CN106649491A - Natural language analysis technology-based information pushing system - Google Patents
Natural language analysis technology-based information pushing system Download PDFInfo
- Publication number
- CN106649491A CN106649491A CN201610880560.XA CN201610880560A CN106649491A CN 106649491 A CN106649491 A CN 106649491A CN 201610880560 A CN201610880560 A CN 201610880560A CN 106649491 A CN106649491 A CN 106649491A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- natural language
- data
- analysis technology
- 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.)
- Pending
Links
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
- G06F16/33—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
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The invention discloses a natural language analysis technology-based information pushing system. The system comprises the following modules: a data integration module used for performing 24-hour continuous acquisition on whole network information, a data storage module used for storing the information acquired by the data integration module to a database, a data processing module used for performing main text extraction, clustering, impurity removal and typesetting optimization on the acquired and stored data and performing popularity analysis to form a special topic, a user portrait model which builds a user distinguishing degree model through behaviors and operations of a user at a client, learns and knows reading interest information of the user and predicts reading preferences of the user, and an information pushing module used for performing intelligent matching according to the reading preferences of the user and the information in the database and pushing the matched information to the user. The natural language analysis technology-based information pushing system is low in pushing operation cost and high in recommendation accuracy.
Description
Technical field
The present invention relates to recommended engine field, more particularly to a kind of information pushing system based on natural language analysis technology
System.
Background technology
Today's society, produces daily substantial amounts of Domestic News content, and arranges relatively unique original picture and text, video hurdle
Mesh, news editor team therefrom filters out comparative good-quality, popular information content and is pushed to user, or, polymerization third party is new
The resource of platform is heard, user individual information content is pushed to according to the reading behavior of user record, the former push mode
The disadvantage is that, pushing, rule is single, high-quality, popular information content are pushed to into everyone user that necessarily can not fit needs
Ask;The push mode of the latter is the disadvantage is that, the resource of polymerization third party's news platform, is polymerized relatively costly, and user reads
Read custom to be limited by third party's news platform, it is impossible to go deep into the potential interest of digging user.
Various information doping on internet, and renewal speed is very fast, need to put into substantial amounts of manpower enter edlin and
Screening operation, operation cost is very high;Reading interest analysis to user is not accurate enough, and being pushed to the information content of user does not have
Fit with user's request, can if things go on like this cause user's reading interest to decline, customer volume is reduced.
The content of the invention
To overcome the deficiencies in the prior art, the purpose of the present invention to be:A kind of letter based on natural language analysis technology is provided
Breath supplying system, temperature analysis is carried out by algorithm to article, is compiled aspect in content and is reduced manual intervention, to personalized recommendation
Effect carries out self-recision, improves the degree of accuracy of recommendation results.
Technical problem in order to solve background technology, the invention provides a kind of letter based on natural language analysis technology
Breath supplying system, including with lower module:
Data Integration module, for carrying out 24 hours uninterrupted samplings to the whole network information;
Database is arrived in data memory module, the information storage for the Data Integration module to be gathered;
Data processing module, for the data of collection warehouse-in to be carried out with text extracting, cluster, decontamination, typesetting optimization, and
Carry out temperature analysis, composition special topic;
User draw a portrait model, by user client behavior and operation, it is established that user's discrimination model, study
The reading interest information of user is solved, and then the reading preference to user is predicted;
Info push module, for the information content in the reading preference of user, with database intelligent is carried out
Match somebody with somebody, and by the information pushing in matching to user.
Further, user's portrait model also includes amending unit, and for the change of the user preferences that follow up, amendment is used
The reading preference result at family.
Specifically, the data processing module is by natural language semantic classification technique and the knot of keyword configuration rule
Close, realize that the refinement of information is analyzed and classified.
The information transmission system based on natural language analysis technology of the present invention also includes interface module, the interface module
Including management data interface unit, application system data interface unit and index data interface unit.
Using above-mentioned technical proposal, the information transmission system based on natural language analysis technology of the present invention is with syndication
Client is carrier, on the basis of integrated optimization the whole network information article, by algorithm semantic analysis, carries out text to article and takes out
Take, cluster, decontamination, typesetting optimization, and article temperature is analyzed, while setting up each user according to user's reading behavior
Personal portrait, then for personal information such as interest, region, the incomes in different user portrait, it is established that user individual
Recommended models, then by means such as big data, artificial intelligence, the interest of study understanding user is inclined within the time as short as possible
Get well, and the reading hobby to user is predicted, and is finally targetedly pushed out reading the excellent of match those with user
Matter information.Both greatly reduce human cost so as to reach, the purpose of information can be pushed according to user's request again.
