channel in real time from a network, and the comprehensive article finally pushed to the user is enabled to be most in line with the reading characteristic of the user.
Preferably, the reading characteristics of the user include: time, place and information topic type of favorite reading of the user; and the types of the information topics which the user likes to read at different time and places.
Preferably, the extraction module is specifically configured to:
and according to the favorite information topic types of the user, extracting information matched with the favorite information topic types of the user from the storage module.
Therefore, the information matched with the information topic types preferred by the user and acquired from various channels is provided from the storage module.
Preferably, the classification module is specifically configured to:
classifying the information into information types respectively matched with different time and places according to the information topic types which are favored to be read by users at different time and places; and the system is used for classifying the information according to different types of the information topics at the same time and place.
Therefore, all the information is classified according to the reading characteristics of the user, and the push of the user is facilitated.
Preferably, the pushing module comprises:
the setting submodule is used for providing setting options in a push mode for the comprehensively written articles; wherein the push-form setting options include:
setting options which are automatically pushed according to the historical browsing habits of the user;
push time, push location, push topic type setting options.
Wherein, the automatic pushing according to the historical browsing habits of the user comprises the following steps:
automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place;
the push module further comprises:
the display sub-module is used for automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place when the setting options which are automatically pushed according to the historical browsing habits of the user are selected;
and when the setting options of the push time, the push place and the push topic type are selected, carrying out push display on the user according to the selected push time, the push place and the push topic type.
Therefore, the integrated article is pushed according to the reading habits of the user, so that the user can quickly, effectively and automatically acquire the information according with the historical browsing habits of the user. And the user can also obtain corresponding push according to the current favorite push time, push place and push topic type.
Preferably, the pushing module is further configured to push the corresponding comprehensively written article according to the set pushing time.
Therefore, corresponding pushing time can be set according to reading requirements to carry out automatic pushing.
Preferably, the comprehensive writing module includes:
the information association submodule is used for respectively acquiring the internal relation of the information data of each type of information aiming at each type of classified information and performing information association on the information data;
the data extraction submodule is used for processing the information related to the information of each type of information so as to extract information fragments meeting the specified content value standard;
the article generation submodule is used for processing the associated information fragments acquired by the data query module to generate an article which is comprehensively written aiming at each type of information;
the article generation submodule is specifically configured to, for each type of information, respectively:
A. forming a knowledge graph of graphical representation according to the knowledge correlation of the content values of the related information segments; the nodes in the graph represent content value points, and connecting lines among the points in the graph represent association relations among the content value points;
B. traversing the content value points in the knowledge graph according to the connection relation between the points in the knowledge graph by taking any content value point in the knowledge graph as a starting point to obtain an optimal path consisting of the content value points and the connection relation between the points;
C. and generating a comprehensive written article according to the information segment corresponding to the path.
From the above, the technical features of the present application can generate a plurality of articles that are composed for each type of information.
Preferably, the selection module is further configured to provide other selectable user reading feature images;
when other user reading feature images are selected:
the acquisition module is also used for acquiring the reading habits and the reading contents of other users;
the analysis module is also used for analyzing the reading habits and the reading contents of other users and forming the reading characteristics of the other users according to the reading habits and the reading contents;
the storage module is also used for storing the reading characteristics and the reading contents of the other users;
the extracting module is also used for extracting information matched with the reading characteristics of other users from the storage module according to the reading characteristics of the other users;
the classification module is also used for classifying the extracted information content according to the reading characteristics of other users;
the comprehensive writing module is also used for respectively carrying out comprehensive writing processing on the classified information of other users and respectively generating a comprehensively written article aiming at each type of information;
the pushing module is also used for pushing and displaying the articles which are comprehensively written on the information browsed by other users to the current user.
Therefore, by comprehensively writing and pushing the information which is favorite to be read by other users, the current user can quickly acquire the content of the information which is favorite to be read by other users by browsing the comprehensive articles.
In summary, the personalized customized writing system provided by the application acquires the relevant information types and information contents according to the reading characteristics of the user, respectively generates a comprehensively written article for each type of information, and pushes the article to the user, thereby being beneficial to realizing that the user can quickly, effectively and automatically acquire the information according with the reading characteristics. And the user can also select the type of the information preferred by the user or the information to be comprehensively written by the comprehensive writing module and then pushed to the user by the pushing module. And timing pushing can be set, and in addition, reading information of reading preferences of other users can be comprehensively processed according to needs and then sent to the current user for browsing. Therefore, the method is beneficial to realizing that the user can quickly, effectively and automatically acquire the information which the user wants to browse.
