CN106354860A - Method for automatically labelling and pushing information resource based on label sets - Google Patents
Method for automatically labelling and pushing information resource based on label sets Download PDFInfo
- Publication number
- CN106354860A CN106354860A CN201610804361.0A CN201610804361A CN106354860A CN 106354860 A CN106354860 A CN 106354860A CN 201610804361 A CN201610804361 A CN 201610804361A CN 106354860 A CN106354860 A CN 106354860A
- Authority
- CN
- China
- Prior art keywords
- label
- resource
- information
- content
- tally set
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for automatically labelling and pushing an information resource based on label sets. The method includes the main steps that the information resource is positioned through a vector space model according to the dimensionality; data of the information resource is obtained; external-connection medium resource system resource labels and user behavior habit information resource labels are obtained through word segmentation processing; the labels are sequentially cleaned, short data packages are added into the labels, and the label sets are obtained; the label sets are input a quality evaluating system and subjected to vectorization indexing, and finally the external-connection medium resource system resource label set and the user behavior habit information resource label set are fed back to a label library to update label content; the external-connection medium resource system resource label set and the user behavior habit information resource label set are matched, and the label sets are pushed to a client side. In this way, the defects that in the prior art, the information resource cannot be effectively integrated, and high-quality internet information required by a user cannot be effectively arranged or mined or organized can be overcome.
Description
Technical field
The present invention relates to information resources automatic labeling label technical field, in particular it relates to the information resources based on tally set
Automatic labeling label the method for automatic push.
Background technology
In the face of the daily magnanimity information issued, current internet information already at a kind of irregular growing trend it
In, in the web2.0 epoch, network environment has become as non-linear, self-organizing a social network.The Internet has become complete
The maximum information resource database of ball, it has also caused that " information is general while the live and work giving people class brings revolutionary variation
Excessively " the problems such as " information puzzle ".The maximum characteristic in the Internet in web2.0 epoch is exactly to make full use of group wisdom, when more
When user is added to this collective, the importance of individual attribute will gradually be desalinated, individuality between mutual-action behavior and the pass between individuality
System will play prior effect.
The mutual-action behavior of people and network is increasingly becoming the main trend of internet development, and masses are as information consumer
Also become information producer, the information that brings while network Development is huge, the problems such as lower-quality information pours in simultaneously.That
, arrange, excavate, information that group weaves high-quality and user and needs are Internet service business, information processing brainstrust institute face
The unprecedented challenge faced.
Label, is regarded as an important component part in web2.0 epoch by everybody, but label is often treated as by a lot of people
One supplement of other products, seldom has and it is worth with the example carrying out deep excavation.
Label, is the custom to people, the extraordinary division using, is also to information resources theme and attribute
Plant succinct refinedly summary extraction, by the record of label, can be to the change of this network hotspot, for personal focus
Change can embody.So label being used as medium, being to realize the effective organizational integration of information resources, more preferably realizing information
The tool taken the initiative in offering a hand.
The research in this field for the prior art, also in the starting stage, lacks the achievement in research with height and depth,
And problem be there is also on Research Thinking.
During realizing the present invention, inventor finds at least to exist in prior art cannot be had to information resources
Imitate integrates it is impossible to effective arrangement, excavation or group weave high-quality and user's needs internet informations.
Content of the invention
It is an object of the invention to, for the problems referred to above, the information resources automatic labeling label based on tally set for the proposition are simultaneously certainly
The dynamic method pushing, to realize effectively arranging, to excavate or group weaves the excellent of the internet information that high-quality and user needs
Point.
