CN106503015A - A kind of method for building user's portrait - Google Patents
A kind of method for building user's portrait Download PDFInfo
- Publication number
- CN106503015A CN106503015A CN201510564860.2A CN201510564860A CN106503015A CN 106503015 A CN106503015 A CN 106503015A CN 201510564860 A CN201510564860 A CN 201510564860A CN 106503015 A CN106503015 A CN 106503015A
- Authority
- CN
- China
- Prior art keywords
- user
- internet
- storehouse
- attribute
- log data
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
- G06F16/337—Profile generation, learning or modification
Abstract
The invention discloses a kind of method for building user's portrait.Wherein, the method for building user's portrait includes：Obtain user's the Internet internet log data and carry out pretreatment, feature extraction is carried out to pretreated the Internet internet log data, obtain the attribute character of user, it is then based on the labeling that multidimensional characteristic storehouse is trained that has set up, attribute character according to user is mated in multidimensional characteristic storehouse, the multidimensional attribute label of user is obtained, user's portrait is built according to multidimensional attribute label.By the way, the present invention can construct the various dimensions user portrait of holography such that it is able to meet the recommendation of the consuming behavior of operator/business/company fast accurate advertisement putting and user group.
Description
Technical field
The present invention relates to a kind of method for building user's portrait.
Background technology
User draws a portrait, i.e. user profile labeling, be exactly by collect with analysis user's social property,
After the data of the main informations such as living habit, consuming behavior, a user is ideally taken out complete
Looks are the basic modes for supporting the big data applications such as personalized recommendation, automatization's marketing.User draws a portrait
It is that company or enterprise provide enough Information bases, enterprise can be helped to be quickly found out accurate user
The more extensive feedback information such as colony and user's request.
However, in the method for existing user's portrait structure, comprehensive to the analysis of user's Internet data,
Inaccurate, so as to cause the user for building portrait embody user's overall picture well, it is impossible to meet
Advertisement operators or enterprise find the demand of accurate user.
Content of the invention
The invention mainly solves the technical problem of how a kind of method for building user's portrait is provided,
User's portrait of holographic various dimensions can be built.
For solving above-mentioned technical problem, one aspect of the present invention is：A kind of structure is provided
The method for building user's portrait, methods described include：Obtain the user the Internet internet log data
And carry out pretreatment；Feature extraction is carried out to the pretreated the Internet internet log data,
Obtain the attribute character of the user；Based on the labeling of the multidimensional characteristic storehouse training that has set up,
Attribute character according to the user is mated in the multidimensional characteristic storehouse, obtains the user
Multidimensional attribute label, the multidimensional attribute label at least includes the base attribute of the user
Label, social property label, internet behavior attribute tags, behavioural habits attribute tags and interest
Characteristic attribute label；User's portrait is built according to the multidimensional attribute label.
Wherein, described feature extraction is carried out to the pretreated the Internet internet log data,
The attribute character for obtaining the user includes：Respectively by offline and online mode to pretreated
The Internet internet log data are analyzed process, obtain the attribute character of the user.
Wherein, described the pretreated the Internet internet log data are entered by offline mode
Row analyzing and processing, the attribute character for obtaining the user include：By the pretreated the Internet
Internet log data are loaded in data storing platform；In conjunction with the history stored in data storing platform
Data, are increased income mapping/abbreviation Computational frame based on Hadoop, to described pretreated described mutually
Networking internet log data carry out off-line analysiss process, obtain the attribute character of the user.
Wherein, described the pretreated internet log data are analyzed by online mode
Process, the attribute character for obtaining the user includes：The pretreated the Internet is surfed the Net day
Will data are evenly distributed to Mark reaction cluster；By Spark core flows calculating platform in real time from described
Mark reaction cluster pulling data simultaneously carries out real-time streams calculating analyzing and processing, obtains the attribute of the user
Feature.
Wherein, the multidimensional characteristic storehouse that has set up includes operator's basic database, terminal type
Base library, application program class library, uniform resource position mark URL class library, access website and
Behavior law statistical nature storehouse, internet content cluster result storehouse, user group's class library, name are real
Body identification contents extraction storehouse, dynamic labels Classification Management storehouse, internet site feature database, history are used
At least one in family interest focus storehouse and terminal motion track change storehouse.
Wherein, methods described also includes the step of setting up the multidimensional characteristic storehouse, wherein：Set up institute
Stating operator's basic database includes：By peripheral system or call detailed record ticket daily record data
Access, to the international member identification code of all users, operator, network type, ownership
Ground, roaming place, at least one Back ground Information in position carry out extraction and analysis, and accumulation obtains described
Operator's informaiton storehouse；Setting up the terminal type base library includes：By obtaining all user's interconnections
Online net daily record data, to the mobile terminal state in all user the Internet internet log data
At least one relevant information in border identity code, terminal models, brand styles, terminal operating system
Extraction and analysis are carried out, accumulation obtains the terminal type base library；Described set up URL classification storehouse
Including：All user the Internet internet log data are obtained, invalid URL is filtered out, for effective
URL set up the class library of effective URL affiliated web sites；The application program of setting up is classified
Storehouse includes：The Internet internet log data of all users are obtained, from the interconnection of all users
Application Type is extracted in online net daily record data, by artificial and by way of combining automatically calmly
Phase is carried out classifying, is counted to the Application Type, to form the application program class library；
The access website and the Behavior law statistics storehouse set up includes：Obtain the Internet of all users
Internet log data, for the price bidding of each user, to user often go access website and
Behavior carries out cumulative statistics, forms the access website and Behavior law statistical nature storehouse；Described build
Vertical internet content cluster result storehouse includes：Obtain the Internet internet log data of all users, pin
The daily record situation produced by the online of each user, often produces in daily record to each user described
User content forms the feature clustering based on user content, produces the internet content cluster result
Storehouse；User group's class library of setting up includes：Obtain the Internet internet log number of all users
According to carrying out feature conjunction to the user with same characteristic features label or same alike result or identical services feature
And, user group is classified, user group's class library is therefore formed；The foundation is gone through
History user interest focus storehouse includes：The Internet internet log number in conjunction with all users of offline storage
According to, the internet behavior of all users is analyzed, the behavior for producing is counted, so right
User's attentinal contents carry out cluster analyses to form the historic user interest focus storehouse；Described build
The vertical terminal motion track change storehouse includes：In to the Internet internet log data of all users
Navigation map class application program is analyzed, and obtains the longitude and latitude positional information of user's movement change,
The latitude and longitude information is shown with GIS-Geographic Information System and is combined, obtain the motion track of user, with
When the customer location time of staying is counted, often go to area so as to obtain each user, to all
User often goes to area to be collected so as to forming terminal motion track change storehouse；Described set up institute
Stating name Entity recognition contents extraction storehouse includes：The Internet internet log number according to all users
According to by the name entity identification algorithms and training sample set of main flow, to having spy in internet content
The entity for determining meaning is extracted, and sets up the name Entity recognition contents extraction storehouse；The foundation
The internet site feature database includes：Previously according to the criteria for classification of internet site, according to institute
There is the Internet internet log of user, to the interconnection in the Internet internet log of all users
Net website carries out feature collection, builds the internet site feature database；Described set up the dynamic
Labeling management storehouse includes：Based on the labeling of each feature database training, by all feature databases
The labeling of training carries out collecting merger, sets up the dynamic labels Classification Management of user preference
Storehouse.
Wherein, the base attribute label of the user includes user name, ID, sex, the people
Race, nationality, age range section, educational background, occupation, income level, user terminal, international member
Identification code, international mobile terminal identification code, operator, network type, ownership place, roaming
What ground, position, terminal brand styles, terminal models, terminal operating system and terminal were installed should
With at least one in program；The social property label include industry, occupation, job site,
At least one in place of abode, bank card, member card and the vehicles；The internet behavior
Attribute tags include browsing, search for, download, buy and commenting at least one；The row
Include in average daily surf time, normal Website login and conventional application program for being accustomed to attribute tags
At least one；The interest characteristicss attribute tags include physical culture, music, social activity, information, shopping,
At least one in leisure, tourism, game and Investment ＆ Financing.
Wherein, methods described also includes：If can not find in the multidimensional characteristic storehouse that has set up with
The multidimensional attribute label of the attribute character coupling of the user, adds in the various dimensions feature database
Plus attribute character and the corresponding multidimensional attribute label of the user.
Wherein, methods described also includes：The user the Internet internet log data are obtained in real time,
It is updated with the multidimensional attribute label to the user.
Wherein, the Internet internet log data are mobile Internet internet log data.
The invention has the beneficial effects as follows：The situation of prior art is different from, the present invention is used by obtaining
The Internet internet log data in family simultaneously carry out pretreatment, to pretreated the Internet internet log number
According to feature extraction is carried out, the attribute character of user is obtained, be then based on the multidimensional characteristic storehouse that has set up
The labeling of training, the attribute character according to user are mated in multidimensional characteristic storehouse, are obtained
The multidimensional attribute label of user, builds user's portrait according to multidimensional attribute label.By so
Mode, the Internet data of user can be comprehensively and accurately analyzed so that it is determined that user
Multidimensional attribute label, so as to build user's portrait according to multidimensional attribute label, can construct
Holographic various dimensions user portrait such that it is able to meet operator/business/company fast accurate advertisement
Throw in the recommendation with the consuming behavior of user group.
Description of the drawings
Fig. 1 is a kind of flow chart of method for building user's portrait provided in an embodiment of the present invention；
Fig. 2 be provided in an embodiment of the present invention by online treatment mode to pretreated the Internet
The flow chart that internet log data are analyzed process；
Fig. 3 be provided in an embodiment of the present invention by processed offline mode to pretreated the Internet
The flow chart that internet log data are analyzed process.