Description of the drawings
In order to be illustrated more clearly that technical scheme, below will be to wanting needed for embodiment or description of the prior art
The accompanying drawing for using is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, right
For those of ordinary skill in the art, on the premise of not paying creative work, can be obtaining it according to these accompanying drawings
Its accompanying drawing.
Fig. 1 is the system block diagram of the information transmission system based on natural language analysis technology provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than the embodiment of whole.It is based on
Embodiment in the present invention, those of ordinary skill in the art obtained on the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
Embodiment:Fig. 1 is that the information transmission system based on natural language analysis technology provided in an embodiment of the present invention is
System block diagram, it can be seen that the information transmission system based on natural language analysis technology is included with lower module:
Data Integration module, for carrying out 24 hours uninterrupted samplings to the whole network information;
Database is arrived in data memory module, the information storage for the Data Integration module to be gathered;
Data processing module, for the data of collection warehouse-in to be carried out with text extracting, cluster, decontamination, typesetting optimization, and
Carry out temperature analysis, composition special topic;
User draw a portrait model, by user client behavior and operation, it is established that user's discrimination model, study
The reading interest information of user is solved, and then the reading preference to user is predicted;
Info push module, for the information content in the reading preference of user, with database intelligent is carried out
Match somebody with somebody, and by the information pushing in matching to user.
Further, user's portrait model also includes amending unit, and for the change of the user preferences that follow up, amendment is used
The reading preference result at family.
Specifically, the data processing module is by natural language semantic classification technique and the knot of keyword configuration rule
Close, realize that the refinement of information is analyzed and classified.
The information transmission system based on natural language analysis technology that the present embodiment is provided also includes interface module, described to connect
Mouth mold block includes management data interface unit, application system data interface unit and index data interface unit.
The present invention relates to a kind of recommended engine technology based on the process of natural language intellectual analysis.First, data backstage meeting
24 hours uninterrupted sampling whole network datas, and carry out text extracting, cluster, decontamination, typesetting optimization, temperature to adopting the data come
The intellectual analysis such as analysis are processed, and the data after optimization processing can enter spare contents storehouse.After user opens client, after
Platform can set up different user's portraits according to a series of reading behaviors of user and operation, and persistently carry out self-recision:This
Invention carries out study prediction to the reading preference of user with most short learning time, and carrying out to user behavior point of can continuing
Analysis, the in time change of follow-up user preferences, improves the order of accuarcy that information is recommended, finally according to the user recorded in user's portrait
Information to match the information that user may be interested from content library, is targetedly pushed to user.
The present invention is directed to the problem that existing human-edited recommends operation cost big and personalized recommendation is of low quality,
On the basis of integrating the whole network information content, by algorithm semantic analysis, text extracting, cluster, decontamination, typesetting are carried out to article
Optimization, and article temperature is analyzed, special topic is set up, without the need for arranging a large amount of editors to carry out content as present media
Manually compile, both ensure that the quality of content, artificial operation cost is reduced again, the article for then again crossing algorithm process with it is big
The user that data analysis draws reads match those, is pushed to user's article interested.
Above disclosed is only several preferred embodiments of the present invention, can not limit the present invention's with this certainly
Interest field, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (4)
1. a kind of information transmission system based on natural language analysis technology, it is characterised in that include with lower module:
Data Integration module, for carrying out 24 hours uninterrupted samplings to the whole network information;
Database is arrived in data memory module, the information storage for the Data Integration module to be gathered;
Data processing module, for the data of collection warehouse-in to be carried out with text extracting, cluster, decontamination, typesetting optimization, and is carried out
Temperature is analyzed, composition special topic;
User draw a portrait model, by user client behavior and operation, it is established that user's discrimination model, study understand use
The reading interest information at family, and then the reading preference to user is predicted;
Info push module, for according to the reading preference of user, with the information content in database carry out it is intelligent match, and
By the information pushing in matching to user.
2. the information transmission system based on natural language analysis technology according to claim 1, it is characterised in that the use
Family portrait model also includes amending unit, for the change of the user preferences that follow up, corrects the reading preference result of user.
3. the information transmission system based on natural language analysis technology according to claim 1, it is characterised in that the number
According to the combination that processing module passes through natural language semantic classification technique and keyword configuration rule, realize that the refinement to information is analyzed
And classify.