Drawings
Fig. 1 is a schematic structural diagram of a personalized customized authoring system according to an embodiment of the present application.
Detailed Description
The present application will be described below with reference to the drawings in the embodiments of the present application.
Example one
The application provides a personalized customization writing system, includes:
an obtaining module 100, configured to obtain reading habits (including reading time and reading location) and reading contents of a current user, and information obtained from a network channel; wherein, the information obtained from the network channel comprises: acquiring data of different time, different types and different channel sources; or acquiring data of specified time, specified type and/or specified channel source. Therefore, data can be acquired in a non-differentiated manner (the acquired data is wider and comprehensive), and data of specified time, specified type and/or specified channel source can be acquired according to needs (the acquired data is targeted, and the subsequent processing is faster and more convenient). In addition, the crawling may be performed according to a certain algorithm or strategy, for example, crawling may be performed for information that the popularity/attention degree of different time periods exceeds a set value. An analysis module 200, configured to analyze the reading habits and the reading contents, and form a reading characteristic of the user according to the analysis; wherein the reading characteristics of the user include: time, place and information topic type of the user favorite reading; and the types of the information topics which the user likes to read at different time and places.
The storage module 300 is used for storing the reading characteristics and the reading contents of the user, and storing the information acquired from the network channel.
An extracting module 400, configured to extract, according to a reading feature of a user, information matching the reading feature of the user from the storage module; the extraction module 400 is specifically configured to: and according to the favorite information topic types of the user, extracting the information matched with the favorite information topic types of the user from the storage module.
A classification module 500, configured to classify the extracted information content according to the user reading characteristics; the classification module 500 is specifically configured to: classifying the information into information types respectively matched with different times and places according to the information topic types which are favored to be read by users at different times and places; and the system is used for classifying the information according to different types of the information topics at the same time and place.
The comprehensive writing module 600 is configured to perform comprehensive writing processing on the classified information, and generate a comprehensively written article for each type of information; the comprehensive writing module 600 specifically includes:
the information association submodule is used for respectively acquiring the internal relation of the information data of each type of information aiming at each type of classified information and performing information association on the information data; an intrinsic connection is here a connection between events, people, places or event types described by information content. This link is determined by a neural network model algorithm and can be understood and agreed upon by a human reader or editor.
The data extraction submodule is used for processing the information related to the information of each type of information so as to extract information fragments meeting the specified content value standard; the judgment of the content value is based on the processing of a neural network model trained by massive corpora. The relevant models are continuously trained by a machine learning system in an unsupervised learning mode. The internal data of the content value is described as a high-dimensional mathematical model based on content semantics, and the related value parameters comprise events, participatory or related people, event occurrence places, time, event progress, event background and the like described in the information content.
And the article generation sub-module is used for processing the associated information segments acquired by the data query module to generate an article which is comprehensively written aiming at each type of information. The method is specifically used for:
A. forming a knowledge graph of graphical representation according to the knowledge correlation of the content values of the related information segments; the nodes in the graph represent content value points, and connecting lines among the points in the graph represent association relations among the content value points; for example, for 2018/04/23, in case of terrorist attack events caused by minivan in toronto, canada, the system provides to learn a large amount of new information contents, and the common phrase of "VAN" is related to canada, terrorists, terrorist events, and terrorist attacks. This learning process updates the connotation and extension of the word van.
B. Traversing the content value points in the knowledge graph according to the connection relation between the points in the knowledge graph by taking any content value point in the knowledge graph as a starting point to obtain an optimal path consisting of the content value points and the connection relation between the points;
C. and generating a comprehensively written article according to the information segment corresponding to the path, and displaying the comprehensively written article to the user.
Among them, the optimal criteria in B may involve: fluency of connection between sentences and paragraphs, richness of vocabulary (richness of words for articles, the score is higher), length of articles (length of news information articles should not be too long or too short), relative density (wide coverage, concise articles and higher score), richness (more covered subjects and higher score), and the like.
And the pushing module 700 is configured to push and display the comprehensively written article. The pushing module 700 includes a setting sub-module, configured to provide a setting option for a pushing form of a synthetically written article; wherein the push-form setting options include:
setting options which are automatically pushed according to the historical browsing habits of the user;
push time, push location, push topic type setting options.
Wherein, the automatic pushing according to the historical browsing habits of the user comprises the following steps:
automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place;
the push module further comprises:
the display sub-module is used for automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place when the setting options which are automatically pushed according to the historical browsing habits of the user are selected;
and when the setting options of the push time, the push place and the push topic type are selected, carrying out push display on the user according to the selected push time, the push place and the push topic type.
Wherein the system further comprises:
a selection module 800 for providing selectable information types; the information acquisition module is also used for acquiring information respectively related to the information types according to the selected information types; and sending the information related to the information type to a classification module. Therefore, the user can select the preferred information type, the information corresponding to the selected information type is transmitted to the classification module, and the extracted information content is classified through the classification module according to the reading characteristics of the user; and the comprehensive writing module is used for pushing the comprehensive writing to the user through the pushing module.
The selecting module 800 is further configured to receive information selected by a user, and send the information selected by the user to the classifying module. Therefore, the user can directly select the information of the user's preference, the selected information is transmitted to the classification module, and the extracted information content is classified through the classification module according to the reading characteristics of the user; and the comprehensive writing module is used for carrying out comprehensive writing and then pushing the comprehensive writing to the user through the pushing module.
Wherein the system further comprises:
the updating module 900 is used for acquiring the latest reading habits and reading contents of the user in real time and sending the latest reading habits and reading contents to the analysis module; and the system is used for acquiring information from a network channel in real time and sending the information to the storage module. Therefore, the updating module 900 can obtain the latest reading habits and reading contents of the user in real time and send the latest reading habits and reading contents to the analysis module, so that the reading characteristics of the user can be updated in real time (the reading characteristics of the user are prevented from being solidified), and the updating module is further used for obtaining information from a network channel in real time from the network, so that the integrated article finally pushed to the user is the most suitable for the reading characteristics of the user.
Wherein, the selection module 800 is further configured to provide other selectable user reading feature images; when other user reading feature images are selected;
the obtaining module 100 is further configured to obtain reading habits and reading contents of other users;
the analysis module 200 is further configured to analyze the reading habits and the reading contents of other users, and accordingly form reading characteristics of the other users;
the storage module 300 is further configured to store the reading characteristics and the reading contents of the other users;
the extracting module 400 is further configured to extract information matched with the reading characteristics of the other users from the storage module according to the reading characteristics of the other users;
the classification module 500 is further configured to classify the extracted information content according to the reading characteristics of other users;
the comprehensive writing module 600 is further configured to perform comprehensive writing processing on the classified information of other users, and generate a comprehensively written article for each type of information;
the pushing module 700 is further configured to push and display the article after the information browsed by other users is comprehensively written to the current user.
Therefore, by comprehensively writing and pushing the information which is favorite to be read by other users, the current user can browse the comprehensive articles, and the user can quickly acquire the content of the information which is favorite to be read by other users.
In summary, the personalized customized writing system provided by the application acquires the relevant information types and information contents according to the reading characteristics of the user, respectively generates a comprehensively written article for each type of information, and pushes the article to the user, thereby being beneficial to realizing that the user can quickly, effectively and automatically acquire the information according with the reading characteristics. And the user can also select the type of the information preferred by the user or the information to be comprehensively written by the comprehensive writing module and then pushed to the user by the pushing module. And timing push can be set, and in addition, information of reading hobby of other users can be comprehensively processed according to needs and then sent to the current user for browsing. Therefore, the method is beneficial to realizing that the user can quickly, effectively and automatically acquire the information which the user wants to browse.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A personalized custom authoring system, comprising:
the acquisition module is used for acquiring the reading habit and the reading content of the current user and acquiring information from a network channel;
the analysis module is used for analyzing the reading habits and the reading contents and forming the reading characteristics of the user according to the analysis;
the storage module is used for storing the reading habit and the reading content of the user and storing information acquired from a network channel;
the extraction module is used for extracting information matched with the reading characteristics of the user from the storage module according to the reading characteristics of the user;
the classification module is used for classifying the extracted information content according to the reading characteristics of the user;
the comprehensive writing module is used for respectively carrying out comprehensive writing processing on the classified information and respectively generating a comprehensively written article aiming at each type of information;
the pushing module is used for pushing and displaying the comprehensively written article;
the reading characteristics of the user include: time, place and information topic type of the user favorite reading; and the information topic types which are favored to be read by the user at different time and place;
the comprehensive writing module comprises:
the information association submodule is used for respectively acquiring the internal relation of the information data of each type of information aiming at each type of classified information and performing information association on the information data;
the data extraction submodule is used for processing the information related to the information of each type of information so as to extract information fragments meeting the specified content value standard;
the article generation submodule is used for processing the associated information fragments acquired by the data query module to generate an article which is comprehensively written aiming at each type of information;
the article generation submodule is specifically configured to, for each type of information, respectively:
A. forming a knowledge graph of graphical representation according to the knowledge correlation of the content values of the related information segments; the nodes in the graph represent content value points, and connecting lines among the points in the graph represent association relations among the content value points;
B. traversing the content value points in the knowledge graph by taking any content value point in the knowledge graph as a starting point according to the connection relation between the points in the knowledge graph so as to obtain an optimal path consisting of the content value points and the connection relation between the points;
C. and generating a comprehensive written article according to the information segment corresponding to the path.
2. The system of claim 1, further comprising:
the selection module is used for providing selectable information types; the information acquisition module is also used for acquiring information related to the information type according to the selected information type; and sending the information related to the information type to a classification module.
3. The system of claim 2, wherein the selection module is further configured to receive information selected by the user and send the information selected by the user to the classification module.
4. The system of claim 1, further comprising:
the updating module is used for acquiring the latest reading habit and reading content of the user in real time and sending the latest reading habit and reading content to the analysis module; and the system is used for acquiring information from a network channel in real time and sending the information to the storage module.
5. The system of claim 1, wherein the extraction module is specifically configured to:
and according to the favorite information topic types of the user, extracting the information matched with the favorite information topic types of the user from the storage module.
6. The system of claim 1, wherein the classification module is specifically configured to:
classifying the information into information types respectively matched with different time and places according to the information topic types which are favored to be read by users at different time and places; and the system is used for classifying the information according to different types of the information topics at the same time and place.
7. The system of claim 1, wherein the push module comprises:
the setting submodule is used for providing setting options in a push mode for the comprehensively written articles; wherein the push-type setting options include:
setting options which are automatically pushed according to the historical browsing habits of the user;
setting options of push time, push place and push topic type;
wherein, the automatic pushing according to the historical browsing habits of the user comprises the following steps:
automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place;
the push module further comprises:
the display sub-module is used for automatically pushing and displaying the comprehensively written articles to the user terminal at corresponding time and place according to the types of information topics which the user likes to read at different time and place when the setting options which are automatically pushed according to the historical browsing habits of the user are selected;
and when the setting options of the push time, the push place and the push topic type are selected, carrying out push display on the user according to the selected push time, the push place and the push topic type.
8. A system according to claim 2 or 3, characterized in that:
the selection module is also used for providing other selectable user reading characteristic pictures; when other user reading feature images are selected:
the acquisition module is also used for acquiring the reading habits and the reading contents of other users;
the analysis module is also used for analyzing the reading habits and the reading contents of other users and forming the reading characteristics of the other users according to the reading habits and the reading contents;
the storage module is also used for storing the reading characteristics and the reading contents of the other users;
the extracting module is also used for extracting information matched with the reading characteristics of other users from the storage module according to the reading characteristics of the other users;
the classification module is also used for classifying the extracted information content according to the reading characteristics of other users;
the comprehensive writing module is also used for respectively carrying out comprehensive writing processing on the classified information of other users and respectively generating a comprehensively written article aiming at each type of information;
the pushing module is also used for pushing and displaying the articles which are comprehensively written on the information browsed by other users to the current user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810619317.1A CN109388708B (en) | 2018-06-15 | 2018-06-15 | Personalized customized writing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810619317.1A CN109388708B (en) | 2018-06-15 | 2018-06-15 | Personalized customized writing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109388708A CN109388708A (en) | 2019-02-26 |
| CN109388708B true CN109388708B (en) | 2022-05-31 |
Family