Specific embodiment
Fig. 1 is referred to, Fig. 1 is a kind of method for building user's portrait provided in an embodiment of the present invention
Flow chart, the realization of following methods drawn a portrait based on the system for building user's portrait, structure user
System can be realized in the form of hardware, it would however also be possible to employ the form reality of SFU software functional unit
Existing, as illustrated, the method for building user's portrait of the present embodiment includes：
S11：Obtain user's the Internet internet log data and carry out pretreatment.
The device of user's portrait is built by docking with peripheral system, initial data is obtained or is passed through
From the light-dividing device of operator's docking, Real-time Collection user the Internet internet log data.Wherein,
User the Internet internet log data include but are not limited to mobile Internet internet log data, have
Line wireless Internet internet log data etc..
Pretreatment is carried out to the user the Internet internet log data for obtaining, so that user the Internet
Internet log data are formatted according to unified standard.Because the information of the Internet meets 4A
(Anyone, Anytime, Anywhere, Anything) characteristic, these non-structured letters
Where (Where) breath and whose (Who) and can be closed by unifying identifier for when (When),
What (What) whose (Who) be shared with.Therefore, a kind of statement of hidden data is designed
Form is：Who, When, Where and What to Whom.The Internet internet log data
Such form can be expressed as, pretreated the Internet be surfed the Net day so as to reach
Will data can consolidation form.
S12：Feature extraction is carried out to pretreated the Internet internet log data, user is obtained
Attribute character.
By feature extraction, the attribute character of user can be obtained.The attribute character of user refers to energy
The key message of user characteristicses is enough identified.Such as to online (or call detail record CDR tickets
Daily record) in analysable content of text be analyzed, mainly to content of text in name, place name,
Mechanism's name etc. is identified, and realizes the extraction of user basic information.
Wherein, in the embodiment of the present invention, can be by way of online and offline combining to pre- place
The Internet internet log data after reason are analyzed process, so as to obtain the attribute character of user.
Online treatment mode can only be processed to current the Internet internet log data, and processed offline
Mode can be analyzed process in conjunction with historical storage data, such that it is able to not have to online treatment mode
The user property feature for having extraction is supplemented and perfect.By online and offline processing mode to mutual
Networking internet log data are processed, such that it is able to current data is associated with historical data
Mining analysis so that the user property of extraction is more comprehensively complete.
Wherein, as a kind of possible implementation, further referring to Fig. 2, Fig. 2 is to pass through
Online treatment mode is analyzed the flow process of process to pretreated the Internet internet log data
Figure, as illustrated, entered to pretreated the Internet internet log data by online treatment mode
Row analyzing and processing includes following sub-step：
S101：Pretreated the Internet internet log data are evenly distributed to Mark reaction cluster；
Mark reaction (Kafka) is that a kind of distributed post of high-throughput subscribes to message system, and it can
With the everything flow data in the website of process consumer scale.Which mainly has following characteristic：
1) persistence of message is provided by the disk data structure of O (1), even if this structure is for number
Prolonged stability can also be kept with the message storage of TB；2) high-throughput：Even
Very common hardware environment is built kafka clusters and can also support hundreds thousand of message per second；3)
Support by kafka servers and charge machine cluster come subregion message；4) support that Hadoop is parallel
Data are loaded.
By pretreated the Internet internet log data, subregion is carried out according to certain rule, made
Obtain daily record data to be evenly distributed on each machine of Kafka clusters.By by daily record number
According to being loaded into Kafka, it is therefore an objective to allow daily record data to be formed with certain sequential or size distributed
Message queue.
S102：Gone forward side by side from Kafka cluster pulling datas by Spark core flows calculating platform in real time
The real-time stream calculation analyzing and processing of row, obtains the attribute character of user.
In the present invention, real-time stream calculation, Spark are carried out by the Spark Streaming under Spark
Streaming belongs to core application DLL (the Application Programming of Spark
Interface, api), it is a kind of streaming Computational frame, it supports high-throughput, supports fault-tolerant reality
When flow data process.
After daily record data is evenly distributed to Kafka clusters in real time, real-time by Spark Streaming
From Kafka pulling datas and carry out real-time streams calculate process parsing, to format daily record data word
Section is analyzed the attribute character for obtaining user.
Wherein, as a kind of possible implementation, further referring to Fig. 3, Fig. 3 is this
Bright embodiment provide by processed offline mode to pretreated the Internet internet log data
The flow chart of process is analyzed, as illustrated, by processed offline mode to pretreated mutual
Networking internet log data are analyzed process includes following sub-step：
S201：Pretreated the Internet internet log data are loaded in data storing platform.
Pretreated the Internet internet log data enter offline logs analysis platform.Wherein, day
Will data by load warehouse-in in data storing platform, data storing platform support structuring and non-
Structurized storage mode, there is provided relevant database, NoSQL data bases and search library.
S202：In conjunction with the historical data stored in data storing platform, increased income based on Hadoop and reflected
/ abbreviation Computational frame is penetrated, pretreated the Internet internet log data are carried out at off-line analysiss
Reason, obtains the attribute character of user.
By combining the historical data of offline storage, increased income mapping/abbreviation based on Hadoop
(Map/Reduce) the historical context analysis of daily record data is completed, user property feature is obtained.
The Internet internet log data of the user of processed offline are in fact that user is continually changing
Behavioral data, the website for such as browsing, often go zone of action, conventional application program (Application,
APP) and consumption habit etc., it is analyzed based on user's internet behavior and custom, such that it is able to obtain
Take the most important approach of user preferences, behavior characteristicss.As the analysis of this partial information is with the time
Change, attribute character has the trend of evolution.In the processed offline, mainly from historic user
The Internet internet log extracting data go out user property feature, user property here is characterized in that
Refer to the key message for going out can be identified for that user property feature from internet log extracting data.Such as clear
Look at and the affiliated type in website, the conventional affiliated types of APP or often go to area etc. belonging to zone of action.
S13：Based on the labeling of the multidimensional characteristic storehouse training that has set up, according to the attribute of user
Feature is mated in multidimensional characteristic storehouse, obtains the multidimensional attribute label of user.
In the present invention, multidimensional characteristic storehouse refers to the general designation that multiple different characteristic storehouses are combined.
Wherein, feature database be through to big data analytic statisticss, and feature obtained from constantly training with not
With the corresponding feature database of labeling.Such as the Internet internet log data of all users are carried out
Analytic statisticss, determine contain in accessed network address scheduled field for tour site, will be all pre- containing this
The website for determining field is integrated into together as feature, and is traveled then as the corresponding label of this feature.
When subsequently being mated, as long as the website that user accesses belongs to the website comprising the scheduled field,
The one of multidimensional attribute label that can be obtained by user by the coupling of feature database is trip
Trip.
Wherein, the multidimensional characteristic storehouse in the embodiment of the present invention is including but not limited to operator's basis letter
Breath storehouse, terminal type base library, application program class library, uniform resource position mark URL classification
Storehouse, access website and Behavior law statistical nature storehouse, internet content cluster result storehouse, user group
Class library, name Entity recognition contents extraction storehouse, dynamic labels Classification Management storehouse, internet site
Feature database, historic user interest focus storehouse and terminal motion track change storehouse etc..
Wherein, in the embodiment of the present invention, the multidimensional attribute label of user is to build user's portrait
Staple.Multidimensional attribute label in the present invention is referred to from multiple dimensions and reflects user characteristicses
Attribute tags.Wherein, in the embodiment of the present invention, multidimensional attribute label is including but not limited to user
Base attribute label, social property label, internet behavior attribute tags, behavioural habits attribute mark
Label and interest characteristicss attribute tags etc..Further, the base attribute label of user include but
Be not limited to user name, ID, sex, nationality, nationality, age range section, educational background,
Occupation, income level, user terminal, international member identification code, international mobile terminal identification code,
Operator, network type, ownership place, roaming place, position, terminal brand styles, terminal
One or more in the application program that model, terminal operating system and terminal are installed.And society
Can attribute tags be including but not limited to industry, occupation, job site, place of abode, bank card,
One or more in member card and the vehicles.Internet behavior attribute tags are included but is not limited to
It is to browse, search for, download, buy and comment on, and behavioural habits attribute tags includes but not
It is limited to average daily surf time, normal Website login and conventional application program etc..Interest characteristicss attribute
Label is including but not limited to physical culture, music, social activity, information, shopping, leisure, tourism, trip
Play and Investment ＆ Financing etc..
Wherein, the base attribute label of user is the usual user's static attribute for embodying, and is relatively steady
Fixed information, such as sex, age etc..And social property, internet behavior attribute, behavioural habits
What attribute, interest characteristicss attribute were embodied is the dynamic attribute of user, is continually changing with the time
Attribute.And the dynamic attribute that exactly these are continually changing just can really embody user group's differentiation
Feature.
When implementing, comprehensive analysis the dynamic attribute of user can be determined in the following manner：
1) website (class of logon is often gone by the average daily surf time of counting user, user
Type), the conventional application APP of user and the time using conventional APP, so as to user
Behavioural habits characteristic attribute be analyzed.
2) come in terms of user content preference/fragmentation surf time preference/customer service preference etc. comprehensive
Close the interest characteristicss attribute of analysis user.Such as according to the different behavior action behaviors of user's online
The APP classes that (for example, browse, search for, download, buy and comment on) or user use
In type (for example, apply comprising various APP, often go Type of website of access etc.) or user
The content-data that net is produced：The purchase type of merchandise, browsed web content, search content, download are interior
Type of appearance etc. carries out the interest characteristicss attribute that comprehensive analysis obtains user.A just such as user
In internet log data, which is searched for, browse is mostly shopping website or the application program for using
It is shopping class application mostly, it may be determined that the interest characteristicss attribute that does shopping as the user, and or
What one user of person searched for, and browsed and comments on is tour site or most-often used application mostly
Program is GT grand touring application, then can determine an interest characteristicss attribute of the tourism for the user,
By that analogy.
Citing is determined as with the related label of user property below to illustrate：
Based on the labeling that multidimensional characteristic storehouse is trained, the dynamic labels management of user preference is set up.
Specifically can be considered by following aspect, weight distribution according to shared by the different factors,
Formulate the related labeling standard of unified dynamic attribute：
URL classification storehouse is such as based on：Analysis user's internet behavior daily record, extracts content and URL
Characteristic of division storehouse is mated, and exports the type that user accesses webpage, while visiting by counting user
The information such as content, access time and frequency are asked, to depict user preference, interest characteristicss is determined
Attribute tags.
Application program class library is such as based on again：Analysis user's internet behavior daily record, extracts APP classes
Type is mated with application program class library, and output user uses APP types, while by statistics
APP user carries out merger consideration using information such as duration, usage frequencies to user interest.
Such as accessing website and Behavior law statistics storehouse again includes：Online feelings for each user
Condition, carries out cumulative statistics to often go access website and the behavior of the user, forms user and access net
The typical law statistical nature storehouse that stands with behavior.
Such as internet content cluster storehouse includes again：For the daily record feelings that the online of each user is produced
Condition, (browses news or model, delivers or comment to the user content that the user is often produced in daily record
By content, content etc. is bought), the feature clustering based on user content is formed, user's online is produced
Content clustering result feature database.
Historic user interest focus storehouse is such as based on again：Analysis user's internet behavior daily record, to which
In action behavior (browse/download/search for/comment on) extracted and counted, in conjunction with history use
Family interest focus storehouse, realizes the cluster to user's attentinal contents, to depict the online row of user
For attribute tags.
And it is based on user group's class library：Analysis user's internet behavior daily record, according to the business of user
Demand or service attribute or user characteristicses, are mated with user group's classification number storehouse,
Determine user's base attribute label.
Storehouse is changed based on terminal motion track：Analysis user's internet behavior daily record, the interconnection to user
In online net daily record data, navigation map class application program is analyzed, and obtains user's movement change
Longitude and latitude positional information, latitude and longitude information is shown with GIS-Geographic Information System and is combined, obtain user's
Motion track, while counting to the customer location time of staying, often goes so as to obtain each user
Area, is mated with terminal motion track change storehouse, and analysis user often goes regional liveness information,
Determine the social property label of user.
S14：User's portrait is built according to multidimensional attribute label.
The highly refined signature identification of the usually manual regulation of label, such as age bracket label：25～35
Year, region label：Beijing, label present two key characters：1st, semantization, people can be very
Easily understand each meaning tag.This also causes user's portrait model to possess practical significance.Can
Preferably meet business demand.Such as, judge user preference.2nd, short text, each label are usual
A kind of implication is only represented, without the need for doing the pretreatment works such as excessive text analyzing again, this is label itself
Provided convenience using machine extraction standard information.So understanding in this sense, Yong Huhua
As being the summation of user tag.
Various dimensions label obtained by by above step, is that user stamps various dimensions label, or
The various dimensions label that has stamped is updated and is supplemented, to complete the structure of user's portrait.
In actual application, it is to obtain in real time to obtain user the Internet internet log data,
So as to pass through user's internet log data of real-time acquisition, it is analyzed process and obtains newest user
Various dimensions label, is updated with existing various dimensions label on drawing a portrait to user or is supplemented, so as to carve
Draw the newest holographic multidimensional user portrait containing space-time characterisation.
In addition, if during being mated, can not find in the multidimensional characteristic storehouse that has set up with
The multidimensional attribute label of the attribute character coupling of user, adds the user in various dimensions feature database
Attribute character and corresponding multidimensional attribute label, by such mode, to constantly update
With improve multidimensional characteristic storehouse.
Wherein, in embodiments of the present invention, multidimensional characteristic storehouse be realize the inventive method basis and
Key, therefore, the embodiment of the present invention further provides the method for building up in multidimensional characteristic storehouse, below
Respectively the foundation in multidimensional characteristic storehouse according to the present invention is described in detail.
Wherein, setting up operator's basic database includes：By peripheral system or call detail record
The access of ticket daily record data, to international member identification code, operator, network type, returns
Possession, roaming place, one or more Back ground Information in position carry out extraction and analysis, and accumulation is obtained
Operator's basic database.Operator's basic database includes operator identifier and corresponding operation
Business's information characteristics.
Setting up terminal type base library includes：By obtaining all user the Internet internet log numbers
According to the mobile terminal international identity code in all user the Internet internet log data, terminal type
Number, at least one relevant information in brand styles, terminal operating system carry out extraction and analysis, tire out
Product obtains terminal type base library.As in current the Internet, application species is more, each agreement
That user agent (User-Agent) field filled in operation is lack of standardization, therefore in actual extracting
During, need to unify the feature field information that disagrees and verified (for example, terminal type
That number part is filled out is iphone, and it is IOS also to have fill out；Some GT900 for simply filling out, need
From the corresponding label information that outer net collects model and brand).
Setting up URL classification storehouse includes：All user the Internet internet log data are obtained, is filtered
Fall invalid URL, for the class library that effective URL sets up effective URL affiliated web sites.For
The internet log data of user, filter out advertisement, function pages, navigation page, mistake page etc.
Class library after invalid URL, to remaining effective URL affiliated web sites.
Setting up application APP class library includes：Obtain the Internet internet log number of all users
According to, from the Internet internet log extracting data APP type of all users, by artificial and from
The dynamic mode for combining periodically is carried out classifying, is counted to APP types, to form application program classification
Storehouse.As APP application species is relatively enriched, function than more prominent, user using and dependency compared with
By force, hence with identified APP application library, download and ARIXTRA market with reference to APP Store
The APP classification suggestions that third party downloads, by artificial and by way of combining automatically periodically to APP
Application homogeneous classification, to form APP class libraries.
Setting up access website and Behavior law statistical nature storehouse includes：Obtain the Internet of all users
Internet log data, for the price bidding of each user, to user often go access website and
Behavior carries out cumulative statistics, is formed and accesses website and Behavior law statistical nature storehouse.
Setting up internet content cluster result storehouse includes：Obtain the Internet internet log number of all users
According to for the daily record situation of the online generation of each user, to each user often generation in daily record
User content form feature clustering based on user content, produce internet content cluster result storehouse.
For the daily record situation that the online of each user is produced, the user often produced in daily record by the user
Content (browses news or model, deliver or comment on content, purchase content etc.), is formed based on use
The feature clustering of indoor appearance, produces user's internet content cluster result feature database.
Setting up user group's class library includes：The Internet internet log data of all users are obtained,
Feature merging is carried out to the user with same characteristic features label or same alike result or identical services feature,
User group is classified, user group's class library is therefore formed.Can be according to actual business
The all users for accumulating are finely divided point group merger so as to must by requirement definition clustering target parameter
Arrive user group's class library.
Setting up historic user interest focus storehouse includes：The Internet in conjunction with all users of offline storage
Internet log data, are analyzed to the internet behavior of all users, and the behavior for producing is united
Meter, and then user's attentinal contents are carried out with cluster analyses with history of forming user interest focus storehouse.
In conjunction with history online behavior analysiss, to the action behavior (browse/download/search for/comment on) for producing
Counted, and then historic user interest is closed to be realized using traditional cluster analyses to user's attentinal contents
The foundation in note point storehouse.
Setting up terminal motion track change storehouse includes：The Internet internet log data to all users
Middle navigation map class application program is analyzed, and obtains the longitude and latitude position letter of user's movement change
Breath, by latitude and longitude information and GIS-Geographic Information System (Geographic Information System, GIS)
Show and combine, obtain the motion track of user, while the customer location time of staying is counted,
Area is often gone to so as to obtain each user, often goes to area to be collected all users so as to forming end
End motion track change storehouse.By analyzing to navigation map class APP in internet log, can obtain
The longitude and latitude positional information of cellphone subscriber's movement change.Therefore, on the one hand, by this information and GIS
Show and combine, the motion track of cellphone subscriber completely can be presented in real time；On the other hand, can be with
The mobile phone customer location time of staying is counted in different time sections, can be right according to statistics duration
Cellphone subscriber often goes actively to carry out liveness analysis, you can obtain distinguishing with often going for cellphone subscriber
Cloth, to form terminal motion track change storehouse.
Suggestion name Entity recognition contents extraction storehouse includes：Surfed the Net day according to the Internet of all users
Will data, by the name entity identification algorithms and training sample set of main flow, to having in internet content
The entity for having certain sense is extracted, and sets up name Entity recognition contents extraction storehouse.By to institute
Have the name entity identification algorithms and training sample set of the Internet main flow of user, to internet content in
There is the entity of certain sense, such as mainly include name, place name, mechanism's name, proper noun etc.
Extracted, set up the attribute character storehouse for special handset user, with abundant multidimensional property label.
Setting up internet site feature database includes：Previously according to the criteria for classification of internet site, root
According to the Internet internet log of all users, to the interconnection in the Internet internet log of all users
Net website carries out feature collection, builds the internet site feature database.It is previously according to interconnection
The criteria for classification of net website, carries out feature collection to the website of the Internet in the daily record data of user
(the corresponding URL in website, title, setup time, affiliated web site classification etc.), builds corresponding
Web site features storehouse.
Setting up dynamic labels Classification Management storehouse includes：Based on the labeling of each feature database training,
The labeling that all feature databases are trained is carried out collecting merger, the dynamic labels of user preference are set up
Classification Management storehouse.Wherein, during concrete application, comprehensively can consider from many aspects, and root
According to the weight shared by the labeling that each feature database is trained, unified labeling standard is formulated,
In conjunction with predefined physical culture/music/social activity/information/shopping/leisure/tourism/game/investment (financing)
Realize etc. accumulation feature of all categories is carried out.
The method for building user's portrait of the above embodiment of the present invention, can build cellphone subscriber to draw
Picture, or structure other-end user's portrait.Wherein, such as when the structure of the embodiment of the present invention
Build user portrait method be used for build cellphone subscriber draw a portrait when, in conjunction with mobile phone terminal essential information storehouse
With cellphone subscriber's essential information storehouse, cellphone subscriber's all properties label field is associated by cell-phone number
Get up, so as to build a complete panorama user portrait containing space-time characterisation so that each mobile phone
User has complete user's portrait information.Certainly, if building picture for other-end user
During picture, it is also possible to by the category of other mark such as association users such as terminal unit ID, ID
Property label, associate so as to all properties label by user with constitute user portrait.
By the detailed description of the method for building user's portrait provided in an embodiment of the present invention above, can
To understand, the method for the present invention is by obtaining user's the Internet internet log data and carrying out pre- place
Pretreated the Internet internet log data are carried out feature extraction, obtain the attribute of user by reason
Then the attribute character of user is mated with the multidimensional characteristic storehouse that sets up, is used by feature
The multidimensional attribute label at family, builds user's portrait according to multidimensional attribute label.By such
Mode, can comprehensively and accurately be analyzed to the Internet data of user so that it is determined that user's is more
Dimensional attribute label, so as to build user's portrait according to multidimensional attribute label, can construct complete
The various dimensions user portrait of breath such that it is able to meet operator/business/company fast accurate advertisement and throw
Put the recommendation with the consuming behavior of user group.
Embodiments of the invention are the foregoing is only, the scope of the claims of the present invention is not thereby limited,
Equivalent structure or equivalent flow conversion that every utilization description of the invention and accompanying drawing content are made, or
Other related technical field is directly or indirectly used in, and the patent for being included in the present invention in the same manner is protected
In the range of shield.
Claims (10)
1. a kind of method that structure user draws a portrait, it is characterised in that methods described includes：
Obtain the user the Internet internet log data and carry out pretreatment；
Feature extraction is carried out to the pretreated the Internet internet log data, the use is obtained
The attribute character at family；
Based on the labeling of the multidimensional characteristic storehouse training that has set up, special according to the attribute of the user
Levy and mated in the multidimensional characteristic storehouse, obtain the multidimensional attribute label of the user, institute
State multidimensional attribute label at least include the base attribute label of the user, social property label,
Internet behavior attribute tags, behavioural habits attribute tags and interest characteristicss attribute tags；
User's portrait is built according to the multidimensional attribute label.
2. method according to claim 1, it is characterised in that described to pretreated institute
Stating the Internet internet log data carries out feature extraction, and the attribute character for obtaining the user includes：
Respectively by offline and online mode to the pretreated the Internet internet log data
Process is analyzed, the attribute character of the user is obtained.
3. method according to claim 2, it is characterised in that described by offline mode pair
The pretreated the Internet internet log data are analyzed process, obtain the category of the user
Property feature includes：
The pretreated the Internet internet log data are loaded in data storing platform；
In conjunction with the historical data stored in data storing platform, increased income mapping/abbreviation based on Hadoop
The pretreated the Internet internet log data are carried out at off-line analysiss by Computational frame
Reason, obtains the attribute character of the user.
4. method according to claim 2, it is characterised in that described by online mode pair
The pretreated the Internet internet log data are analyzed process, obtain the category of the user
Property feature includes：
The pretreated the Internet internet log data are evenly distributed to Mark reaction cluster；
From the Mark reaction cluster pulling data and carried out by Spark core flows calculating platform in real time
Stream calculation analyzing and processing, obtains the attribute character of the user in real time.
5. method according to claim 1, it is characterised in that the multidimensional that has set up is special
Levying storehouse includes operator's basic database, terminal type base library, application program class library, unification
URLs URL classification storehouse, access website and Behavior law statistical nature storehouse, internet content
Cluster result storehouse, user group's class library, name Entity recognition contents extraction storehouse, dynamic labels point
Class management storehouse, internet site feature database, historic user interest focus storehouse and terminal moving rail
At least one in mark change storehouse.
6. method according to claim 5, it is characterised in that methods described also includes setting up
The step of multidimensional characteristic storehouse, wherein：
Setting up operator's basic database includes：Talked about by peripheral system or call detail record
The access of single daily record data, to the international member identification code of all users, operator, network
Type, ownership place, roaming place, at least one Back ground Information in position carry out extraction and analysis, tire out
Product obtains operator's basic database；
Setting up the terminal type base library includes：By obtaining all user the Internets internet log
Data, to the mobile terminal international identity code in all user the Internet internet log data,
At least one relevant information in terminal models, brand styles, terminal operating system carries out extracting divides
Analysis, accumulation obtain the terminal type base library；
The URL classification storehouse of setting up includes：All user the Internet internet log data are obtained,
Invalid URL is filtered out, for the classification that effective URL sets up effective URL affiliated web sites
Storehouse；
The application program class library of setting up includes：Obtain the Internet internet log number of all users
According to from the Internet internet log extracting data Application Type of all users, passing through
Mode that is artificial and combining automatically is periodically carried out classifying, is counted to the Application Type, with
Form the application program class library；
The access website and the Behavior law statistical nature storehouse set up includes：Obtain all users
The Internet internet log data, for the price bidding of each user, to user often go access
Website and behavior carry out cumulative statistics, form the access website and Behavior law statistical nature
Storehouse；
The internet content cluster result storehouse of setting up includes：Obtain the Internet online day of all users
Will data, for the daily record situation of the online generation of each user, to each user Chang described
The user content produced in will forms the feature clustering based on user content, produces the internet content
Cluster result storehouse；
User group's class library of setting up includes：Obtain the Internet internet log number of all users
According to carrying out feature conjunction to the user with same characteristic features label or same alike result or identical services feature
And, user group is classified, user group's class library is therefore formed；
The historic user interest focus storehouse of setting up includes：In conjunction with the mutual of all users of offline storage
Networking internet log data, are analyzed to the internet behavior of all users, and the behavior for producing is entered
Row statistics, and then user's attentinal contents are carried out with cluster analyses to form the historic user interest pass
Note point storehouse；
The terminal motion track change storehouse of setting up includes：The Internet internet log to all users
In data, navigation map class application program is analyzed, and obtains the longitude and latitude position of user's movement change
Information, the latitude and longitude information is shown with GIS-Geographic Information System and is combined, obtain the moving rail of user
Mark, while counting to the customer location time of staying, often goes to area so as to obtain each user,
Often go to area to be collected all users and change storehouse so as to form the terminal motion track；
Described set up the name Entity recognition contents extraction storehouse and include：Interconnection according to all users
Online net daily record data, by the name entity identification algorithms and training sample set of main flow, to online
The entity that there is certain sense in content is extracted, and sets up the name Entity recognition contents extraction
Storehouse；
Described set up the internet site feature database and include：Classification previously according to internet site
Standard, according to the Internet internet log of all users, surfs the Net to the Internet of all users
Internet site in daily record carries out feature collection, builds the internet site feature database；
Described set up the dynamic labels Classification Management storehouse and include：Mark based on each feature database training
Classification is signed, the labeling that all feature databases are trained is carried out collecting merger, user preference is set up
The dynamic labels Classification Management storehouse.
7. method according to claim 1, it is characterised in that the base attribute of the user
Label include user name, ID, sex, nationality, nationality, age range section, educational background,
Occupation, income level, user terminal, international member identification code, international mobile terminal identification code,
Operator, network type, ownership place, roaming place, position, terminal brand styles, terminal
At least one in the application program that model, terminal operating system and terminal are installed；The society
Attribute tags include industry, occupation, job site, place of abode, bank card, member card and
At least one in the vehicles；The internet behavior attribute tags include browsing, search for, download,
At least one in purchase and comment；When the behavioural habits attribute tags include daily surfing the Net
Between, at least one in normal Website login and conventional application program；The interest characteristicss attribute mark
Signing includes physical culture, music, social activity, information, shopping, leisure, tourism, game and investment reason
At least one in wealth.
8. method according to claim 1, it is characterised in that methods described also includes：If
Can not find in the multidimensional characteristic storehouse that has set up many with what the attribute character of the user was mated
Dimensional attribute label, adds the attribute character of the user and corresponding in the various dimensions storehouse
Multidimensional attribute label.
9. method according to claim 1, it is characterised in that methods described also includes：Real
When obtain the user the Internet internet log data, with the multidimensional attribute label to the user
It is updated.
