CN109033149A - Information recommendation method, device, server and storage medium - Google Patents
Information recommendation method, device, server and storage medium Download PDFInfo
- Publication number
- CN109033149A CN109033149A CN201810601202.XA CN201810601202A CN109033149A CN 109033149 A CN109033149 A CN 109033149A CN 201810601202 A CN201810601202 A CN 201810601202A CN 109033149 A CN109033149 A CN 109033149A
- Authority
- CN
- China
- Prior art keywords
- user
- terminal
- portrait
- log data
- internet log
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of information recommendation method, device, server and storage mediums, this method comprises: obtaining the single user internet log data of first terminal and multi-user's internet log data of second terminal when detecting that first terminal is connect with second terminal by multi-screen interactive;According to single user internet log data and multi-user's internet log data, generates and draw a portrait with first terminal and the corresponding user of second terminal;When detecting first terminal with second terminal multi-screen interactive and connecting disconnection, the current internet log data of second terminal are obtained;Current internet log data at least one user portrait corresponding with second terminal is matched;Determine target user's portrait that match degree is greater than the preset threshold;It is drawn a portrait according to target user and recommends target information to second terminal.Internet log data when the present invention can be connected according to multi-screen interactive generate accurate user's portrait, to carry out accurate information recommendation, improve the accuracy of information recommendation.
Description
Technical field
The present invention relates to computer processing technical field, more particularly to a kind of information recommendation method, device, server and
Storage medium.
Background technique
With the development of internet, people's lives are more and more closely connected together with internet.At this
In the allegro epoch, user wants to quickly find the product oneself needed by internet, but the product number of magnanimity
According to constantly being generated in internet daily, this cause Internet user be difficult to quickly find it is oneself needs or interested
Information.
In order to allow user to quickly find oneself interested information and product, traditional information recommendation method is according to one
The user history information (such as purchasing history, play history, search history etc.) recorded on a terminal device carries out product (example
Such as commodity) or information (such as video, short-sighted frequency, advertisement) recommendation.
But when a terminal device may be that multi-user shared equipment (can setting by multiple user's cross-references
It is standby) when, such as television set, computer etc., then historical information of its record can then cover usage record (such as the husband of multiple users
Two people of wife use television set, then usage record includes husband's and wife's).So pass through the user on the terminal device
When historical information carries out information recommendation, then generally recommend accuracy rate lower.
Therefore, the information recommendation method in traditional technology is low in the prevalence of information recommendation accuracy, recommendation effect is poor
Problem.
Summary of the invention
The present invention provides a kind of information recommendation method, device, server and storage mediums, to solve in traditional technology
The problem that information recommendation accuracy is low present in information recommendation method, recommendation effect is poor.
To solve the above-mentioned problems, in a first aspect, the embodiment of the invention provides a kind of information recommendation method, the method
Include:
When detecting that first terminal is connect with second terminal by multi-screen interactive, the single user online of first terminal is obtained
Multi-user's internet log data of daily record data and second terminal, wherein the first terminal is personal device, and described second eventually
End is multi-user shared equipment, and multi-user's internet log data include the user of at least two first terminals described in the use
The internet log data generated when second terminal;
According to the single user internet log data and multi-user's internet log data, generate and the first terminal
And the corresponding user's portrait of the second terminal;
When detecting the first terminal with second terminal multi-screen interactive and connecting disconnection, obtain second terminal it is current on
Net daily record data;
The current internet log data at least one user portrait corresponding with the second terminal is matched;
Determine target user's portrait that match degree is greater than the preset threshold;
It is drawn a portrait according to the target user and recommends target information to the second terminal.
Optionally, described according to the single user internet log data and multi-user's internet log data, generate with
The first terminal and the corresponding user's portrait of the second terminal, comprising:
Attributive character extraction is carried out to the single user internet log data, obtains first corresponding to the first terminal
Attributive character;
Attributive character extraction is carried out to multi-user's internet log data, obtains second corresponding to the second terminal
Attributive character;
By first attributive character and second attributive character respectively with the attributive character in default multidimensional tag library
It is matched, determines corresponding with first attributive character the first label, and corresponding with second attributive character the
Two labels, wherein the default multidimensional tag library includes the corresponding relationship for having trained label and attributive character;
According to first object label identical in first label and second label building and the first terminal
And the corresponding user's portrait of the second terminal, wherein user's portrait includes the first object label.
Optionally, described that the current internet log data at least one user corresponding with the second terminal draws a portrait
It is matched, comprising:
Attributive character extraction is carried out to the current internet log data, obtains target category corresponding with the second terminal
Property feature;
The objective attribute target attribute feature is matched with the attributive character in the default multidimensional tag library, it is determining with it is described
Corresponding second target labels of objective attribute target attribute feature;
By the first object label difference of second target labels each user's portrait corresponding with the second terminal
It is matched, wherein the second terminal corresponds at least one user portrait;
The determination target user that match degree is greater than the preset threshold portrait, comprising:
In at least one user corresponding with second terminal portrait, the determining matching with second target labels
Degree is greater than the corresponding target user's portrait of first object label of preset threshold.
Second aspect, the embodiment of the invention also provides a kind of information recommending apparatus, described device includes:
First obtains module, for when detecting that first terminal is connect with second terminal by multi-screen interactive, acquisition the
The single user internet log data of one terminal and multi-user's internet log data of second terminal, wherein the first terminal is
Personal device, the second terminal are multi-user shared equipment, and multi-user's internet log data include at least two first
The internet log data that the user of terminal is generated when using the second terminal;
Generation module, for generating according to the single user internet log data and multi-user's internet log data
User corresponding with the first terminal and the second terminal draws a portrait;
Second obtains module, for when detect the first terminal with second terminal multi-screen interactive and connect disconnect when, obtain
Take the current internet log data of second terminal;
Matching module, for will the current internet log data at least one user picture corresponding with the second terminal
As being matched;
Determining module, for determining that the target user that match degree is greater than the preset threshold draws a portrait;
Recommending module recommends target information to the second terminal for drawing a portrait according to the target user.
Optionally, the generation module includes:
First extracting sub-module is corresponded to for carrying out attributive character extraction to the single user internet log data
In the first attributive character of the first terminal;
Second extracting sub-module is corresponded to for carrying out attributive character extraction to multi-user's internet log data
In the second attributive character of the second terminal;
First matched sub-block, for by first attributive character and second attributive character respectively with default multidimensional
Attributive character in tag library is matched, and determines corresponding with first attributive character the first label, and with described the
Corresponding second label of two attributive character, wherein the default multidimensional tag library includes pair for having trained label and attributive character
It should be related to;
Submodule is constructed, for constructing according to first object label identical in first label and second label
User corresponding with the first terminal and the second terminal draws a portrait, wherein user's portrait includes described first
Target labels.
Optionally, the matching module includes:
Third extracting sub-module, for carrying out attributive character extraction to the current internet log data, obtain with it is described
The corresponding objective attribute target attribute feature of second terminal;
Second matched sub-block, for by the attributive character in the objective attribute target attribute feature and the default multidimensional tag library
It is matched, determines the second target labels corresponding with the objective attribute target attribute feature;
Third matched sub-block, for second target labels each user corresponding with the second terminal to draw a portrait
First object label matched respectively, wherein the second terminal correspond at least one user portrait;
The determining module includes:
Determine submodule, it is determining with described at least one user corresponding with second terminal portrait
The corresponding target user's portrait of the two target labels first object label that match degree is greater than the preset threshold.
The third aspect, the embodiment of the invention also provides a kind of servers, comprising: memory, processor and is stored in institute
The computer program that can be run on memory and on the processor is stated, when the computer program is executed by the processor
The step of realizing the information recommendation method.
Fourth aspect, it is described computer-readable to deposit the embodiment of the invention also provides a kind of computer readable storage medium
It is stored with computer program on storage media, the information recommendation method is realized when the computer program is executed by processor
Step.
Compared with prior art, the present invention includes the following advantages:
In this way, the present invention is implemented after its personal device and multi-user shared equipment are carried out multi-screen interactive connection by user
The method of example can generate three-dimensional user to the user and draw a portrait, then after the two disconnects multi-screen interactive connection, as the user
When the multi-user shared equipment operated again, the present invention can be multi-user shared to determine according to its current internet log data
The user for corresponding to the user in equipment corresponding at least one user portrait draws a portrait, thus according to the user draw a portrait come to its into
The accurate information recommendation of row, improves the accuracy of information recommendation, recommendation effect is good.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of information recommendation method embodiment of the invention;
Fig. 2 is a kind of structural block diagram of information recommending apparatus embodiment of the invention.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Referring to Fig.1, a kind of step flow chart of information recommendation method embodiment of the invention is shown, this method can be single
Solely it is applied to server;It can also be respectively applied to multiple equipment, here may include first terminal, second terminal and service
Device;Second terminal can also be applied individually to any.
This method can specifically include following steps:
Step 101, when detecting that first terminal is connect with second terminal by multi-screen interactive, the list of first terminal is obtained
Multi-user's internet log data of user's internet log data and second terminal, wherein the first terminal is personal device, institute
Stating second terminal is multi-user shared equipment;
Wherein, multi-user's internet log data include the user of at least two first terminals whole using described second
The internet log data generated when end;
Such as personal device includes the mobile phone of the mobile phone of user A, user B, multi-user shared equipment is user A and user B
The television set used, then the internet log data on television set include user A using television set when the internet log number that generates
The internet log data generated when according to user B using television set.
Wherein, multi-screen interactive connection refer to: with preset protocol (including but not limited to IGRS protocol, Miracast agreement,
DLNA agreement, other proprietary protocols etc.) keep two multimedia terminals (such as common based on IOS, Android, Symbian difference
The different intelligent terminal device of operating system, such as mobile phone, PAD, TV etc.) it is connected by the same WIFI network.
It is connected, can be carried out in different multimedia terminal in multimedia (audio, video, picture etc.) by multi-screen interactive
The sequence of operations such as transmission, parsing, displaying and the control of appearance, and can be in different multimedia terminal in shared displaying simultaneously
Hold, enriches the multimedia life of user.
For popular, multi-screen interactive connection is exactly that first terminal can be mutual by special connection equipment with second terminal
Be connected conversion.For example the film on mobile phone can play on TV, the picture on tablet computer can be shared on TV,
The content of computer can project to viewing etc. on TV.
In this step, (wherein, when detecting that first terminal is connect with second terminal by the multi-screen interactive of above-mentioned explanation
The first terminal is personal device, and the second terminal is multi-user shared equipment), so that it may obtain being applied alone for first terminal
Multi-user's internet log data of family internet log data and second terminal.
Wherein, so-called personal device, i.e., the personal device used by sole user, such as PC, personal mobile phone etc.
Deng (owner that the internet log data that record on personal device belong to the personal device being defaulted here, even if the owner
Authorize other people that the personal device can be used, it is to meet this to own that the internet log data recorded on the personal device, which are also defaulted,
The viewing demand of person);So-called multi-user shared equipment, i.e., the equipment that multiple users can share, such as home television set.
Wherein, here single user internet log data and multi-user's internet log data are all user's online in terminal
Daily record data, and name why is distinguished here, reason is that first terminal default is used by the same person, therefore, corresponds to
Internet log data be a corresponding user, so referred to as single user internet log data;And second terminal is multiple use
The shared device that family uses, therefore, online daily record data is corresponding multiple users, so referred to as multi-user's internet log number
According to.
And internet log data include but are not limited to mobile Internet internet log data, on wire/wireless internet
Net daily record data etc..
Step 102, according to the single user internet log data and multi-user's internet log data, generate with it is described
First terminal and the corresponding user's portrait of the second terminal;
For example, the corresponding user of first terminal is user A, and the corresponding user of second terminal is user A and user B,
So in the prior art when forming user's portrait, corresponding the is mainly generated using the user's history data of first terminal
The user of one terminal draws a portrait, so that being drawn a portrait according to the user carries out information recommendation;And utilize multiple users of second terminal
Historical data is drawn a portrait to generate the user of corresponding second terminal, so that being drawn a portrait according to the user carries out information recommendation.Pass through in this way
When user's history data documented by single terminal carry out information recommendation, since its user's portrait generated can not be complete
Or the feature of the user of the currently used terminal is accurately given expression to, it is low so as to cause information recommendation accuracy rate, recommendation effect is poor
The problem of.
In order to solve the above-mentioned technical problem, in embodiments of the present invention, a use is being generated to multi-user shared equipment side
It, can be according to the single user internet log data and use on the personal device of the user A when user's portrait at family (such as user A)
Multi-user's internet log data in the group of family in the multi-user shared equipment including user A, i.e., used using the same user
The internet log data of multiple terminals, to generate user's portrait of user A (that is, eventually with the first terminal and described second
The corresponding user's portrait in end), which draws a portrait and had both corresponded to personal device-first terminal of user A, and corresponding
In the multi-user shared equipment-second terminal that user A and user B are used in conjunction with.
Similarly, when user B is also using the personal device of oneself come (user A and user B are total with above-mentioned multi-user shared equipment
Equipment) carry out multi-screen interactive connection when, the method for the embodiment of the present invention can equally be remembered respectively according in this two equipment
The internet log data of record, the user for generating user B to multi-user shared equipment side draw a portrait, and user portrait both corresponded to
The personal device of user B, also correspond to the multi-user shared equipment that user A and user B are used in conjunction with.
In this way, the method by means of the embodiment of the present invention just combines user A in personal device A and multi-user shared equipment
Internet log data on (user group includes user A, user B) generate to be directed to multi-user shared equipment dedicated for the use
User's portrait A of family A;Similarly, the user portrait B dedicated for the user B can also be generated for multi-user shared equipment, etc.
Deng.
User's internet log data can be utilized using any one in known method for the implementation method of step 102
Realize that the present invention does not limit this, there is illustrated the lifes of one embodiment of the invention to generate the algorithm of user's portrait
At the method that user draws a portrait, following sub-step can specifically include:
S21 carries out attributive character extraction to the single user internet log data, obtains corresponding to the first terminal
First attributive character;
S22 carries out attributive character extraction to multi-user's internet log data, obtains corresponding to the second terminal
Second attributive character;
It is extracted by the attributive character to internet log data, the attributive character of the user of available using terminal.Its
In, which corresponds to a user, such as user A.And the second attributive character then corresponds to multiple use
Family, for example including user A and user B.
The attributive character of user refers to the key message that can be identified for that user characteristics.
It wherein,, can be by online when carrying out attributive character extraction to internet log data in the embodiment of the present invention
(i.e. in real time) and the mode combined offline carry out feature extraction to above two internet log data respectively, to obtain user
Attributive character.Online processing mode can only be handled current internet internet log data, and processed offline mode
It can be analyzed and processed in conjunction with historical storage data, so as to the user property feature that do not extracted to online processing mode
Carry out supplement and it is perfect.
Internet internet log data are handled by online and offline processing mode, so as to by current data
It is associated mining analysis with historical data, so that the user property feature extracted is more comprehensively complete.
S23, by first attributive character and second attributive character respectively with the attribute in default multidimensional tag library
Feature is matched, and determines the first label corresponding with first attributive character, and corresponding with second attributive character
The second label, wherein the default multidimensional tag library includes the corresponding relationship for having trained label and attributive character;
In embodiments of the present invention, multidimensional tag library refers to the general designation that multiple and different feature databases are combined.Wherein, special
Sign library is and the spy that label and the corresponding relationship of attributive character obtained from constantly training are constituted by counting to big data analysis
Levy library.Wherein, which can be various dimensions.
Wherein, in one embodiment, the embodiment of the present invention can in advance make user's internet behavior rule statistics, APP
With rule, user's internet content Feature Words extract, information of mobile phone terminal is integrated, the more of the portrait analysis feature of multidimensional are formed
Dimension label library.
For example the internet internet log data of all users are analyzed and counted, it determines in accessed network address containing predetermined
Field is tour site, and all websites containing the scheduled field are used as to the attributive character of tour site, and travels and then make
For the corresponding label of the attributive character, then by constantly to user's internet behavior rule statistics, APP laws of use statistics,
The operations such as user's internet content Feature Words extraction, so that it may form huge multidimensional tag library.
When by being matched from the attributive character extracted in internet log data with the attributive character in multidimensional tag library,
As long as the website of user's access belongs to the website comprising the scheduled field, i.e., use can be obtained by by the matching of multidimensional tag library
One label at family is " tourism ".And in the matching process of multidimensional tag library, the label of available multiple dimensions, thus
Obtain various dimensions label.
Such as user A searched for website 1, website 2, website 3 on personal device.And in the network address of above three website
Including the distinctive certain field of tour site, then the method for the embodiment of the present invention can by website 1, website 2 and website 3 respectively with
Attributive character in multidimensional tag library is matched, then finding the equal corresponding label " trip of these three attributive character through overmatching
Trip ", therefore, label " tourism " is exactly and the matched label of above three attributive character.
So in the present embodiment, can by the first attributive character of the user A from personal device respectively with it is default more
Attributive character in dimension label library is matched, so that it is determined that with matched first label of the first attributive character (wherein, due to more
In dimension label library, a label can correspond to a variety of attributive character, and therefore, different attributive character can be matched to identical mark
Label);Wherein, the quantity of the first label is one or more.
It similarly, can also be by the second attributive character of the online feature of the multiple users of embodiment from multi-user shared equipment
It is matched respectively with the attributive character in default multidimensional tag library, so that it is determined that with matched second mark of the second attributive character
Label.Wherein, the quantity of the second label is one or more.
In addition, in one embodiment, the multidimensional tag library in the embodiment of the present invention include but is not limited to be operator's base
Plinth information bank, terminal type base library, application program class library, uniform resource locator (Uniform Resource
Locator, URL) class library, access website and Behavior law statistical nature library, internet content cluster result library, user group point
Class libraries, name Entity recognition contents extraction library, dynamic labels Classification Management library, internet site feature database, historical user's interest
Focus and terminal motion track variation library etc..
Wherein, in the embodiment of the present invention, the various dimensions label of user is the main element for constructing user's portrait.In the present invention
Various dimensions label refer to from multiple dimensions reflection user characteristics label.Wherein, the various dimensions in the embodiment of the present invention
Label includes, but is not limited to the essential attribute label, social property label, online row of first terminal user (such as user A)
For attribute tags, behavioural habits attribute tags and interest attribute feature tag.
Further, the essential attribute label of user include but is not limited to be user name, user identifier, gender, 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 models, terminal operation device
And one or more of the application program of terminal installation.And social property label include but is not limited to be industry, occupation,
One of job site, place of abode, bank card, member card and vehicles are a variety of.Internet behavior attribute tags packet
Browsing, search, downloading, purchase and comment etc. are included but are not limited to, and it is day that behavioural habits attribute tags, which include but is not limited to,
Equal surf time, normal Website login and common application program etc..Interest attribute feature tag include but is not limited to be sport, sound
Pleasure, social activity, information, shopping, leisure, tourism, game and Investment & Financing etc..
Wherein, the essential attribute label of user is that usually to embody is user's static attribute, is metastable information, example
Such as gender, age.And that social property, internet behavior attribute, behavioural habits attribute, interest attribute feature are embodied is user
Dynamic attribute, be continually changing attribute at any time.And exactly these continually changing dynamic attributes just can really embody
User group's differentiation feature.
In specific implementation, comprehensive analysis the dynamic attribute feature of user can be determined in the following manner:
1) often go the website (type) of logon, user are common to answer by the average daily surf time of counting user, user
With program APP and using the time of common APP, so that the behavioural habits attributive character to user is analyzed.
2) carry out comprehensive analysis user from user content preference/fragmentation surf time preference/customer service preference etc.
Interest attribute feature.Such as according to user online different behavior act behaviors (for example, browsing, search, downloading, purchase and
Comment etc.) or the APP type (for example, comprising various APP application, often going Type of website etc. of access) that uses of user or
User surfs the Internet the content-data generated: the purchase type of merchandise, browsed web content, search content, download type etc. of content into
Row comprehensive analysis obtains the interest attribute feature of user.Just in the internet log data of such as one user, search, browsing
Mostly be shopping website or the application program used it is shopping class application mostly, can determines that shopping is one of the user emerging
Interesting attributive character or user search, browsing and comment are tour site or most-often used application mostly
Program is tourism application, then can determine that tourism is the interest attribute feature of the user, and so on.
Highly refined signature identification as defined in label is usually manual, such as age bracket label: 25~35 years old, region mark
Label: Beijing, label show two important features: 1, semantization, and people can easily understand each meaning tag.This but also
User's portrait model has practical significance.Business demand can preferably be met.Such as, judge user preference.2, short text, each
Label usually only indicates a kind of meaning, and label itself no longer needs to do the pretreatment works such as excessive text analyzing, this is to utilize machine
Extraction standard information is provided convenience.So understanding in this sense, user's portrait is the summation of user tag.
S24, according to first object label identical in first label and second label building and described first
Terminal and the corresponding user's portrait of the second terminal, wherein user's portrait includes the first object label.
Wherein it is possible to determine identical label, i.e. first object label in the first label and the second label.Because first
Target labels can embody browsing feature of the user A in the example above on personal device and multi-user shared equipment, because
This, can be constructed using first object label and be drawn a portrait with the personal device and the corresponding user of multi-user shared equipment, i.e.,
Portrait of the user A in multi-user shared equipment.
Similarly, when user B is connect using the mobile phone of oneself with TV multi-screen interactive, the method for the embodiment of the present invention is same
The portrait with the mobile phone of user B and the corresponding user B of the TV can be constructed, in this way, used for this multi-user
For TV, the method for the embodiment of the present invention can individually construct these people when personal device is connect with its multi-screen interactive
The user of the user of equipment draws a portrait, so that the TV has multiple independent portraits using user.
The various dimensions label obtained by above multiple multidimensional label storehouse matchings, i.e. first object label, the present invention are implemented
All labels in first object label can be associated fusion by the method for example, stamp various dimensions label for user, or
The various dimensions label stamped is updated and is supplemented, to complete the building of user's portrait.
It wherein, due to the personal user that user A is first terminal, and is one of multiple users of second terminal, therefore, this
User's portrait of the user A generated in step both corresponds to first terminal, also corresponds to second terminal.
In actual application, it when obtaining the internet log data in two terminals, can be in real time, thus logical
After the single user obtained in real time/multi-user's internet log data, it is analyzed and processed to obtain the multidimensional scale of newest user A
Label are updated or supplement to have various dimensions label on drawing a portrait to user, to depict newest containing space-time characterisation
Holographic multidimensional user portrait.
In this way, the method for the embodiment of the present invention can determine by means of two groups of internet log data in two terminals
The attributive character of single user in one terminal and the attributive character of multiple users in second terminal, and by single user
Attributive character matched respectively with the attributive character in preset various dimensions feature database with the attributive character of multiple users, from
And the first label corresponding with first attributive character is obtained, and the second label corresponding with second attributive character,
Finally, using identical label in the first label and the second label as the multidimensional attribute label of the single user, the various dimensions
The generation of attribute tags is since (personal device and multi-user are total for the different types of terminals of use by means of the single user two
With equipment) internet log data, therefore, expression feature it is more accurate, but also utilizing the multidimensional attribute label institute
User's portrait of building is more three-dimensional.
In addition, the method for the embodiment of the present invention can also can not find the attribute with user in established multidimensional tag library
When the various dimensions label of characteristic matching, the attributive character of user and corresponding various dimensions label are added to various dimensions feature database
In.In this way, to constantly update and improve multidimensional tag library.
By means of the method for step 101 and step 102, as long as being capable of personal device and multi-user shared equipment progress multi-screen
When interaction connection, the three-dimensional user that the method for the embodiment of the present invention can construct the corresponding sole user of personal device is drawn
Picture also creates corresponding this and is mostly used in this way, the three-dimensional user for generating its corresponding sole user not only for personal device draws a portrait
The three-dimensional user portrait of some user in multiple users of family shared device.
In practical applications, man and wife all uses home videos, then when husband by its mobile phone and home videos into
When row multi-screen interactive connects, the user that the method for the embodiment of the present invention can generate husband draws a portrait, and (user draws a portrait information more
It is accurate to add, the personal mobile phone not only used with reference to it, reference is also made to its Internet data using television set when);And work as wife
When its mobile phone and home videos are carried out multi-screen interactive connection, the user that wife also can be generated in the method for the embodiment of the present invention is drawn
As (user portrait information is more comprehensive, the personal mobile phone not only used with reference to it, when reference is also made to it using television set
Internet data).So that the label for user's portrait that the embodiment of the present invention generates is more comprehensive, feature is accurate.
Step 103, when detecting the first terminal with the second terminal multi-screen interactive and connecting disconnection, described in acquisition
The current internet log data of second terminal;
Wherein, such as user A is disconnected the first terminal (for example, personal mobile phone) and second terminal (family's electricity that it is used
Depending on) between multi-screen interactive connection, such as exited film throw screen.The available family of the method for so embodiment of the present invention
The current internet log data of TV.
So-called current internet log data, i.e., all data of current upper net operation.Such as internet searching some TV play
Search behavior data.
Step 104, by the current internet log data at least one user corresponding with the second terminal draw a portrait into
Row matching;
After terminating to throw screen, such as user A operates television set, i.e., carries out network operation to second terminal, then
The method of the embodiment of the present invention is available to arrive the corresponding current internet log data of the network operation, can be according to preset algorithm
The current internet log data at least one user portrait corresponding with television set is matched, television set here can be with
User's portrait of the corresponding one or more user for using the television set.
Wherein, since during executing step 101 and step 102, connecting with television set multi-screen interactive can also be wrapped
Other personal devices, such as the mobile phone of user B are included, then the use of user B also can be generated after step 101 and step 102
Family portrait, user portrait are both the personal mobile phone of corresponding user B, may correspond to the television set.Therefore, work as end
When throw the upper net operation of user A after screen is television set, which can correspond to the user of the user portrait and user B of user A
Portrait just needs the user by the user of the current internet log data of the user A and user A portrait and user B to draw a portrait here
It is matched respectively.
Step 105, target user's portrait that match degree is greater than the preset threshold is determined;
Second terminal is multi-user (including user A and user B) shared television set, and television set can correspond to multiple use
The user at family draws a portrait, and the user of user's portrait and user B including user A draws a portrait here.And the user of television set is operated here
For user A, then in practical applications, since the operation behavior of the same user is with uniformity, the two users draw
The user for being greater than the necessarily user A of preset threshold with the current operation Data Matching degree of the user A as in draws a portrait.So this step
In rapid, the user that determining target user's portrait is user A draws a portrait.
Optionally, in one embodiment, it when executing step 104, can be achieved in that
Attributive character extraction is carried out to the current internet log data, obtains target category corresponding with the second terminal
Property feature;
Specific object feature extraction principle is referring to above-mentioned sub-step S21, S22, and which is not described herein again.
The objective attribute target attribute feature is matched with the attributive character in the default multidimensional tag library, it is determining with it is described
Corresponding second target labels of objective attribute target attribute feature;
Specific matching principle is referred to the elaboration of above-mentioned sub-step S23, and which is not described herein again.
By the first object label difference of second target labels each user's portrait corresponding with the second terminal
It is matched, wherein the second terminal corresponds at least one user portrait;
Correspondingly, can then draw a portrait at least one user corresponding with the second terminal when executing step 105
In, determine that target user corresponding with second target labels first object label that match degree is greater than the preset threshold draws
Picture.
Due to multi-user shared equipment, such as television set includes user A and user B using user, and passes through step 101
With step 102, two users for generating user A and user B to the television set draw a portrait.It, can will be current so in this step
Use using the user tag of the user of television set, i.e. the second target labels, in two users portrait corresponding with the television set
Family label is matched respectively, such as the second target labels are matched with the label in the portrait of user A, obtains a mark
Sign matching degree;The second target labels are matched with the label in the portrait of user B again, tag match degree of getting back.
So in the two tag match degree, the corresponding user of tag match degree that selection is greater than preset threshold draws a portrait as current
It is drawn a portrait using the user of the user of television set, such as the user A is watched TV using the television set, then can be matched to use here
The user of family A draws a portrait.
In this way, the method for the embodiment of the present invention can be by by the attributive character in current internet log data corresponding
The various dimensions label that two target labels carry out each user's portrait corresponding with second terminal carries out matched mode, to determine and be somebody's turn to do
Target user's portrait that second target labels match.It is mutual that multi-screen is carried out with multi-user shared equipment when the personal device of user
When dynamic connection and then disconnection, which operates the multi-user shared equipment again, and the method for the embodiment of the present invention can basis
The upper net operation of user determines user's portrait of the matching user, recommends to complete subsequent accurate information.
Step 106, it is drawn a portrait according to the target user and recommends target information to the second terminal.
Wherein, due to having the label of multiple dimensions on user's portrait, and the label all corresponds to user portrait
User's, therefore, it can directly recommend the target information for meeting the label in user portrait, target letter to the second terminal
Breath includes but is not limited to video, audio, picture, commodity purchasing link etc..
In this way, the present invention is implemented after its personal device and multi-user shared equipment are carried out multi-screen interactive connection by user
The method of example can generate three-dimensional user to the user and draw a portrait, then after the two disconnects multi-screen interactive connection, when the use
When family operates the multi-user shared equipment again, the present invention can be multi-user shared to determine according to its current internet log data
The user for corresponding to the user in equipment corresponding at least one user portrait draws a portrait, thus according to the user draw a portrait come to its into
The accurate information recommendation of row, improves the accuracy of information recommendation, information recommendation effect is good.
Corresponding to above- mentioned information recommended method, the embodiment of the invention also provides a kind of information recommending apparatus, which can
To be applied to cloud server completely;Can be with a part of VAS application -to-terminal service (multi-user shared equipment and personal device), one
Divide and is applied to cloud server;It can also be applied to multi-user shared equipment, i.e. second terminal completely.
In the present embodiment, a part of VAS application -to-terminal service of the information recommending apparatus, a part are applied to cloud server.Its
In, the apparatus may include multiple user data acquisition modules, matching module;
In this example, multiple user data acquisition modules can be deployed to respectively in different terminals, above-mentioned for completing
The collecting work of net daily record data, and it is uploaded to cloud server;And matching module can then be deployed to cloud server side, use
It draws a portrait in generating user using collected multiterminal internet log data, and the attribute in current internet log data is special
It levies corresponding label to carry out the work such as matching with corresponding user portrait, so that it is determined that target user draws a portrait, and according to target user
Portrait comes to multi-user shared equipment recommendation target information.
In another embodiment, when the information recommending apparatus is entirely applied to cloud server side.That is, multiple numbers of users
Cloud server side is deployed according to acquisition module and matching module, wherein multiple user data acquisition modules are respectively used to adopt
Collect the internet log data of different terminals.Other processes are similar to the above embodiments, and which is not described herein again.
In yet another embodiment, when the information recommending apparatus is entirely applied to second terminal side.That is, multiple user data
Acquisition module and matching module are deployed in second terminal side, wherein multiple user data acquisition modules may include acquisition
The second user data acquisition module of multi-user's internet log data of two terminals itself can also include acquisition first terminal
Multiple first user data acquisition modules of single user internet log data;The function of modules and the above-mentioned cloud that is applied to take
The method of business device is similar, and only executing subject is different, and which is not described herein again.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to
According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented
Necessary to example.
It is corresponding with method provided by the embodiments of the present invention, referring to Fig. 2, show a kind of information recommendation of the present invention
The structural block diagram of Installation practice, can specifically include following module:
First obtains module 21, for obtaining when detecting that first terminal is connect with second terminal by multi-screen interactive
The single user internet log data of first terminal and multi-user's internet log data of second terminal, wherein the first terminal
For personal device, the second terminal is multi-user shared equipment, and multi-user's internet log data include at least two the
The internet log data that the user of one terminal is generated when using the second terminal;
Generation module 22, for according to the single user internet log data and multi-user's internet log data, life
It draws a portrait at the first terminal and the corresponding user of the second terminal;
Second obtains module 23, for when detect the first terminal with second terminal multi-screen interactive and connect disconnect when,
Obtain the current internet log data of second terminal;
Matching module 24, for by the current internet log data at least one user corresponding with the second terminal
Portrait is matched;
Determining module 25, for determining that the target user that match degree is greater than the preset threshold draws a portrait;
Recommending module 26 recommends target information to the second terminal for drawing a portrait according to the target user.