For achieving the above object, the technical solution used in the present invention is: a kind of is automatically pasted based on the information resources of tally set
Label the method for automatic push, specifically include that
Step 1: application cartesian vector spatial model, resource information is pressed dimension by label and classifies, each classification label
Weights describe the position in this dimension for the resource information;
Step 2: crawled using reptile, subtitle recognition, video extraction and voice recognition mode, realize the automatic batch of resource information
Obtain;
Step 3: word segmentation processing is carried out by tag library, rule base and thesaurus storehouse, and then the label obtaining is ranked up
Cleaning, finally obtains the content tab meeting resource information theme and attribute, and gained content tab is added short packages, shape
Become content tab collection;
Step 4: using the behavioural habits information excavating label to user for step 1-3, obtain user behavior custom tally set;
Step 5: the resource information finally giving tally set and user behavior are accustomed to tally set input quality assessment system, to mark
Label are filtered and are screened, respectively according to static, dynamically indexed respectively, realize the vector quantization index of label, form static state
Label and dynamic labels, simultaneously these tag feedback to tag library, update its content, and the quality making tag library is in benign cycle
Formula ground improves, and realizes growing with each passing hour of tag library simultaneously, constantly includes the label of reaction era development trend, described dynamic labels
Can achieve timing automatic renewal, the manager's manual operation that is updated to of described static labels updates;
Step 6: content tab collection is mated with user behavior custom tally set, by tally set automatic push to client,
And content is pushed according to the resource information adjustment of client downloads.
Further, in step 1, described resource information is the resource information of external resource media resource system input, including literary composition
Basis, picture, audio or video resource content and its user's evaluation content.Further, described in step 5, label is filtered
With screening specifically, filter out misspelling, excessively chivalrous, point to mark fuzzy or that there is unsound mind-set
Sign, filter out and can concentrate the good high-quality label of the reusability expressing the source language message feature to indexing system.
Further, in step 6, content tab collection and user behavior custom tally set are carried out mate including, first paragraph coupling,
Contents semantic information is expressed in the label that the content that external media resource system is issued is filtrated to get by automatic labeling label technology,
Relevant information is stored in tally set, by data broadcasting, outer covering is transmitted;And second segment coupling, the personal happiness of user's expression
Good, leave dominant or recessive historical record on the terminal device, terminal unit filter out in broadcast short data stream limited can
The tally set of kind can be liked, viewer, after seeing label set content, casts out the full text not having energy to read in detail, from nearby
The full text having energy to read in detail is obtained in server.
Various embodiments of the present invention based on the information resources automatic labeling label of tally set and the method for automatic push, due to master
Including: information resources are positioned by dimension using vector space model;Information resources utilization reptile is crawled, captions are known
Not, the mode of video extraction and speech recognition, obtains information resources data;By tag library, rule base, thesaurus storehouse to obtaining
The data taking carries out word segmentation processing, obtains external media resource system resource tag and user behavior habits information resource tag;To mark
Label are ranked up cleaning, and label is added short packages, obtain meeting the external media resource system resource of asset topics and attribute
Tally set and user behavior habits information resource tag collection;By tally set input quality assessment system, tally set is screened,
And carry out vector quantization index, finally external media resource system resource tag collection and user behavior habits information resource tag collection are fed back
To tag library, update label substance;External media resource system resource tag collection and user behavior habits information resource tag collection are carried out
Coupling, tally set is pushed to client;Information resources effectively cannot be integrated such that it is able to overcome in prior art,
Cannot effectively arrange, excavate or group weaves the defect of the internet information that high-quality and user needs.
Other features and advantages of the present invention will illustrate in the following description, and, partly become from description
Obtain it is clear that or being understood by implementing the present invention.
Below by drawings and Examples, technical scheme is described in further detail.
Brief description
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for description, the reality with the present invention
Apply example and be used for explaining the present invention together, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the flute of the information resources automatic labeling label based on tally set described in the embodiment of the present invention the method for automatic push
Karr vector space model figure;
Fig. 2 is the letter of the information resources automatic labeling label based on tally set described in the embodiment of the present invention the method for automatic push
The integral frame figure of breath resource automatic labeling label;
Fig. 3 be the embodiment of the present invention described in the information resources automatic labeling label based on tally set and the method for automatic push from
Move labelled fundamental diagram;
Fig. 4 is the mark of the information resources automatic labeling label based on tally set described in the embodiment of the present invention the method for automatic push
Sign collection formation basic theory figure;
Fig. 5 is the information resources automatic labeling label based on tally set the making of the method for automatic push described in the embodiment of the present invention
With tally set description information resource position view;
Fig. 6 is the letter of the information resources automatic labeling label based on tally set described in the embodiment of the present invention the method for automatic push
Breath resource automatic push schematic diagram.
Specific embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated it will be appreciated that preferred reality described herein
Apply example to be merely to illustrate and explain the present invention, be not intended to limit the present invention.
Specifically, a kind of based on the information resources automatic labeling label of tally set and the method for automatic push, specifically include that
Step 1: application cartesian vector spatial model, resource information is pressed dimension by label and classifies, each classification label
Weights describe the position in this dimension for the resource information;
Step 2: crawled using reptile, subtitle recognition, video extraction and voice recognition mode, realize the automatic batch of resource information
Obtain;
Step 3: word segmentation processing is carried out by tag library, rule base and thesaurus storehouse, and then the label obtaining is ranked up
Cleaning, finally obtains the content tab meeting resource information theme and attribute, and gained content tab is added short packages, shape
Become content tab collection;
Step 4: using the behavioural habits information excavating label to user for step 1-3, obtain user behavior custom tally set;
Step 5: the resource information finally giving tally set and user behavior are accustomed to tally set input quality assessment system, to mark
Label are filtered and are screened, respectively according to static, dynamically indexed respectively, realize the vector quantization index of label, form static state
Label and dynamic labels, simultaneously these tag feedback to tag library, update its content, and the quality making tag library is in benign cycle
Formula ground improves, and realizes growing with each passing hour of tag library simultaneously, constantly includes the label of reaction era development trend, described dynamic labels
Can achieve timing automatic renewal, the manager's manual operation that is updated to of described static labels updates;
Step 6: content tab collection is mated with user behavior custom tally set, by tally set automatic push to client,
And content is pushed according to the resource information adjustment of client downloads.
Further, in step 1, described resource information is the resource information of external resource media resource system input, including literary composition
Basis, picture, audio or video resource content and its user's evaluation content.Further, described in step 5, label is filtered
With screening specifically, filter out misspelling, excessively chivalrous, point to mark fuzzy or that there is unsound mind-set
Sign, filter out and can concentrate the good high-quality label of the reusability expressing the source language message feature to indexing system.
Further, in step 6, content tab collection and user behavior custom tally set are carried out mate including, first paragraph coupling,
Contents semantic information is expressed in the label that the content that external media resource system is issued is filtrated to get by automatic labeling label technology,
Relevant information is stored in tally set, by data broadcasting, outer covering is transmitted;And second segment coupling, the personal happiness of user's expression
Good, leave dominant or recessive historical record on the terminal device, terminal unit filter out in broadcast short data stream limited can
The tally set of kind can be liked, viewer, after seeing label set content, casts out the full text not having energy to read in detail, from nearby
The full text having energy to read in detail is obtained in server.
In conjunction with Fig. 1, nowadays traditional being difficult to according to the standard that cataloguing carries out classification integration to matchmaker's standing breath of China's broadcasting and TV
The matchmaker's standing organizing current rapid growth ceases, the Internet of now, is also badly in need of a kind of letter being capable of more efficient integration information
Breath group organization model.
Article one, resource information not necessarily definitely belongs to certain classification, may belong to multiple classification, therefore applies Descartes
Vector space model, using the resource consolidation advantage such as the motility of label, magnanimity, simplicity, resource information is passed through label
By dimension classification, the weights of each classification label can describe the position in this dimension for the resource information, so pass through vector quantization
The management to resource realized by label, had both improve the efficiency of resource publisher, and had reduced the complexity of its work, facilitates user to examine again
Rope finds relevant information resource, is more beneficial for each big media resource system and realizes the personalized ventilation system to user.
Label embodies similarity in interest, thinking, expression way for the user, and user adds label and user can be helped to remember
Record its focus, as retrieval using entrance or other users that this is also interested in provide beneficial to retrieval
Entrance, can be divided into static labels, dynamic labels according to tag attributes, after the completion of such as one TV play shoots, director, master
Drill, the information such as manufacturing company will not change, so referred to as static labels;TV play makes can be put down in different after finishing
Platform broadcasts, and repeatedly broadcasts, and the viewer ship broadcasted, number of clicks are not fix every time, referred to as dynamic labels.
By arranging label, first, the content of retrieval can be made closer to theme, improve the accuracy rate of retrieval and look into complete
Rate.Second, increase visit capacity, add the label related to theme, can allow viewer more easily by associated resource information with
Tag search is to target resource.3rd, convenient recommendation, actively find similar resource, common hobby can have been found by label
User with Focus Area.
At present, macroscopically more collecting substantial amounts of label easily, however, lacking quality surveillance mechanism to control
Label quality processed, leads to the reusability outstanding problem of label, and is mainly client to the application source of label at present
The label that user produces is it is difficult to the value of maximized embodiment label, so how both to be assisted by the mechanism of automatization
User improves the quality of label, just sticks for resource when resource is issued simultaneously and suitably describes its core content theme and resource
The label of attribute, and it is classified as static labels and dynamic labels are indexed respectively, it is to realize resource to effectively integrate, improve
Recall precision and the key issue of recommendation service.
In conjunction with Fig. 2, design the automatic labeling label system of self feed back, investigate historical behavior record and the information money of user simultaneously
The situation in source, by the feedback learning repeatedly of system, sets up high-quality tag library, realizes label and automatically indexes mechanism.Should
Label automatic indexing technology can extract label it is also possible to identify picture and video using ocr technology from content of text messages
Caption information, extracts respective labels.The text of broadcasting and TV, the Internet and mobile network end, picture, sound therefore can be applied to
Frequently, the various information resource management system such as video.
In conjunction with Fig. 3, after external media resource system input information resource, crawl first with reptile, subtitle recognition, video
Extraction, speech recognition, realize the automatic batch of all kinds of resource content such as text, picture, audio frequency, video and its user's evaluation content
Obtain, the manageable structured language of the system that converts thereof into;Pass through tag library, rule base afterwards, agree to that dictionary etc. enters
Row word segmentation processing, and then the label obtaining is ranked up cleaning, finally obtain the label meeting asset topics and attribute.Another
Aspect, after resource is issued, system can excavate a part of label in conjunction with the behavioural habits of user using same method.
By all label input quality assessment systems finally giving, filter out misspelling, excessively chivalrous, point to fuzzy
Or label that there is unsound mind-set, filter out can concentrate expression the source language message feature reusability good
High-quality label to indexing system, respectively according to static, dynamically indexed respectively, the vector quantization realizing label indexes, simultaneously
These tag feedback to label dictionary, update its content, so that the quality of tag library is improved in benign cycle formula, realize simultaneously
Growing with each passing hour of tag library, constantly includes the label of reaction era development trend.
Label automatic indexing is capable of automatically updating of label, when detect external system have new resource to issue or
Issued matchmaker money relevant information have more new change after, can automatic batch realize crawling, filtering to its information, complete label mark
Draw.Just for dynamic labels when being wherein updated to the label of index, static labels just cannot be realized automatically once generation
Modification, if need to change to it, needs manager to do artificial change.
(1) text category information resource tag index data structure reference, as shown in table 1
(2) picture category information resources label index data structure reference table 2:
(3) audio class information resources label index data structure reference, as shown in table 3
(4) video class information resources label index data structure reference
In conjunction with Fig. 4, also there is label ambiguity in label, and such as one label " notebook " is it is impossible to judge that it is stationery class
Notebook, or notebook computer, but if the label such as " pc ", " computer " and it condense together just will not produce this
Ambiguity problem, also will not produce the content no related to target topic in retrieval result.By automatic indexing, can apply
Short packages, go to describe each information resources using a tally set, accurately express its content, this dapper mark
Sign collection, both facilitated transmission, and avoided label ambiguity problem simultaneously.
In conjunction with Fig. 5, by tally set, the mark behavior of user and resource publisher is more relevantly described, precisely smart
The tally set of refining is more precisely depicted the physical location that entity more conforms to particular user preferences in vast resources.With
When meet the assessment accuracy rate of indexing system and recall ratio two indices.
In conjunction with Fig. 6, information resources tally set divides two sections of enforcements to the semantic matches of content.First paragraph, resource publisher institute
Contents semantic information is expressed by automatic labeling label technology, relevant information stores in the label that the content issued is filtrated to get
In tally set, by data broadcasting, outer covering is transmitted;Second segment, viewer expresses his hobby (as often browsed what net
What column stood, or the interest to some public topics for the expression), leave dominant or recessive historical record on the terminal device,
Terminal unit filters out the limited tally set that may like kind in broadcast short data stream, and viewer is seeing label set content
Afterwards, cast out the full text not having energy to read in detail, obtain the full text having energy to read in detail, two sections of couplings of experience from server nearby
Thus obtaining the effect of " content seeks reader certainly ".It is used label as medium, the information of realization is taken the initiative in offering a hand, when embodying web2.0
The core concept in generation " people-oriented ".
The invention mainly comprises:
(1) full automatic label indexing technique fully utilizes the advantage of label, realizes integration, the inspection of the information resources to magnanimity
Rope, sequence, recommendation etc..This technology can be automatically obtained to text, picture, audio frequency, the label batch extracting of video class information resources,
Denoising, quality audit, index, the function such as retrieve, automatically update, and there is the function of self-teaching;
(2) label automatic indexing, respectively according to the different directions of static labels, dynamic labels, realizes the vector quantization index of label,
Dynamic labels can achieve and automatically update, and static labels, then need to be manual by management personnel if desired for modification once generating and can not change
Operation;
(3) label automatic indexing technology one side is used for information resources publishing side, makes information carry high-quality label when issuing
Collection, comprehensive integration is sorted out automatically to realize information, and convenient transmission also makes resource be easier to be retrieved simultaneously;
(4) on the other hand it is applied to user side, realize the personalized of user behavior custom and extract, excavate, beneficial to information
Join recommendation, thus really realizing content actively find user;
(5) resource content automatic addressing, by being mated the tally set of the tally set of user and resource information, is realized related
The automatic push of information labels collection, user can voluntarily download the resource that it is wanted according to demand;
(6) resource content automatic addressing technology also has self-teaching behavior, is browsed by downloading each user's final choice
Information resources feedback, constantly adjustment pushes content, realizes comprehensively accurately coupling and recommends.
At least can reach following beneficial effect:
(1) automatic Quality Control Strategy, improves label quality
(2) vector space model is utilized to press dimension to Information resource location, flexibly, accurately, comprehensively
(3) inherent nature of mined information resource
(4) it is beneficial to recommend, increase the experience of user, increase the cohesiveness of user
(5) label is closer to resource content, beneficial to improving system retrieval effect
(6) pass through self feed back system constructing high-quality label dictionary, form benign cycle, make tag system both ensure quality, and energy
Grow with each passing hour to update at any time and optimize
(7) time saving and energy saving, cost-effective, adapt to informationized society
(8) comply with the development of web2.0, promote the information exchange of user and the Internet
(9) form the data resource of unified standard form, facilitate resource consolidation, convenient management, improves resource utilization
(10) make resource tag obtain browse optimization extendible using label visualization, flattening makes tag system relatively simultaneously
Tradition cataloguing extensibility strengthens, and by cluster and label the Visual Implementation browse optimization, also overcomes because of flattening simultaneously
The drawbacks of being likely to result in the page and cannot show all labels completely
Finally it is noted that the foregoing is only the preferred embodiments of the present invention, it is not limited to the present invention, although
With reference to the foregoing embodiments the present invention is described in detail, for a person skilled in the art, it still can be right
Technical scheme described in foregoing embodiments is modified, or carries out equivalent to wherein some technical characteristics.All
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvement made etc., should be included in the protection of the present invention
Within the scope of.
Claims (4)
1. the method for the information resources automatic labeling label based on tally set automatic push is it is characterised in that include
Step 1: application cartesian vector spatial model, resource information is pressed dimension by label and classifies, each classification label
Weights describe the position in this dimension for the resource information;
Step 2: crawled using reptile, subtitle recognition, video extraction and voice recognition mode, realize the automatic batch of resource information
Obtain;
Step 3: word segmentation processing is carried out by tag library, rule base and thesaurus storehouse, and then the label obtaining is ranked up
Cleaning, finally obtains the content tab meeting resource information theme and attribute, and gained content tab is added short packages, shape
Become content tab collection;
Step 4: using the behavioural habits information excavating label to user for step 1-3, obtain user behavior custom tally set;
Step 5: the resource information finally giving tally set and user behavior are accustomed to tally set input quality assessment system, to mark
Label are filtered and are screened, respectively according to static, dynamically indexed respectively, realize the vector quantization index of label, form static state
Label and dynamic labels, simultaneously these tag feedback to tag library, update its content, and the quality making tag library is in benign cycle
Formula ground improves, and realizes growing with each passing hour of tag library simultaneously, constantly includes the label of reaction era development trend, described dynamic labels
Can achieve timing automatic renewal, the manager's manual operation that is updated to of described static labels updates;
Step 6: content tab collection is mated with user behavior custom tally set, by tally set automatic push to client,
And content is pushed according to the resource information adjustment of client downloads.
2. the information resources automatic labeling label based on tally set according to claim 1 automatic push method, its feature
It is, in step 1, described resource information is the resource information of external resource media resource system input, including text, picture, audio frequency
Or video resource content and its user's evaluation content.
3. the information resources automatic labeling label method based on tally set according to claim 2 is it is characterised in that step 5
Described in label filtered and screened specifically, filter out misspelling, excessively chivalrous, point to fuzzy or have not
The label of the mind-set of health, filter out can concentrate the good high-quality label of reusability of expression the source language message feature to
Indexing system.
4. the information resources automatic labeling label method based on tally set according to claim 3 is it is characterised in that step 6
In, content tab collection is carried out mating including first paragraph mates, and external media resource system is issued with user behavior custom tally set
Contents semantic information is expressed, relevant information is stored in label in the label that content is filtrated to get by automatic labeling label technology
Concentrate, by data broadcasting, outer covering is transmitted;And second segment coupling, user expression personal like, stay on the terminal device
Under dominant or recessive historical record, terminal unit filter out in broadcast short data stream limited may hobby kind label
Collection, viewer, after seeing label set content, casts out the full text not having energy to read in detail, and obtaining from server nearby has essence
The full text that power is read in detail.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610804361.0A CN106354860A (en) | 2016-09-06 | 2016-09-06 | Method for automatically labelling and pushing information resource based on label sets |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610804361.0A CN106354860A (en) | 2016-09-06 | 2016-09-06 | Method for automatically labelling and pushing information resource based on label sets |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106354860A true CN106354860A (en) | 2017-01-25 |
Family
ID=57859662
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610804361.0A Pending CN106354860A (en) | 2016-09-06 | 2016-09-06 | Method for automatically labelling and pushing information resource based on label sets |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106354860A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107295375A (en) * | 2017-06-13 | 2017-10-24 | 中国传媒大学 | Variety show content characteristic obtains system and application system |
CN107562828A (en) * | 2017-08-22 | 2018-01-09 | 武汉理工大学 | Multi-source Information Maritime is searched for and clash handle system and method |
CN109376309A (en) * | 2018-12-28 | 2019-02-22 | 北京百度网讯科技有限公司 | Document recommendation method and device based on semantic label |
CN109614509A (en) * | 2018-10-29 | 2019-04-12 | 山东中创软件工程股份有限公司 | Ship portrait construction method, device, equipment and storage medium |
CN109840301A (en) * | 2019-01-22 | 2019-06-04 | 珠海天燕科技有限公司 | A kind of method and device |
CN109857854A (en) * | 2019-01-02 | 2019-06-07 | 新浪网技术(中国)有限公司 | A kind of user's commercial labels method for digging and device, server |
CN110557504A (en) * | 2019-08-30 | 2019-12-10 | Oppo广东移动通信有限公司 | Dynamic update method, device, equipment and medium for ring of intelligent terminal equipment |
CN111180080A (en) * | 2019-12-30 | 2020-05-19 | 四川华迪信息技术有限公司 | Accurate pushing method for health knowledge base of old people |
CN112836134A (en) * | 2021-03-17 | 2021-05-25 | 苏州帕普云数科技有限公司 | Personalized push management method based on behavior data analysis |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014027415A1 (en) * | 2012-08-16 | 2014-02-20 | 株式会社Jx通信社 | Information provision device, information provision method, and program |
CN104331476A (en) * | 2014-11-04 | 2015-02-04 | 周艳 | Real-time content recommending method of content transaction field |
CN105512326A (en) * | 2015-12-23 | 2016-04-20 | 成都品果科技有限公司 | Picture recommending method and system |
-
2016
- 2016-09-06 CN CN201610804361.0A patent/CN106354860A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014027415A1 (en) * | 2012-08-16 | 2014-02-20 | 株式会社Jx通信社 | Information provision device, information provision method, and program |
CN104331476A (en) * | 2014-11-04 | 2015-02-04 | 周艳 | Real-time content recommending method of content transaction field |
CN105512326A (en) * | 2015-12-23 | 2016-04-20 | 成都品果科技有限公司 | Picture recommending method and system |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107295375A (en) * | 2017-06-13 | 2017-10-24 | 中国传媒大学 | Variety show content characteristic obtains system and application system |
CN107562828A (en) * | 2017-08-22 | 2018-01-09 | 武汉理工大学 | Multi-source Information Maritime is searched for and clash handle system and method |
CN107562828B (en) * | 2017-08-22 | 2020-10-30 | 武汉理工大学 | Multi-source maritime information searching and conflict processing system and method |
CN109614509A (en) * | 2018-10-29 | 2019-04-12 | 山东中创软件工程股份有限公司 | Ship portrait construction method, device, equipment and storage medium |
US11216504B2 (en) | 2018-12-28 | 2022-01-04 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Document recommendation method and device based on semantic tag |
CN109376309A (en) * | 2018-12-28 | 2019-02-22 | 北京百度网讯科技有限公司 | Document recommendation method and device based on semantic label |
CN109376309B (en) * | 2018-12-28 | 2022-05-17 | 北京百度网讯科技有限公司 | Document recommendation method and device based on semantic tags |
CN109857854A (en) * | 2019-01-02 | 2019-06-07 | 新浪网技术(中国)有限公司 | A kind of user's commercial labels method for digging and device, server |
CN109840301A (en) * | 2019-01-22 | 2019-06-04 | 珠海天燕科技有限公司 | A kind of method and device |
CN110557504A (en) * | 2019-08-30 | 2019-12-10 | Oppo广东移动通信有限公司 | Dynamic update method, device, equipment and medium for ring of intelligent terminal equipment |
CN111180080A (en) * | 2019-12-30 | 2020-05-19 | 四川华迪信息技术有限公司 | Accurate pushing method for health knowledge base of old people |
CN112836134A (en) * | 2021-03-17 | 2021-05-25 | 苏州帕普云数科技有限公司 | Personalized push management method based on behavior data analysis |
CN112836134B (en) * | 2021-03-17 | 2023-08-22 | 苏州帕普云数科技有限公司 | Personalized push management method based on behavior data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106354860A (en) | Method for automatically labelling and pushing information resource based on label sets | |
US10235421B2 (en) | Systems and methods for facilitating the gathering of open source intelligence | |
US8135669B2 (en) | Information access with usage-driven metadata feedback | |
CN110059271B (en) | Searching method and device applying tag knowledge network | |
TWI631474B (en) | Method and device for product identification label and method for product navigation | |
CN104484431B (en) | A kind of multi-source Personalize News webpage recommending method based on domain body | |
CN102279894B (en) | Method for searching, integrating and providing comment information based on semantics and searching system | |
CN101359332A (en) | Design method for visual search interface with semantic categorization function | |
JP2009514075A (en) | How to provide users with selected content items | |
CN103207917B (en) | The method of mark content of multimedia, the method and system of generation content recommendation | |
CN103886081A (en) | Information sending method and system | |
CN110008378A (en) | Corpus collection method, device, equipment and storage medium based on artificial intelligence | |
CN102207948A (en) | Method for generating incident statement sentence material base | |
CN110990670B (en) | Growth incentive book recommendation method and recommendation system | |
CN102214227B (en) | Automatic public opinion monitoring method based on internet hierarchical structure storage | |
CN112231563B (en) | Content recommendation method, device and storage medium | |
CN111861550B (en) | Family portrait construction method and system based on OTT equipment | |
CN106294358A (en) | The search method of a kind of information and system | |
WO2021111400A1 (en) | System and method for enabling a search platform to users | |
JP5367872B2 (en) | How to provide users with selected content items | |
CN112148938A (en) | Cross-domain heterogeneous data retrieval system and retrieval method | |
US20110153613A1 (en) | Information search apparatus and method using locational/societal relation-based automatic category generation | |
CN106933993B (en) | Information processing method and device | |
Sulaiman et al. | An object properties filter for multi-modality ontology semantic image retrieval | |
CN113407678A (en) | Knowledge graph construction method, device and equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20170125 |