10. the method according to any one of claim 1-9, it is characterised in that the Internet
Internet log data are mobile Internet internet log data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510564860.2A CN106503015A (en) | 2015-09-07 | 2015-09-07 | A kind of method for building user's portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510564860.2A CN106503015A (en) | 2015-09-07 | 2015-09-07 | A kind of method for building user's portrait |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503015A true CN106503015A (en) | 2017-03-15 |
Family
ID=58287071
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510564860.2A Pending CN106503015A (en) | 2015-09-07 | 2015-09-07 | A kind of method for building user's portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503015A (en) |
Cited By (101)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016103A (en) * | 2017-04-12 | 2017-08-04 | 北京焦点新干线信息技术有限公司 | A kind of method and device for building user's portrait |
| CN107038237A (en) * | 2017-04-18 | 2017-08-11 | 昆山数泰数据技术有限公司 | User's portrait system and portrait method based on big data |
| CN107193936A (en) * | 2017-05-19 | 2017-09-22 | 前海梧桐（深圳）数据有限公司 | A kind of method and its system for being used to set enterprise features tab |
| CN107220383A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技（北京）有限公司 | Data filtering method |
| CN107330001A (en) * | 2017-06-09 | 2017-11-07 | 国政通科技股份有限公司 | The creation method and system of a kind of diversification label |
| CN107562870A (en) * | 2017-08-30 | 2018-01-09 | 国信优易数据有限公司 | A kind of user recommends method and apparatus |
| CN107578272A (en) * | 2017-08-10 | 2018-01-12 | 上海斐讯数据通信技术有限公司 | A kind of method and device for kinsfolk's portrait |
| CN107590673A (en) * | 2017-03-17 | 2018-01-16 | 南方科技大学 | user classification method and device |
| CN107612707A (en) * | 2017-08-04 | 2018-01-19 | 上海斐讯数据通信技术有限公司 | The preprocess method and system of the homologous sample data classification storage in Industry-oriented field |
| CN107679904A (en) * | 2017-09-28 | 2018-02-09 | 山东浪潮云服务信息科技有限公司 | A kind of method and device of Recommendations |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN107730269A (en) * | 2017-07-21 | 2018-02-23 | 南通大学 | A kind of Electricity customers portrait method of Behavior-based control analysis |
| CN107729560A (en) * | 2017-11-08 | 2018-02-23 | 北京奇虎科技有限公司 | User's portrait building method, device and computing device based on big data |
| CN107798118A (en) * | 2017-11-08 | 2018-03-13 | 北京奇虎科技有限公司 | User's portrait building method, device and computing device based on big data |
| CN107808307A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Business personnel's picture forming method, electronic installation and computer-readable recording medium |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| CN107870986A (en) * | 2017-10-13 | 2018-04-03 | 平安科技（深圳）有限公司 | User behavior analysis method, application server and computer-readable recording medium based on reptile data |
| CN108021929A (en) * | 2017-11-16 | 2018-05-11 | 华南理工大学 | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system |
| CN108021670A (en) * | 2017-12-06 | 2018-05-11 | 中国南方航空股份有限公司 | Multi-source heterogeneous data fusion system and method |
| CN108154401A (en) * | 2018-01-15 | 2018-06-12 | 网易无尾熊（杭州）科技有限公司 | User's portrait depicting method, device, medium and computing device |
| CN108269128A (en) * | 2018-01-22 | 2018-07-10 | 北京小米移动软件有限公司 | Put-on method, device, equipment and the storage medium of advertisement |
| CN108280117A (en) * | 2017-11-22 | 2018-07-13 | 广州市动景计算机科技有限公司 | Metadata of drawing a portrait preparation method, device, storage medium and electronic equipment |
| CN108335147A (en) * | 2018-02-28 | 2018-07-27 | 北京搜狐新媒体信息技术有限公司 | A kind of data analysing method and system based on user behavior |
| CN108363821A (en) * | 2018-05-09 | 2018-08-03 | 深圳壹账通智能科技有限公司 | A kind of information-pushing method, device, terminal device and storage medium |
| CN108509569A (en) * | 2018-03-26 | 2018-09-07 | 河北省科学院应用数学研究所 | Generation method, device, electronic equipment and the storage medium of enterprise's portrait |
| CN108628980A (en) * | 2018-04-27 | 2018-10-09 | 四川斐讯信息技术有限公司 | A kind of user's portrait method and system based on user network behavior |
| CN108629633A (en) * | 2018-05-09 | 2018-10-09 | 浪潮软件股份有限公司 | A kind of method and system for establishing user's portrait based on big data |
| CN108763278A (en) * | 2018-04-11 | 2018-11-06 | 口碑(上海)信息技术有限公司 | The statistical method and device of user characteristics label |
| CN108804908A (en) * | 2017-05-04 | 2018-11-13 | 腾讯科技（深圳）有限公司 | A kind of device-fingerprint generation method, device and computing device |
| CN108830298A (en) * | 2018-05-21 | 2018-11-16 | 麒麟合盛网络技术股份有限公司 | A kind of method and device of determining user characteristics label |
| CN108898413A (en) * | 2018-05-14 | 2018-11-27 | 链家网（北京）科技有限公司 | A kind of traveller's management method and device |
| CN108932646A (en) * | 2017-05-26 | 2018-12-04 | 中移（杭州）信息技术有限公司 | User tag verification method, device and electronic equipment based on operator |
| CN109033149A (en) * | 2018-06-12 | 2018-12-18 | 北京奇艺世纪科技有限公司 | Information recommendation method, device, server and storage medium |
| CN109064210A (en) * | 2018-06-29 | 2018-12-21 | 康美药业股份有限公司 | A kind of method that establishing user tag library, electronic equipment, storage medium and system |
| CN109241461A (en) * | 2018-08-10 | 2019-01-18 | 新华三信息安全技术有限公司 | A kind of user draws a portrait construction method and device |
| CN109242309A (en) * | 2018-09-05 | 2019-01-18 | 广州视源电子科技股份有限公司 | The user that attends a meeting portrait generation method, device, intelligent meeting equipment and storage medium |
| CN109271392A (en) * | 2018-10-30 | 2019-01-25 | 长威信息科技发展股份有限公司 | Quick discrimination and the method and apparatus for extracting relevant database entity and attribute |
| CN109271423A (en) * | 2018-09-29 | 2019-01-25 | 深圳市轱辘汽车维修技术有限公司 | A kind of object recommendation method, apparatus, terminal and computer readable storage medium |
| CN109271593A (en) * | 2018-11-06 | 2019-01-25 | 北京京航计算通讯研究所 | Military project group personal information labeling process based on cluster |
| CN109347903A (en) * | 2018-08-28 | 2019-02-15 | 浙江工业大学 | A kind of campus message pushing and optimizing method based on generalized information system |
| CN109389138A (en) * | 2017-08-09 | 2019-02-26 | 武汉安天信息技术有限责任公司 | A kind of user's portrait method and device |
| CN109408723A (en) * | 2018-11-06 | 2019-03-01 | 北京奇艺世纪科技有限公司 | A kind of method for pushing and device |
| CN109472490A (en) * | 2018-11-06 | 2019-03-15 | 北京京航计算通讯研究所 | Military project group personal information labeling system based on cluster |
| 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 |
| CN109670112A (en) * | 2018-12-20 | 2019-04-23 | 北京城市网邻信息技术有限公司 | A kind of generation method, device, storage medium and the terminal of user's portrait ID |
| CN109684539A (en) * | 2018-12-07 | 2019-04-26 | 陈包容 | It is a kind of based on the user of cell phone apparatus information and internet information draw a portrait method |
| CN109684373A (en) * | 2018-11-26 | 2019-04-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Emphasis party based on trip and call bill data analysis has found method |
| CN109710697A (en) * | 2018-12-28 | 2019-05-03 | 厦门笨鸟电子商务有限公司 | A kind of generation method of corporate user's portrait |
| 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 |
| CN109815386A (en) * | 2018-12-21 | 2019-05-28 | 厦门市美亚柏科信息股份有限公司 | A kind of construction method, device and storage medium based on user's portrait |
| CN109815987A (en) * | 2018-12-27 | 2019-05-28 | 北京卓思天成数据咨询股份有限公司 | A kind of listener clustering method and categorizing system |
| CN109886719A (en) * | 2018-12-20 | 2019-06-14 | 平安科技（深圳）有限公司 | Data mining processing method, device and computer equipment based on grid |
| CN109905873A (en) * | 2019-02-25 | 2019-06-18 | 国家计算机网络与信息安全管理中心 | A kind of network account correlating method based on signature identification information |
| CN109919652A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | User group's classification method, device, equipment and storage medium |
| CN109919437A (en) * | 2019-01-29 | 2019-06-21 | 特斯联（北京）科技有限公司 | A kind of smart travel target matching method and system based on big data |
| CN109936549A (en) * | 2017-12-18 | 2019-06-25 | 航天信息股份有限公司 | Audit data processing method and device based on PKI platform |
| CN109933699A (en) * | 2019-03-05 | 2019-06-25 | 中国科学院文献情报中心 | A kind of construction method and device of academic portrait model |
| CN109934638A (en) * | 2019-03-21 | 2019-06-25 | 南京金信通信息服务有限公司 | A method of according to the graphical customer portrait of user tag and early warning |
| CN109947811A (en) * | 2017-11-29 | 2019-06-28 | 北京京东金融科技控股有限公司 | Generic features library generating method and device, storage medium, electronic equipment |
| CN110020234A (en) * | 2017-07-31 | 2019-07-16 | 中国电信股份有限公司 | The method and apparatus for determining Broadband Network Access point information |
| CN110135901A (en) * | 2019-05-10 | 2019-08-16 | 重庆天蓬网络有限公司 | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment |
| CN110263126A (en) * | 2019-06-20 | 2019-09-20 | 维沃移动通信有限公司 | A kind of generation method and mobile terminal of user's portrait |
| CN110263053A (en) * | 2019-06-17 | 2019-09-20 | 浙江每日互动网络科技股份有限公司 | A kind of server obtaining mobile terminal portrait label based on mobile terminal data |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110431585A (en) * | 2018-01-22 | 2019-11-08 | 华为技术有限公司 | A kind of generation method and device of user's portrait |
| CN110442572A (en) * | 2019-06-28 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The determination method and device of user characteristics value |
| CN110489660A (en) * | 2019-07-22 | 2019-11-22 | 武汉大学 | A kind of user's economic situation portrait method of social media public data |
| CN110659414A (en) * | 2019-09-02 | 2020-01-07 | 惠州学院 | User portrait based personalized information pushing method and user side |
| CN110674410A (en) * | 2019-10-08 | 2020-01-10 | 北京物灵科技有限公司 | User portrait construction and content recommendation method, device and equipment |
| CN110781930A (en) * | 2019-10-14 | 2020-02-11 | 西安交通大学 | User portrait grouping and behavior analysis method and system based on log data of network security equipment |
| CN110942337A (en) * | 2019-10-31 | 2020-03-31 | 天津中科智能识别产业技术研究院有限公司 | Accurate tourism marketing method based on internet big data |
| CN110941823A (en) * | 2018-09-21 | 2020-03-31 | 武汉安天信息技术有限责任公司 | Threat information acquisition method and device |
| CN110968572A (en) * | 2018-09-29 | 2020-04-07 | 北京小米移动软件有限公司 | User portrait data cleaning method and device |
| WO2020082596A1 (en) * | 2018-10-23 | 2020-04-30 | 深圳壹账通智能科技有限公司 | Data processing-based automatic user profile generating method and system |
| CN111277995A (en) * | 2018-12-05 | 2020-06-12 | 中国移动通信集团甘肃有限公司 | Method and equipment for identifying terminal user |
| CN111382343A (en) * | 2018-12-27 | 2020-07-07 | 方正国际软件(北京)有限公司 | Label system generation method and device |
| CN111400599A (en) * | 2020-03-17 | 2020-07-10 | 苏宁金融科技(南京)有限公司 | User group portrait generation method, device and system |
| CN111428124A (en) * | 2019-01-10 | 2020-07-17 | 珠海金山办公软件有限公司 | Method, system, terminal and storage medium for marking user |
| CN111444236A (en) * | 2020-03-23 | 2020-07-24 | 华南理工大学 | Mobile terminal user portrait construction method and system based on big data |
| CN111491060A (en) * | 2019-01-28 | 2020-08-04 | 百度在线网络技术（北京）有限公司 | Information click log and ticket splicing method and device |
| CN111625726A (en) * | 2020-06-02 | 2020-09-04 | 小红书科技有限公司 | User portrait processing method and device |
| CN111640436A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Method for providing a dynamic customer representation of a call partner to an agent |
| CN111709843A (en) * | 2020-05-09 | 2020-09-25 | 中国人民财产保险股份有限公司 | Client portrait generation method and device and electronic equipment |
| CN111798351A (en) * | 2020-09-09 | 2020-10-20 | 北京神州泰岳智能数据技术有限公司 | Data processing method and device and readable storage medium |
| CN111918323A (en) * | 2019-09-18 | 2020-11-10 | 北京云海淘金数据技术有限公司 | Data calibration method, device, equipment and storage medium |
| CN112001739A (en) * | 2019-05-27 | 2020-11-27 | 广东小天才科技有限公司 | Method and system for generating user learning portrait |
| CN112000748A (en) * | 2020-07-14 | 2020-11-27 | 北京神州泰岳智能数据技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN112214556A (en) * | 2020-09-30 | 2021-01-12 | 招商局金融科技有限公司 | Label generation method and device, electronic equipment and computer readable storage medium |
| CN112311612A (en) * | 2019-07-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Family portrait construction method and device and storage medium |
| CN112631889A (en) * | 2020-12-31 | 2021-04-09 | 中国农业银行股份有限公司 | Portrayal method, device and equipment for application system and readable storage medium |
| WO2021087684A1 (en) * | 2019-11-04 | 2021-05-14 | 深圳市欢太科技有限公司 | Method and apparatus for processing user behavior data, server, and storage medium |
| CN113010795A (en) * | 2021-04-12 | 2021-06-22 | 北京明略软件系统有限公司 | User dynamic portrait generation method, system, storage medium and electronic device |
| CN113065883A (en) * | 2020-01-02 | 2021-07-02 | 中国移动通信集团广东有限公司 | Method and device for delivering advertisements |
| CN113065895A (en) * | 2021-03-29 | 2021-07-02 | 上海酷量信息技术有限公司 | Advertisement recommendation method and device based on geographic position |
| WO2021155691A1 (en) * | 2020-02-07 | 2021-08-12 | 腾讯科技（深圳）有限公司 | User portrait generating method and apparatus, storage medium, and device |
| CN113316778A (en) * | 2019-06-24 | 2021-08-27 | 深圳市欢太科技有限公司 | Equipment recommendation method and related product |
| CN113366469A (en) * | 2019-06-29 | 2021-09-07 | 深圳市欢太科技有限公司 | Data classification method and related product |
| CN113923156A (en) * | 2021-09-29 | 2022-01-11 | 湖北美和易思教育科技有限公司 | Intelligent gateway management method and system based on multi-path network |
| CN114722252A (en) * | 2022-03-18 | 2022-07-08 | 深圳市小满科技有限公司 | Foreign trade user classification method based on user portrait and related equipment |
| CN117435449A (en) * | 2023-11-06 | 2024-01-23 | 广州丰石科技有限公司 | User portrait analysis method and device, electronic equipment and storage medium |
| CN111640436B (en) * | 2020-05-15 | 2024-04-19 | 北京青牛技术股份有限公司 | Method for providing dynamic customer portraits of conversation objects to agents |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761296A (en) * | 2014-01-20 | 2014-04-30 | 北京集奥聚合科技有限公司 | Method and system for analyzing network behaviors of mobile terminal users |
| CN104735062A (en) * | 2015-03-12 | 2015-06-24 | 微梦创科网络科技（中国）有限公司 | Network user registration method and server |
| CN104750731A (en) * | 2013-12-30 | 2015-07-01 | 华为技术有限公司 | Method and device for obtaining complete user portrait |
-
2015
- 2015-09-07 CN CN201510564860.2A patent/CN106503015A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750731A (en) * | 2013-12-30 | 2015-07-01 | 华为技术有限公司 | Method and device for obtaining complete user portrait |
| CN103761296A (en) * | 2014-01-20 | 2014-04-30 | 北京集奥聚合科技有限公司 | Method and system for analyzing network behaviors of mobile terminal users |
| CN104735062A (en) * | 2015-03-12 | 2015-06-24 | 微梦创科网络科技（中国）有限公司 | Network user registration method and server |
Cited By (132)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590673A (en) * | 2017-03-17 | 2018-01-16 | 南方科技大学 | user classification method and device |
| CN107016103A (en) * | 2017-04-12 | 2017-08-04 | 北京焦点新干线信息技术有限公司 | A kind of method and device for building user's portrait |
| CN107038237A (en) * | 2017-04-18 | 2017-08-11 | 昆山数泰数据技术有限公司 | User's portrait system and portrait method based on big data |
| CN108804908A (en) * | 2017-05-04 | 2018-11-13 | 腾讯科技（深圳）有限公司 | A kind of device-fingerprint generation method, device and computing device |
| CN107193936A (en) * | 2017-05-19 | 2017-09-22 | 前海梧桐（深圳）数据有限公司 | A kind of method and its system for being used to set enterprise features tab |
| CN108932646A (en) * | 2017-05-26 | 2018-12-04 | 中移（杭州）信息技术有限公司 | User tag verification method, device and electronic equipment based on operator |
| CN108932646B (en) * | 2017-05-26 | 2021-04-13 | 中移（杭州）信息技术有限公司 | User tag verification method and device based on operator and electronic equipment |
| CN107330001A (en) * | 2017-06-09 | 2017-11-07 | 国政通科技股份有限公司 | The creation method and system of a kind of diversification label |
| CN107220383A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技（北京）有限公司 | Data filtering method |
| CN107730269A (en) * | 2017-07-21 | 2018-02-23 | 南通大学 | A kind of Electricity customers portrait method of Behavior-based control analysis |
| CN110020234A (en) * | 2017-07-31 | 2019-07-16 | 中国电信股份有限公司 | The method and apparatus for determining Broadband Network Access point information |
| CN110020234B (en) * | 2017-07-31 | 2021-09-03 | 中国电信股份有限公司 | Method and device for determining broadband network access point information |
| CN107612707B (en) * | 2017-08-04 | 2021-04-09 | 深圳市其乐游戏科技有限公司 | Preprocessing method and system for classified storage of homologous sample data in industry field |
| CN107612707A (en) * | 2017-08-04 | 2018-01-19 | 上海斐讯数据通信技术有限公司 | The preprocess method and system of the homologous sample data classification storage in Industry-oriented field |
| CN109389138A (en) * | 2017-08-09 | 2019-02-26 | 武汉安天信息技术有限责任公司 | A kind of user's portrait method and device |
| CN107578272A (en) * | 2017-08-10 | 2018-01-12 | 上海斐讯数据通信技术有限公司 | A kind of method and device for kinsfolk's portrait |
| CN107562870A (en) * | 2017-08-30 | 2018-01-09 | 国信优易数据有限公司 | A kind of user recommends method and apparatus |
| CN107808307A (en) * | 2017-09-28 | 2018-03-16 | 平安科技（深圳）有限公司 | Business personnel's picture forming method, electronic installation and computer-readable recording medium |