4. the information transmission system based on natural language analysis technology according to any one in claim 1-3, it is special
Levy and be, also including interface module, the interface module include management data interface unit, application system data interface unit and
Index data interface unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610880560.XA CN106649491A (en) | 2016-09-30 | 2016-09-30 | Natural language analysis technology-based information pushing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610880560.XA CN106649491A (en) | 2016-09-30 | 2016-09-30 | Natural language analysis technology-based information pushing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106649491A true CN106649491A (en) | 2017-05-10 |
Family
ID=58853791
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610880560.XA Pending CN106649491A (en) | 2016-09-30 | 2016-09-30 | Natural language analysis technology-based information pushing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106649491A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
CN107491486A (en) * | 2017-07-17 | 2017-12-19 | 广州特道信息科技有限公司 | User's portrait construction method and device |
CN107992478A (en) * | 2017-11-30 | 2018-05-04 | 百度在线网络技术(北京)有限公司 | The method and apparatus for determining focus incident |
CN109784961A (en) * | 2017-11-13 | 2019-05-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device |
CN110188273A (en) * | 2019-05-27 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Notification method, device, server and the readable medium of information content |
CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
CN111612414A (en) * | 2020-04-24 | 2020-09-01 | 上海第一财经传媒有限公司 | Mobile media application management system |
CN114205323A (en) * | 2021-12-13 | 2022-03-18 | 厦门傲播网络科技有限公司 | Sports message pushing processing method and system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110029514A1 (en) * | 2008-07-31 | 2011-02-03 | Larry Kerschberg | Case-Based Framework For Collaborative Semantic Search |
CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
CN103782291A (en) * | 2011-07-26 | 2014-05-07 | 国际商业机器公司 | Customization of natural language processing engine |
-
2016
- 2016-09-30 CN CN201610880560.XA patent/CN106649491A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110029514A1 (en) * | 2008-07-31 | 2011-02-03 | Larry Kerschberg | Case-Based Framework For Collaborative Semantic Search |
CN103782291A (en) * | 2011-07-26 | 2014-05-07 | 国际商业机器公司 | Customization of natural language processing engine |
CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
CN107491486A (en) * | 2017-07-17 | 2017-12-19 | 广州特道信息科技有限公司 | User's portrait construction method and device |
CN109784961A (en) * | 2017-11-13 | 2019-05-21 | 阿里巴巴集团控股有限公司 | A kind of data processing method and device |
CN107992478A (en) * | 2017-11-30 | 2018-05-04 | 百度在线网络技术(北京)有限公司 | The method and apparatus for determining focus incident |
US10747771B2 (en) | 2017-11-30 | 2020-08-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining hot event |
CN110188273A (en) * | 2019-05-27 | 2019-08-30 | 北京字节跳动网络技术有限公司 | Notification method, device, server and the readable medium of information content |
CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
CN111612414A (en) * | 2020-04-24 | 2020-09-01 | 上海第一财经传媒有限公司 | Mobile media application management system |
CN111612414B (en) * | 2020-04-24 | 2024-04-02 | 上海第一财经传媒有限公司 | Mobile media application management system |
CN114205323A (en) * | 2021-12-13 | 2022-03-18 | 厦门傲播网络科技有限公司 | Sports message pushing processing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106649491A (en) | Natural language analysis technology-based information pushing system | |
CN104933113B (en) | A kind of expression input method and device based on semantic understanding | |
CN110489395A (en) | Automatically the method for multi-source heterogeneous data knowledge is obtained | |
CN108009228A (en) | A kind of method to set up of content tab, device and storage medium | |
US11640583B2 (en) | Generation of user profile from source code | |
CN105913072A (en) | Training method of video classification model and video classification method | |
CN107451217A (en) | Information recommends method and device | |
CN109582945A (en) | Article generation method, device and storage medium | |
CN105989056B (en) | A kind of Chinese news recommender system | |
CN107885793A (en) | A kind of hot microblog topic analyzing and predicting method and system | |
CN108305180B (en) | Friend recommendation method and device | |
CN112231563B (en) | Content recommendation method, device and storage medium | |
CN111159341B (en) | Information recommendation method and device based on user investment and financial management preference | |
CN108780654A (en) | Generate the mobile thumbnail for video | |
CN110196945B (en) | Microblog user age prediction method based on LSTM and LeNet fusion | |
CN108280164B (en) | Short text filtering and classifying method based on category related words | |
CN111460162B (en) | Text classification method and device, terminal equipment and computer readable storage medium | |
CN112929746B (en) | Video generation method and device, storage medium and electronic equipment | |
CN113495959B (en) | Financial public opinion identification method and system based on text data | |
CN115114395A (en) | Content retrieval and model training method and device, electronic equipment and storage medium | |
CN111026866B (en) | Domain-oriented text information extraction clustering method, device and storage medium | |
CN109242042B (en) | Picture training sample mining method and device, terminal and computer readable storage medium | |
Hoyt et al. | PodcastRE Analytics: Using RSS to Study the Cultures and Norms of Podcasting. | |
CN109325175A (en) | Merge the news push method, device and equipment of microblogging interest digging | |
CN112989167B (en) | Method, device and equipment for identifying transport account and computer readable storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |