CN105354339B - Content personalization providing method based on context - Google Patents
Content personalization providing method based on context Download PDFInfo
- Publication number
- CN105354339B CN105354339B CN201510930193.5A CN201510930193A CN105354339B CN 105354339 B CN105354339 B CN 105354339B CN 201510930193 A CN201510930193 A CN 201510930193A CN 105354339 B CN105354339 B CN 105354339B
- Authority
- CN
- China
- Prior art keywords
- user
- context
- interest
- entity
- belief network
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000002452 interceptive effect Effects 0.000 claims abstract description 5
- 230000003993 interaction Effects 0.000 claims abstract description 3
- 230000008569 process Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 7
- RTHCYVBBDHJXIQ-UHFFFAOYSA-N N-methyl-3-phenyl-3-[4-(trifluoromethyl)phenoxy]propan-1-amine Chemical compound C=1C=CC=CC=1C(CCNC)OC1=CC=C(C(F)(F)F)C=C1 RTHCYVBBDHJXIQ-UHFFFAOYSA-N 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007630 basic procedure Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The content personalization providing method based on context that the present invention provides a kind of, this method include：The behavior record of user is collected by interactive interface, obtains the context of user's interaction, user interest is calculated using depth belief network, is that target user generates push result based on the user interest.The present invention proposes a kind of content personalization providing method based on context, and the demand of user is obtained by analyzing user interest, improves the efficiency that user obtains information needed and information push.
Description
Technical field
The present invention relates to big data, more particularly to a kind of content personalization providing method based on context.
Background technology
With the development of internet and universal, information explosion growth makes user be difficult to timely and accurately find useful number
According to source, people is caused to be perplexed by information overload during obtaining abundant data source.How to help user from surge
Effective data source is obtained in magnanimity information, initiatively provides data that are more rich, comprehensive and meeting its potential demand to the user
Source, electron commercial field technology bring great challenge.However, having ignored specific environment in current techniques to user interest
Influence.On the other hand, the push evaluation information of resource generated according to user in face of numerous resources, currently existing scheme, this
The interest situation that kind can only embody user to project entirety based on the push that project is scored.However actually user is to project resource
Evaluation often generated according to attributive character possessed by it, therefore score the entirety of resource according to only according to user
And the push result generated often has one-sidedness.
Invention content
To solve the problems of above-mentioned prior art, the present invention proposes a kind of content personalization based on context
Providing method, including：
The behavior record of user is collected by interactive interface, the context of user's interaction is obtained, using depth belief network
User interest is calculated, is that target user generates push result based on the user interest.
Preferably, before the calculating user interest using depth belief network, further include：
The depth belief network model of user interest is established for the relationship between context, user and project resource, is had
Body includes：
Step 1：Using user's context and environmental context insertion depth belief network the context root different as two
The body construction of corresponding user's context and environmental context is sequentially inserted into depth belief network tree by node respectively；
Step 2：Based on context the attribute of a relation in entity, the node in Connection Step 1 so that deposited between above-mentioned node
In dependence；
Step 3：It is added to depth belief network bottom using user interest data as the leaf node in depth belief network
In layer, and the user of these representatives is related to the item attribute class in project entity to the leaf node of item attribute interest
Connection；
The context user interest depth belief network is expressed as by the description that process is established according to above-mentioned network<Nu, Eu,
PN>；Wherein, NuFor variables collection, EuFor oriented line set, PNFor the set of conditional probabilities on node variable；
Context user interest depth belief network model is divided into user interest depth belief network and based on attribute
Project entity two parts are constituted；In top layer user interest depth belief network structure, by context element Ck, specific context
Example CkqAnd user interest puThree parts constitute input, state and the export structure of network accordingly, i.e. root node is environment
Corresponding father's concept in context and user's context entity, the various context element C in context entitykAnd it is corresponding each
Kind context instance constitutes the father node in the model accordingly according to the hierarchical structure in entity respectively, by the use in entity
Family interest is as the leaf node in the network structure；
In the relation on attributes concept and the example of bottom project entity described project, and portrayed by the Semantic mapping of entity
Contacting between user interest and project；Using context instance as the evidence node in depth trust network, user is to project
The interest of attribute is then expressed as leaf node as result of calculation, then the directed arc E between nodeuIndicate various contexts it
Between and the probability dependency between context and user interest.
The present invention compared with prior art, has the following advantages：
The present invention proposes a kind of content personalization providing method based on context, is used by analyzing user interest
The demand at family improves the efficiency that user obtains information needed and information push.
Description of the drawings
Fig. 1 is the flow chart of the content personalization providing method according to the ... of the embodiment of the present invention based on context.
Specific implementation mode
Retouching in detail to one or more embodiment of the invention is hereafter provided together with the attached drawing of the diagram principle of the invention
It states.The present invention is described in conjunction with such embodiment, but the present invention is not limited to any embodiments.The scope of the present invention is only by right
Claim limits, and the present invention covers many replacements, modification and equivalent.Illustrate in the following description many details with
Just it provides a thorough understanding of the present invention.These details are provided for exemplary purposes, and without in these details
Some or all details can also realize the present invention according to claims.
An aspect of of the present present invention provides a kind of content personalization providing method based on context.Fig. 1 is according to this hair
The content personalization providing method flow chart based on context of bright embodiment.
The present invention establishes the method for pushing comprising context entity, user subject and project entity.For context and use
Relationship between the interest of family establishes user interest model according to the contact between each entity elements in method for pushing, and statement is used
Incidence relation between family context and its interest, and analyze interest of the user in some specific context；Calculate context
The concept of comentropy and context key angle value, and the crucial angle value of computational context information entropy and context element, root
User interest is calculated according to the crucial angle value of these contexts.Combination collaborative filtering based on context and keyword filtering into
Row merges push.Combine first user to project score and user is to the aspect searching target users of interest two of item attribute
Neighbours, and context similarity mode and context key angle value are added to the generation of the collaborative filtering push based on user
Cheng Zhong utilizes collaborative filtering method for pushing；According to current context information and user to the interest of item attribute, using based on
The method of knowledge push generates push result；It is generated finally by two kinds of method for pushing of calculation optimization method pair based on context
Result integrated and form final result.
On the basis of above-mentioned established method for pushing, the present invention is from structural element and realizes the angle of process, establishes
Project based on context pushes logical framework.Push frame is by inputting, push process, output three phases form；The frame
Contain knowledge Modeling, Users' Interests Mining, push generation and four levels of user feedback.
First, the top priority for pushing realization is exactly the method for pushing established about user, context and project, then from
Valid data of the extraction for pushing process in the model, the part correspond to the input phase of push；Secondly, it is emerging to excavate user
Interest, this process are the key preconditions that push generates；In push generating portion, by the user interest of extraction and and current context
Similar user's history behavioral data is combined, while carrying out semantic matches using domain knowledge, and then generates push result；Most
Afterwards, push result is presented to the user with push of sorting, predicted value or other forms, and is pushed away according to the update of the feedback result of user
User model in delivery method, the output stage as pushed.
The push framework that the present invention is established obtains user interest, then in conjunction with user behavior similar with current context
Record uses certain technology to generate push result based on the characteristics of field push knowledge.Based on method for pushing, believed using depth
Network is read to analyze user in different contexts to the interest of item attribute type；Then consider that different contexts are emerging to user
The difference that interest has an impact calculates the difference that various contexts have an impact user interest.
Based on semantic relation and logic computing function abundant between entitative concept, can be realized according to the model emerging to user
The profound of interest calculates.User subject and context entity in the method for pushing established to oneself and its between relationship carry out it is general
Extension in rate, using probabilistic model thought establish the user interest depth belief network model based on entity, realize to
The calculating of family interest, and then potential user interest is obtained to filter incoherent resource item, and knowledge based is combined to push
Method pushed, to provide the result for meeting its demand to the user.
The present invention establishes the depth belief network mould of user interest for the relationship between context, user and project resource
Type.The step of building user interest depth belief network model is as follows：
Step 1：Using user's context and environmental context insertion depth belief network the context root different as two
Node respectively inserts the concept of corresponding user's context and environmental context ontology according to their structures in entity successively
Enter in depth belief network tree；
Step 2：Based on context the attribute of a relation in entity, the node in Connection Step 1 so that deposited between above-mentioned node
In dependence；
Step 3：It is added to depth belief network bottom using user interest data as the leaf node in depth belief network
In layer, and the user of these representatives is related to the item attribute class in project entity to the leaf node of item attribute interest
Connection.
The context user interest depth belief network is expressed as by the description that process is established according to above-mentioned network：
Depth trust network=<Nu, Eu, PN>
Wherein, NuFor variables collection, EuFor oriented line set, PNFor the set of conditional probabilities on node variable.
Context user interest depth belief network model based on entity by user interest depth belief network and is based on
Project entity two parts of attribute are constituted.
In top layer user interest depth belief network structure, by context element Ck, specific context instance Ckq, and
User interest puThree parts constitute input, state and the export structure of network accordingly.I.e. root node be environmental context and
Corresponding father's concept in user's context entity, the various context element C in context entitykAnd corresponding various contexts
Example constitutes the father node in the model accordingly according to the hierarchical structure in entity respectively, and the user interest in entity is made
For the leaf node in the network structure.
The relation on attributes concept and the example of project, and the language that this two parts passes through entity are described in bottom project entity
Benefit film showing, which is penetrated, features contacting between user interest and project.Using context instance as the evidence section in depth trust network
Point, i.e. CiFor NuIn father node, user is then expressed as leaf node to the interest of item attribute as result of calculation, then node
Between directed arc EuIt indicates between various contexts and the probability dependency between context and user interest.
The present invention identifies the important context element being had an impact to user's housing choice behavior or interest, and by these
The calculating for the significance level that hereafter element has an impact user, further analysis is based under the influence of these important context elements
User interest.Calculate a certain specific context instance ckqUnder, user selects attribute type for aijProject entropy, in turn
Obtain selection of the user under the context instance to the project of certain attribute type.
Iaij ckq=fckq(aij)logn/fckq(aij)
Wherein, fckq(aij) indicate under context instance, belong to attribute type a in the selected all items of user uij
Project probability.According to selection of the user to project under specific context instance, wrapped in certain context element using user
To the entropy of selected project under the different context instances contained, come express each example that the context element is included to
The percentage contribution of family selection result.Calculating process to contextual information entropy includes following steps.
Step 1 obtains and calculates field feedback.
It by the feedback information binaryzation of user, 0 and 1 two states are quantitatively turned to for the feedback scored with user
Value, in context instance ckqUnder the influence of, user u is in project resource space to being a with attributive characterijProject appraisal
The definition of value is：
fckq(aij)=count (ur=1 | aij)/count(ur=1)
Wherein, urIndicate that the positive feedback i.e. state value of user is 1 feedback, count (u when taking 1r=1 | aij) indicate to use
Family is in context instance ckqUnder to attributive character be aijProject possessed by positive feedback number, count (ur=1) table
Show user in context instance ckqUnder to positive feedback number possessed by all items.
Step 2：Generate context instance ckqUnder evaluation value set.
fckq(ai)={ fckq(aij),…,fckq(aij)}
Wherein, aijFor j-th of attributive character under project ith attribute type.
Step 3：Calculate the entropy of context instance.
Wherein, I (ckq) indicate user in context instance ckqUnder to the items selection of different attribute type；fckq(aij) table
Show in context instance ckqUnder, the selected attribute type a of user uiBelong to a certain feature a in projectijProject probability；n
For the number of attribute type possessed by project.
Step 4：Computational context information entropy, i.e., the different lower respective contexts element C of context instance distributionkEntropy.
Wherein, p (ckq) it is context instance ckqUnder in given context element ckDistribution in sample, t are the context
The number of context instance sample included in element.
Before push generates, the context element for selecting those entropy smaller is inputted as the data of push generation.This
Outside, when excavating user interest, the size of contextual information entropy constantly adjusts user interest depth belief network model, goes
Except the context element to cut little ice to the interest of target user in network model.Based on context the crucial angle value of element
And its context instance for being included analyzes user interest.The calculation such as formula of context key angle value：.
DCk=l-E (Ck)
Wherein, CkFor to the associated context element of user interest, and DCkIndicate the crucial angle value of the context element.
User uiIn one group of contextual information cdUnder to item attribute aijInterest-degree calculate it is as follows：
Wherein, ckqIt is this group of contextual information cdIn to the associated context instance of the interest of the user, p (aij|ckq)
For context instance ckqLower user is a to attributive characterijProject preliminary interest value, n be it is associated to user interest on
The number of Examples below.
The present invention further scores to item attribute feature interest and user from user from the aspect of two, proposes to merge push
Method.First, the missing values of user's Scoring matrix are filled using the collaborative filtering of the semantic similarity based on item attribute, so
Afterwards from user to the interest angle of item attribute, the neighborhood for the common search target user that scores in conjunction with user；Then
The matching of context similarity and context key angle value are subjected to collaborative filtering, generate push result set；It will finally be based on upper
Keyword filtering push and the result of collaborative filtering hereafter blends, and obtains final push result.Item based on context
Mesh merges the basic procedure pushed：
The user interest data information of oneself acquisition of extraction, and to the associated context of user interest；Then it is pushing
Current context data, the relevant user behavior record of historical context data are pre-processed in method；
The similitude between user is calculated to scoring for project to the interest of item attribute and user from user, and then is looked for
To neighborhood, the push generating process based on user then is added in the similarity mode of context and context key angle value
In；
According to the current context of user, project resource is pushed away using the keyword filter method generation based on context
Send result；
According to push caused by collaborative filtering and keyword filtering as a result, generating the access sequence of final push result in turn
Row, and the push result is fed back into user by interface；The feedback information provided after push sequence is obtained by user.
In collaborative filtering push, push result is generated to the scoring information of project according to different user.If user information
For U={ u1,u2,…,um, represent user's set, I={ I1,I2,…,ImIt is project resource set, then A={ Rij|ui×Ij}
It scores set, wherein u for user resourcesi∈ U, Ij∈I.Therefore indicate that above-mentioned user scores data set with m*n matrix As (m, n)
Conjunction, m rows and n row, which respectively represent, m user and n project resource in the Scoring matrix, the element representation of the i-th row jth row is used
Family uiTo project resource IjScore.
The present invention constructs the supplying system system knot based on context using service-oriented layering and modular mode
Structure.The framework is divided into 3 layers, respectively data Layer, computation layer and application layer, each level contains different modules
Realize the service under corresponding level.Data Layer is the description to realizing the related information source used in Push Service.The level
Data organisation module is provided accordingly, by the integration to related data sources, corresponding mould is built by the way of semantization
Type, the realization for user's push provide Knowledge Base.The information that computation layer is provided according to data Layer carries for the realization of push
For kernel service.The interesting acquisition module of module, context computing module, semantic matches module and the push that the level includes
Generation module.Interest acquisition module：The Context Knowledge and user knowledge provided according to data Layer, it is general using depth belief network
The method that rate calculates obtains user interest information.Context computing module：According to the current contextual information of user, in data Layer
Model in the contextual information of extension and the relevant information of user interest obtained using predefined computation rule.It is semantic
Matching module：By carry out semanteme Similarity matching of the method based on entity between various data sources, and then obtain various moneys
Similarity situation between source provides knowledge for push generation module and supports.Push generation module：Based on context computing module
The knowledge provided with semantic matches module is generated using certain method and similar with user's context and demand is finally pushed away
Send result.Application layer provides the interactive service of user and Push Service, by user to the feedback information of push result, constantly more
User's correlation model of new data layer.According to push architecture proposed by the present invention, the reality of the Push Service based on context
Existing process is divided into following steps.Supplying system realizes information communication of the Push Service between user by interactive interface first,
The related context information that user is obtained according to the simple behavior operation of user, collects the interest characteristics of user, is according to this push
The realization of process provides information foundation；According to the behavior record and current context of user, calculated using depth belief network
Method analyze user interest situation；Based on the relevant knowledge of push user subject, in conjunction with user interest, retrieval is used with current
The similar neighbour user of family interest；It is similar to current context using the method retrieval of similarity calculation in conjunction with current context
Historical context set；Push mode based on context modeling, using the improvement collaborative filtering push side based on context
Method generates push result for target user；According to current context information and user interest, based on predetermined in method for pushing
Rule carries out keyword filtering push, generates the push result of rule-based knowledge；Using context calculation optimization method, will close
Keyword filtering is filtered out with conflicting result in collaborative filtering, and then is generated final push result set merging and fed back to target
User.
In conclusion the present invention proposes a kind of content personalization providing method based on context, by analyzing user
Interest obtains the demand of user, improves the efficiency that user obtains information needed and information push.
Obviously, it should be appreciated by those skilled in the art, each module of the above invention or each steps can be with general
Computing system realize that they can be concentrated in single computing system, or be distributed in multiple computing systems and formed
Network on, optionally, they can be realized with the program code that computing system can perform, it is thus possible to they are stored
It is executed within the storage system by computing system.In this way, the present invention is not limited to any specific hardware and softwares to combine.
It should be understood that the above-mentioned specific implementation mode of the present invention is used only for exemplary illustration or explains the present invention's
Principle, but not to limit the present invention.Therefore, that is done without departing from the spirit and scope of the present invention is any
Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.In addition, appended claims purport of the present invention
Covering the whole variations fallen into attached claim scope and boundary or this range and the equivalent form on boundary and is repairing
Change example.
Claims (1)
1. a kind of content personalization providing method based on context, which is characterized in that including：
The behavior record of user is collected by interactive interface, obtains the context of user's interaction, is calculated using depth belief network
User interest is that target user generates push result based on the user interest；
Before the calculating user interest using depth belief network, further include：
The depth belief network model of user interest is established for the relationship between context, user and project resource, it is specific to wrap
It includes：
Step 1：Using user's context and environmental context insertion depth belief network the context root node different as two,
The body construction of corresponding user's context and environmental context is sequentially inserted into depth belief network tree respectively；
Step 2：Based on context the attribute of a relation in entity, the node in Connection Step 1 so that exist between above-mentioned node according to
The relationship of relying；
Step 3：It is added to user interest data as the leaf node in depth belief network in depth belief network bottom,
And it is associated with the item attribute class in project entity to the leaf node of item attribute interest that these are represented user；
The context user interest depth belief network is expressed as by the description that process is established according to above-mentioned network<Nu, Eu, PN>；
Wherein, NuFor variables collection, EuFor oriented line set, PNFor the set of conditional probabilities on node variable；
Context user interest depth belief network model is divided into user interest depth belief network and based on the project of attribute
Entity two parts are constituted；In top layer user interest depth belief network structure, by context element Ck, specific context instance
CkqAnd user interest puThree parts constitute input, state and the export structure of network accordingly, i.e., under root node is environmentally
Corresponding father's concept in text and user's context entity, the various context element C in context entitykAnd it is corresponding it is various on
Examples below constitutes the father node in the model accordingly according to the hierarchical structure in entity respectively, and the user in entity is emerging
Interest is as the leaf node in the network structure；
In the relation on attributes concept and the example of bottom project entity described project, and user is portrayed by the Semantic mapping of entity
Contacting between interest and project；Using context instance as the evidence node in depth trust network, user is to item attribute
Interest be then expressed as leaf node as result of calculation, then the directed arc E between nodeuBetween indicating various contexts, with
And the probability dependency between context and user interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510930193.5A CN105354339B (en) | 2015-12-15 | 2015-12-15 | Content personalization providing method based on context |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510930193.5A CN105354339B (en) | 2015-12-15 | 2015-12-15 | Content personalization providing method based on context |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105354339A CN105354339A (en) | 2016-02-24 |
| CN105354339B true CN105354339B (en) | 2018-08-17 |
Family
ID=55330311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510930193.5A Expired - Fee Related CN105354339B (en) | 2015-12-15 | 2015-12-15 | Content personalization providing method based on context |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354339B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180046470A1 (en) * | 2016-08-11 | 2018-02-15 | Google Inc. | Methods, systems, and media for presenting a user interface customized for a predicted user activity |
| CN108805291B (en) * | 2017-04-27 | 2020-09-29 | 清华大学 | Training method of network representation learning model and server |
| CN110580317B (en) * | 2019-08-29 | 2022-02-22 | 武汉赛可锐信息技术有限公司 | Social information analysis method and device, terminal equipment and storage medium |
| CN114003714B (en) * | 2021-12-21 | 2022-03-25 | 北京理工大学 | Intelligent knowledge pushing method for document context sensing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075851A (en) * | 2009-11-20 | 2011-05-25 | 北京邮电大学 | Method and system for acquiring user preference in mobile network |
| CN103500208A (en) * | 2013-09-30 | 2014-01-08 | 中国科学院自动化研究所 | Deep layer data processing method and system combined with knowledge base |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
-
2015
- 2015-12-15 CN CN201510930193.5A patent/CN105354339B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075851A (en) * | 2009-11-20 | 2011-05-25 | 北京邮电大学 | Method and system for acquiring user preference in mobile network |
| CN103500208A (en) * | 2013-09-30 | 2014-01-08 | 中国科学院自动化研究所 | Deep layer data processing method and system combined with knowledge base |
| CN105139237A (en) * | 2015-09-25 | 2015-12-09 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105354339A (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597855A (en) | Domain knowledge map construction method and system based on big data driving | |
| KR20210038860A (en) | Intent recommendation method, apparatus, device and storage medium | |
| CN105320719B (en) | A kind of crowd based on item label and graphics relationship raises website item recommended method | |
| CN107798387B (en) | Knowledge service system and method suitable for full life cycle of high-end equipment | |
| CA2802887A1 (en) | Systems of computerized agents and user-directed semantic networking | |
| CN105354339B (en) | Content personalization providing method based on context | |
| Gheisari et al. | Data mining techniques for web mining: a survey | |
| CN113254630B (en) | Domain knowledge map recommendation method for global comprehensive observation results | |
| CN105608118B (en) | Result method for pushing based on customer interaction information | |
| CN104298785A (en) | Searching method for public searching resources | |
| CN108875090A (en) | A kind of song recommendations method, apparatus and storage medium | |
| Sharaff et al. | Analysing fuzzy based approach for extractive text summarization | |
| US20240078473A1 (en) | Systems and methods for end-to-end machine learning with automated machine learning explainable artificial intelligence | |
| Lokoč et al. | Using an interactive video retrieval tool for lifelog data | |
| CN113806560A (en) | Power data knowledge graph generation method and system | |
| CN113515589A (en) | Data recommendation method, device, equipment and medium | |
| Kovács et al. | Conceptualization with incremental bron-kerbosch algorithm in big data architecture | |
| Salah et al. | Construction of OTunAr: ontology of Tunisian archeology | |
| Manuja et al. | Intelligent text classification system based on self-administered ontology | |
| CN115293479A (en) | Public opinion analysis workflow system and method thereof | |
| JP4745993B2 (en) | Consciousness system construction device and consciousness system construction program | |
| Qingjie et al. | Research on domain knowledge graph based on the large scale online knowledge fragment | |
| CN107220249A (en) | Full-text search based on classification | |
| Vakali et al. | New directions in web data management 1 | |
| Makarova et al. | A case-based reasoning approach with fuzzy linguistic rules: Accuracy validation and application in interface design-support intelligent system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201231 Address after: No. 1608, 16th floor, building 1, 333 Dehua Road, high tech Zone, Chengdu, Sichuan 610000 Patentee after: Delu Power Technology (Chengdu) Co.,Ltd. Address before: 312-315, 3rd floor, building 7, 99 Tianhua 1st Road, high tech Zone, Chengdu, Sichuan 610041 Patentee before: CHENGDU BAIYUN SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211125 Address after: No. 505, 5th floor, building 6, No. 599, shijicheng South Road, Chengdu hi tech Zone, China (Sichuan) pilot Free Trade Zone, Chengdu, Sichuan 610000 Patentee after: Zhongguan Shuke (Chengdu) Network Technology Co.,Ltd. Address before: No. 1608, 16th floor, building 1, 333 Dehua Road, high tech Zone, Chengdu, Sichuan 610000 Patentee before: Delu Power Technology (Chengdu) Co.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180817 |