| CN107679904A (en) * | 2017-09-28 | 2018-02-09 | 山东浪潮云服务信息科技有限公司 | A kind of method and device of Recommendations |
| WO2019062081A1 (en) * | 2017-09-28 | 2019-04-04 | 平安科技（深圳）有限公司 | Salesman profile formation method, electronic device and computer readable storage medium |
| CN107730313A (en) * | 2017-09-30 | 2018-02-23 | 口碑(上海)信息技术有限公司 | Recommend method and device in shop based on rationale for the recommendation |
| CN107870986A (en) * | 2017-10-13 | 2018-04-03 | 平安科技（深圳）有限公司 | User behavior analysis method, application server and computer-readable recording medium based on reptile data |
| CN107844548A (en) * | 2017-10-30 | 2018-03-27 | 北京锐安科技有限公司 | A kind of data label method and apparatus |
| CN107729560A (en) * | 2017-11-08 | 2018-02-23 | 北京奇虎科技有限公司 | User's portrait building method, device and computing device based on big data |
| CN107798118A (en) * | 2017-11-08 | 2018-03-13 | 北京奇虎科技有限公司 | User's portrait building method, device and computing device based on big data |
| 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 |
| CN108021929A (en) * | 2017-11-16 | 2018-05-11 | 华南理工大学 | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system |
| CN108021929B (en) * | 2017-11-16 | 2023-01-10 | 华南理工大学 | Big data-based mobile terminal e-commerce user portrait establishing and analyzing method and system |
| CN108280117A (en) * | 2017-11-22 | 2018-07-13 | 广州市动景计算机科技有限公司 | Metadata of drawing a portrait preparation method, device, storage medium and electronic equipment |
| CN109947811A (en) * | 2017-11-29 | 2019-06-28 | 北京京东金融科技控股有限公司 | Generic features library generating method and device, storage medium, electronic equipment |
| CN108021670A (en) * | 2017-12-06 | 2018-05-11 | 中国南方航空股份有限公司 | Multi-source heterogeneous data fusion system and method |
| CN109936549A (en) * | 2017-12-18 | 2019-06-25 | 航天信息股份有限公司 | Audit data processing method and device based on PKI platform |
| CN108154401A (en) * | 2018-01-15 | 2018-06-12 | 网易无尾熊（杭州）科技有限公司 | User's portrait depicting method, device, medium and computing device |
| CN108269128B (en) * | 2018-01-22 | 2022-03-08 | 北京小米移动软件有限公司 | Advertisement putting method, device, equipment and storage medium |
| CN110431585A (en) * | 2018-01-22 | 2019-11-08 | 华为技术有限公司 | A kind of generation method and device of user's portrait |
| CN108269128A (en) * | 2018-01-22 | 2018-07-10 | 北京小米移动软件有限公司 | Put-on method, device, equipment and the storage medium of advertisement |
| CN110431585B (en) * | 2018-01-22 | 2024-03-15 | 华为技术有限公司 | User portrait generation method and device |
| CN108335147B (en) * | 2018-02-28 | 2021-08-13 | 北京搜狐新媒体信息技术有限公司 | Data analysis method and system based on user behaviors |
| CN108335147A (en) * | 2018-02-28 | 2018-07-27 | 北京搜狐新媒体信息技术有限公司 | A kind of data analysing method and system based on user behavior |
| CN108509569B (en) * | 2018-03-26 | 2022-06-03 | 河北省科学院应用数学研究所 | Method and device for generating enterprise portrait, electronic equipment and storage medium |
| CN108509569A (en) * | 2018-03-26 | 2018-09-07 | 河北省科学院应用数学研究所 | Generation method, device, electronic equipment and the storage medium of enterprise's portrait |
| CN108763278B (en) * | 2018-04-11 | 2021-01-01 | 口碑(上海)信息技术有限公司 | Statistical method and device for user characteristic labels |
| CN108763278A (en) * | 2018-04-11 | 2018-11-06 | 口碑(上海)信息技术有限公司 | The statistical method and device of user characteristics label |
| CN108628980A (en) * | 2018-04-27 | 2018-10-09 | 四川斐讯信息技术有限公司 | A kind of user's portrait method and system based on user network behavior |
| CN108629633A (en) * | 2018-05-09 | 2018-10-09 | 浪潮软件股份有限公司 | A kind of method and system for establishing user's portrait based on big data |
| CN108363821A (en) * | 2018-05-09 | 2018-08-03 | 深圳壹账通智能科技有限公司 | A kind of information-pushing method, device, terminal device and storage medium |
| CN108898413A (en) * | 2018-05-14 | 2018-11-27 | 链家网（北京）科技有限公司 | A kind of traveller's management method and device |
| CN108830298A (en) * | 2018-05-21 | 2018-11-16 | 麒麟合盛网络技术股份有限公司 | A kind of method and device of determining user characteristics label |
| CN108830298B (en) * | 2018-05-21 | 2021-07-23 | 麒麟合盛网络技术股份有限公司 | Method and device for determining user feature tag |
| CN109033149B (en) * | 2018-06-12 | 2020-11-13 | 北京奇艺世纪科技有限公司 | Information recommendation method and device, server and storage medium |
| CN109033149A (en) * | 2018-06-12 | 2018-12-18 | 北京奇艺世纪科技有限公司 | Information recommendation method, device, server and storage medium |
| CN109064210A (en) * | 2018-06-29 | 2018-12-21 | 康美药业股份有限公司 | A kind of method that establishing user tag library, electronic equipment, storage medium and system |
| CN109241461A (en) * | 2018-08-10 | 2019-01-18 | 新华三信息安全技术有限公司 | A kind of user draws a portrait construction method and device |
| CN109241461B (en) * | 2018-08-10 | 2020-05-22 | 新华三信息安全技术有限公司 | User portrait construction method and device |
| CN109347903B (en) * | 2018-08-28 | 2021-02-26 | 浙江工业大学 | Campus message pushing optimization method based on GIS (geographic information System) |
| CN109347903A (en) * | 2018-08-28 | 2019-02-15 | 浙江工业大学 | A kind of campus message pushing and optimizing method based on generalized information system |
| CN109242309A (en) * | 2018-09-05 | 2019-01-18 | 广州视源电子科技股份有限公司 | The user that attends a meeting portrait generation method, device, intelligent meeting equipment and storage medium |
| CN110941823B (en) * | 2018-09-21 | 2022-06-21 | 武汉安天信息技术有限责任公司 | Threat information acquisition method and device |
| CN110941823A (en) * | 2018-09-21 | 2020-03-31 | 武汉安天信息技术有限责任公司 | Threat information acquisition method and device |
| CN110968572B (en) * | 2018-09-29 | 2022-11-18 | 北京小米移动软件有限公司 | User portrait data cleaning method and device |
| CN109271423A (en) * | 2018-09-29 | 2019-01-25 | 深圳市轱辘汽车维修技术有限公司 | A kind of object recommendation method, apparatus, terminal and computer readable storage medium |
| CN110968572A (en) * | 2018-09-29 | 2020-04-07 | 北京小米移动软件有限公司 | User portrait data cleaning method and device |
| WO2020082596A1 (en) * | 2018-10-23 | 2020-04-30 | 深圳壹账通智能科技有限公司 | Data processing-based automatic user profile generating method and system |
| 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 |
| CN109271392A (en) * | 2018-10-30 | 2019-01-25 | 长威信息科技发展股份有限公司 | Quick discrimination and the method and apparatus for extracting relevant database entity and attribute |
| CN109472490A (en) * | 2018-11-06 | 2019-03-15 | 北京京航计算通讯研究所 | Military project group personal information labeling system based on cluster |
| CN109271593A (en) * | 2018-11-06 | 2019-01-25 | 北京京航计算通讯研究所 | Military project group personal information labeling process based on cluster |
| CN109408723A (en) * | 2018-11-06 | 2019-03-01 | 北京奇艺世纪科技有限公司 | A kind of method for pushing and device |
| CN109684373B (en) * | 2018-11-26 | 2023-07-18 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Key relation person discovery method based on travel and call ticket data analysis |
| CN109684373A (en) * | 2018-11-26 | 2019-04-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Emphasis party based on trip and call bill data analysis has found method |
| CN111277995B (en) * | 2018-12-05 | 2023-04-07 | 中国移动通信集团甘肃有限公司 | Method and equipment for identifying terminal user |
| CN111277995A (en) * | 2018-12-05 | 2020-06-12 | 中国移动通信集团甘肃有限公司 | Method and equipment for identifying terminal user |
| CN109684539A (en) * | 2018-12-07 | 2019-04-26 | 陈包容 | It is a kind of based on the user of cell phone apparatus information and internet information draw a portrait method |
| CN109670112A (en) * | 2018-12-20 | 2019-04-23 | 北京城市网邻信息技术有限公司 | A kind of generation method, device, storage medium and the terminal of user's portrait ID |
| CN109886719A (en) * | 2018-12-20 | 2019-06-14 | 平安科技（深圳）有限公司 | Data mining processing method, device and computer equipment based on grid |
| CN109815386A (en) * | 2018-12-21 | 2019-05-28 | 厦门市美亚柏科信息股份有限公司 | A kind of construction method, device and storage medium based on user's portrait |
| CN109815987B (en) * | 2018-12-27 | 2020-12-01 | 北京卓思天成数据咨询股份有限公司 | Crowd classification method and system |
| CN111382343A (en) * | 2018-12-27 | 2020-07-07 | 方正国际软件(北京)有限公司 | Label system generation method and device |
| CN111382343B (en) * | 2018-12-27 | 2023-11-28 | 方正国际软件(北京)有限公司 | Label system generation method and device |
| CN109815987A (en) * | 2018-12-27 | 2019-05-28 | 北京卓思天成数据咨询股份有限公司 | A kind of listener clustering method and categorizing system |
| CN109710697A (en) * | 2018-12-28 | 2019-05-03 | 厦门笨鸟电子商务有限公司 | A kind of generation method of corporate user's portrait |
| CN111428124A (en) * | 2019-01-10 | 2020-07-17 | 珠海金山办公软件有限公司 | Method, system, terminal and storage medium for marking user |
| CN109919652A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | User group's classification method, device, equipment and storage medium |
| CN111491060A (en) * | 2019-01-28 | 2020-08-04 | 百度在线网络技术（北京）有限公司 | Information click log and ticket splicing method and device |