ID=65417502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810619317.1A Active CN109388708B (en) | 2018-06-15 | 2018-06-15 | Personalized customized writing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109388708B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245339B (en) * | 2019-06-20 | 2023-04-18 | 北京百度网讯科技有限公司 | Article generation method, article generation device, article generation equipment and storage medium |
| 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831220A (en) * | 2012-08-23 | 2012-12-19 | 江苏物联网研究发展中心 | Subject-oriented customized news information extraction system |
| CN104054075A (en) * | 2011-12-06 | 2014-09-17 | 派赛普申合伙公司 | Text mining, analysis and output system |
| CN104765842A (en) * | 2015-04-15 | 2015-07-08 | 中山大学 | Optimum study scheme pushing method and system |
| CN105760495A (en) * | 2016-02-17 | 2016-07-13 | 扬州大学 | Method for carrying out exploratory search for bug problem based on knowledge map |
| CN106844322A (en) * | 2017-01-22 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Intelligent article generation method and device |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2454290C (en) * | 2003-12-29 | 2013-05-21 | Ibm Canada Limited-Ibm Canada Limitee | Graphical user interface (gui) script generation and documentation |
| US8760318B2 (en) * | 2011-12-06 | 2014-06-24 | Optotraffic, Llc | Method for traffic monitoring and secure processing of traffic violations |
| CN106777364A (en) * | 2017-01-22 | 2017-05-31 | 竹间智能科技（上海）有限公司 | Artificial intelligence response method and device that topic drives |
| CN107943774A (en) * | 2017-11-20 | 2018-04-20 | 北京百度网讯科技有限公司 | article generation method and device |
-
2018
- 2018-06-15 CN CN201810619317.1A patent/CN109388708B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104054075A (en) * | 2011-12-06 | 2014-09-17 | 派赛普申合伙公司 | Text mining, analysis and output system |
| CN102831220A (en) * | 2012-08-23 | 2012-12-19 | 江苏物联网研究发展中心 | Subject-oriented customized news information extraction system |
| CN104765842A (en) * | 2015-04-15 | 2015-07-08 | 中山大学 | Optimum study scheme pushing method and system |
| CN105760495A (en) * | 2016-02-17 | 2016-07-13 | 扬州大学 | Method for carrying out exploratory search for bug problem based on knowledge map |
| CN106844322A (en) * | 2017-01-22 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Intelligent article generation method and device |
| CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109388708A (en) | 2019-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10831808B2 (en) | Method and system for sentiment analysis of information | |
| CN109255053B (en) | Resource searching method, device, terminal, server and computer readable storage medium | |
| CN105068661B (en) | Man-machine interaction method based on artificial intelligence and system | |
| CN104933113B (en) | A kind of expression input method and device based on semantic understanding | |
| CN110059271B (en) | Searching method and device applying tag knowledge network | |
| US10217058B2 (en) | Predicting interesting things and concepts in content | |
| CN106227815B (en) | Multi-modal clue personalized application program function recommendation method and system | |
| WO2016179938A1 (en) | Method and device for question recommendation | |
| US8457368B2 (en) | System and method of object recognition and database population for video indexing | |
| WO2017088245A1 (en) | Method and apparatus for recommending reference document | |
| US20150154204A1 (en) | Signature-based system and method for generation of personalized multimedia channels | |
| WO2021098648A1 (en) | Text recommendation method, apparatus and device, and medium | |
| CN106970991B (en) | Similar application identification method and device, application search recommendation method and server | |
| CN111414479A (en) | Label extraction method based on short text clustering technology | |
| CN104394057A (en) | Expression recommendation method and device | |
| KR20130119246A (en) | Apparatus and method for recommending contents based sensibility | |
| CN111125528B (en) | Information recommendation method and device | |
| CN109992781B (en) | Text feature processing method and device and storage medium | |
| CN111684815B (en) | Message pushing method and device based on video data and computer storage medium | |
| CN112929746B (en) | Video generation method and device, storage medium and electronic equipment | |
| US9176993B2 (en) | Efficiently identifying images, videos, songs or documents most relevant to the user using binary search trees on attributes for guiding relevance feedback | |
| CN109299277A (en) | The analysis of public opinion method, server and computer readable storage medium | |
| CN109388708B (en) | Personalized customized writing system | |
| CN113596579B (en) | Video generation method, device, medium and electronic equipment | |
| CN112199932A (en) | PPT generation method, device, computer-readable storage medium and processor |
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 |