| CN109919437A (en) * | 2019-01-29 | 2019-06-21 | 特斯联（北京）科技有限公司 | A kind of smart travel target matching method and system based on big data |
| CN109919437B (en) * | 2019-01-29 | 2020-01-31 | 特斯联（北京）科技有限公司 | big data-based intelligent tourism target matching method and system |
| CN109905873B (en) * | 2019-02-25 | 2021-08-31 | 国家计算机网络与信息安全管理中心 | Network account correlation method based on characteristic identification information |
| CN109905873A (en) * | 2019-02-25 | 2019-06-18 | 国家计算机网络与信息安全管理中心 | A kind of network account correlating method based on signature identification information |
| CN109933699A (en) * | 2019-03-05 | 2019-06-25 | 中国科学院文献情报中心 | A kind of construction method and device of academic portrait model |
| CN109934638A (en) * | 2019-03-21 | 2019-06-25 | 南京金信通信息服务有限公司 | A method of according to the graphical customer portrait of user tag and early warning |
| CN110135901A (en) * | 2019-05-10 | 2019-08-16 | 重庆天蓬网络有限公司 | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment |
| CN112001739A (en) * | 2019-05-27 | 2020-11-27 | 广东小天才科技有限公司 | Method and system for generating user learning portrait |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110263053A (en) * | 2019-06-17 | 2019-09-20 | 浙江每日互动网络科技股份有限公司 | A kind of server obtaining mobile terminal portrait label based on mobile terminal data |
| CN110263126A (en) * | 2019-06-20 | 2019-09-20 | 维沃移动通信有限公司 | A kind of generation method and mobile terminal of user's portrait |
| CN113316778A (en) * | 2019-06-24 | 2021-08-27 | 深圳市欢太科技有限公司 | Equipment recommendation method and related product |
| CN110442572A (en) * | 2019-06-28 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The determination method and device of user characteristics value |
| CN110442572B (en) * | 2019-06-28 | 2024-02-02 | 创新先进技术有限公司 | User characteristic value determining method and device |
| CN113366469A (en) * | 2019-06-29 | 2021-09-07 | 深圳市欢太科技有限公司 | Data classification method and related product |
| CN110489660B (en) * | 2019-07-22 | 2020-12-18 | 武汉大学 | User economic condition portrait method of social media public data |
| CN110489660A (en) * | 2019-07-22 | 2019-11-22 | 武汉大学 | A kind of user's economic situation portrait method of social media public data |
| CN112311612A (en) * | 2019-07-29 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Family portrait construction method and device and storage medium |
| CN110659414A (en) * | 2019-09-02 | 2020-01-07 | 惠州学院 | User portrait based personalized information pushing method and user side |
| CN110659414B (en) * | 2019-09-02 | 2023-01-13 | 惠州学院 | User portrait based personalized information pushing method and user side |
| CN111918323A (en) * | 2019-09-18 | 2020-11-10 | 北京云海淘金数据技术有限公司 | Data calibration method, device, equipment and storage medium |
| CN110674410B (en) * | 2019-10-08 | 2022-05-24 | 北京物灵科技有限公司 | User portrait construction and content recommendation method, device and equipment |
| CN110674410A (en) * | 2019-10-08 | 2020-01-10 | 北京物灵科技有限公司 | User portrait construction and content recommendation method, device and equipment |
| CN110781930A (en) * | 2019-10-14 | 2020-02-11 | 西安交通大学 | User portrait grouping and behavior analysis method and system based on log data of network security equipment |
| CN110942337A (en) * | 2019-10-31 | 2020-03-31 | 天津中科智能识别产业技术研究院有限公司 | Accurate tourism marketing method based on internet big data |
| WO2021087684A1 (en) * | 2019-11-04 | 2021-05-14 | 深圳市欢太科技有限公司 | Method and apparatus for processing user behavior data, server, and storage medium |
| CN113065883A (en) * | 2020-01-02 | 2021-07-02 | 中国移动通信集团广东有限公司 | Method and device for delivering advertisements |
| WO2021155691A1 (en) * | 2020-02-07 | 2021-08-12 | 腾讯科技（深圳）有限公司 | User portrait generating method and apparatus, storage medium, and device |
| CN111400599A (en) * | 2020-03-17 | 2020-07-10 | 苏宁金融科技(南京)有限公司 | User group portrait generation method, device and system |
| CN111444236B (en) * | 2020-03-23 | 2023-04-28 | 华南理工大学 | Mobile terminal user portrait construction method and system based on big data |
| CN111444236A (en) * | 2020-03-23 | 2020-07-24 | 华南理工大学 | Mobile terminal user portrait construction method and system based on big data |
| CN111709843A (en) * | 2020-05-09 | 2020-09-25 | 中国人民财产保险股份有限公司 | Client portrait generation method and device and electronic equipment |
| CN111709843B (en) * | 2020-05-09 | 2023-07-28 | 中国人民财产保险股份有限公司 | Customer portrait generation method and device and electronic equipment |
| CN111640436A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Method for providing a dynamic customer representation of a call partner to an agent |
| CN111640436B (en) * | 2020-05-15 | 2024-04-19 | 北京青牛技术股份有限公司 | Method for providing dynamic customer portraits of conversation objects to agents |
| CN111625726A (en) * | 2020-06-02 | 2020-09-04 | 小红书科技有限公司 | User portrait processing method and device |
| CN112000748A (en) * | 2020-07-14 | 2020-11-27 | 北京神州泰岳智能数据技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN111798351A (en) * | 2020-09-09 | 2020-10-20 | 北京神州泰岳智能数据技术有限公司 | Data processing method and device and readable storage medium |
| CN112214556B (en) * | 2020-09-30 | 2024-02-23 | 招商局金融科技有限公司 | Label generation method, label generation device, electronic equipment and computer readable storage medium |
| CN112214556A (en) * | 2020-09-30 | 2021-01-12 | 招商局金融科技有限公司 | Label generation method and device, electronic equipment and computer readable storage medium |
| CN112631889A (en) * | 2020-12-31 | 2021-04-09 | 中国农业银行股份有限公司 | Portrayal method, device and equipment for application system and readable storage medium |
| CN112631889B (en) * | 2020-12-31 | 2024-02-23 | 中国农业银行股份有限公司 | Portrayal method, device, equipment and readable storage medium for application system |
| CN113065895A (en) * | 2021-03-29 | 2021-07-02 | 上海酷量信息技术有限公司 | Advertisement recommendation method and device based on geographic position |
| CN113010795A (en) * | 2021-04-12 | 2021-06-22 | 北京明略软件系统有限公司 | User dynamic portrait generation method, system, storage medium and electronic device |
| CN113923156A (en) * | 2021-09-29 | 2022-01-11 | 湖北美和易思教育科技有限公司 | Intelligent gateway management method and system based on multi-path network |
| CN113923156B (en) * | 2021-09-29 | 2023-04-11 | 武汉美和易思数字科技有限公司 | Intelligent gateway management method and system based on multi-path network |
| CN114722252A (en) * | 2022-03-18 | 2022-07-08 | 深圳市小满科技有限公司 | Foreign trade user classification method based on user portrait and related equipment |
| CN117435449A (en) * | 2023-11-06 | 2024-01-23 | 广州丰石科技有限公司 | User portrait analysis method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503015A (en) | A kind of method for building user's portrait | |
| CN106504099A (en) | A kind of system for building user's portrait | |
| US11843651B2 (en) | Personalized recommendation method and system, and terminal device | |
| CN102075851B (en) | Method and system for acquiring user preference in mobile network | |
| US20110082848A1 (en) | Systems, methods and computer program products for search results management | |
| CN108140041B (en) | For the viewing time cluster of video search | |
| CN105493057B (en) | The content selection controlled using accuracy | |
| CN107862553A (en) | Advertisement real-time recommendation method, device, terminal device and storage medium | |
| CN104395901B (en) | For user to be promoted to obtain the method and system of content | |
| CN105045916A (en) | Mobile game recommendation system and recommendation method thereof | |
| US20120078725A1 (en) | Method and system for contextual advertisement recommendation across multiple devices of content delivery | |
| KR101803049B1 (en) | User list generation and identification | |
| CN101329674A (en) | System and method for providing personalized searching | |
| CN104008184A (en) | Method and device for pushing information | |
| CN105718184A (en) | Data processing method and apparatus | |
| CN102859516A (en) | Generating improved document classification data using historical search results | |
| CN102054003A (en) | Methods and systems for recommending network information and creating network resource index | |
| TW200917070A (en) | System and method to facilitate matching of content to advertising information in a network | |
| CN108885624A (en) | Information recommendation system and method | |
| US10853424B1 (en) | Content delivery using persona segments for multiple users | |
| CN103617230A (en) | Method and system for advertisement recommendation based microblog | |
| CN102708174A (en) | Method and device for displaying rich media information in browser | |
| US20100318427A1 (en) | Enhancing database management by search, personal search, advertising, and databases analysis efficiently using core-set implementations | |
| US20110184815A1 (en) | System and method for sharing profits with one or more content providers | |
| CN102446191A (en) | Method for generating webpage content abstracts and equipment and system adopting same |
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: 20170315 |