Optionally, the generation module 22 includes:
First extracting sub-module is corresponded to for carrying out attributive character extraction to the single user internet log data
In the first attributive character of the first terminal;
Second extracting sub-module is corresponded to for carrying out attributive character extraction to multi-user's internet log data
In the second attributive character of the second terminal;
First matched sub-block, for by first attributive character and second attributive character respectively with default multidimensional
Attributive character in tag library is matched, and determines corresponding with first attributive character the first label, and with described the
Corresponding second label of two attributive character, wherein the default multidimensional tag library includes pair for having trained label and attributive character
It should be related to;
Submodule is constructed, for constructing according to first object label identical in first label and second label
User corresponding with the first terminal and the second terminal draws a portrait, wherein user's portrait includes described first
Target labels.
Optionally, the matching module 24 includes:
Third extracting sub-module, for carrying out attributive character extraction to the current internet log data, obtain with it is described
The corresponding objective attribute target attribute feature of second terminal;
Second matched sub-block, for by the attributive character in the objective attribute target attribute feature and the default multidimensional tag library
It is matched, determines the second target labels corresponding with the objective attribute target attribute feature;
Third matched sub-block, for second target labels each user corresponding with the second terminal to draw a portrait
First object label matched respectively, wherein the second terminal correspond at least one user portrait;
The determining module 25 includes:
Determine submodule, it is determining with described at least one user corresponding with second terminal portrait
The corresponding target user's portrait of the two target labels first object label that match degree is greater than the preset threshold.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
The embodiment of the invention also provides a kind of servers, comprising: memory, processor and is stored on the memory
And the computer program that can be run on the processor, the computer program realize above-mentioned when being executed by the processor
The step of information recommendation method described in one embodiment of anticipating.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium
Computer program is contained, the computer program realizes that information described in any one above-mentioned embodiment pushes away when being executed by processor
The step of recommending method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (device) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to a kind of information recommendation method provided by the present invention, a kind of information recommending apparatus, a kind of server and
A kind of computer readable storage medium, is described in detail, and specific case used herein is to the principle of the present invention and reality
The mode of applying is expounded, and the above description of the embodiment is only used to help understand the method for the present invention and its core ideas;Together
When, for those of ordinary skill in the art, according to the thought of the present invention, have in specific embodiments and applications
Change place, in conclusion the contents of this specification are not to be construed as limiting the invention.
Claims (8)
1. a kind of information recommendation method characterized by comprising
When detecting that first terminal is connect with second terminal by multi-screen interactive, the single user online of the first terminal is obtained
Multi-user's internet log data of daily record data and the second terminal, wherein the first terminal is personal device, described the
Two terminals are multi-user shared equipment, and multi-user's internet log data include that the user of at least two first terminals is using
The internet log data generated when the second terminal;
According to the single user internet log data and multi-user's internet log data, generate with the first terminal and
The corresponding user's portrait of the second terminal;
When detecting the first terminal with the second terminal multi-screen interactive and connecting disconnection, working as the second terminal is obtained
Preceding internet log data;
The current internet log data at least one user portrait corresponding with the second terminal is matched;
Determine target user's portrait that match degree is greater than the preset threshold;
It is drawn a portrait according to the target user and recommends target information to the second terminal.
2. the method according to claim 1, wherein described according to the single user internet log data and described
Multi-user's internet log data are generated and are drawn a portrait with the first terminal and the corresponding user of the second terminal, comprising:
Attributive character extraction is carried out to the single user internet log data, obtains the first attribute corresponding to the first terminal
Feature;
Attributive character extraction is carried out to multi-user's internet log data, obtains the second attribute corresponding to the second terminal
Feature;
First attributive character and second attributive character are carried out with the attributive character in default multidimensional tag library respectively
Matching determines the first label corresponding with first attributive character, and the second mark corresponding with second attributive character
Label, wherein the default multidimensional tag library includes the corresponding relationship for having trained label and attributive character;
According to first object label identical in first label and second label building with the first terminal and
The corresponding user's portrait of the second terminal, wherein user's portrait includes the first object label.
3. according to the method described in claim 2, it is characterized in that, described by the current internet log data and described second
Corresponding at least one user portrait of terminal matches, comprising:
Attributive character extraction is carried out to the current internet log data, it is special to obtain objective attribute target attribute corresponding with the second terminal
Sign;
The objective attribute target attribute feature is matched with the attributive character in the default multidimensional tag library, the determining and target
Corresponding second target labels of attributive character;
The first object label of second target labels each user's portrait corresponding with the second terminal is carried out respectively
Matching, wherein the second terminal corresponds at least one user portrait;
The determination target user that match degree is greater than the preset threshold portrait, comprising:
In at least one user corresponding with second terminal portrait, determination is big with the matching degree of second target labels
In the corresponding target user's portrait of the first object label of preset threshold.
4. a kind of information recommending apparatus characterized by comprising
First obtains module, for when detecting that first terminal is connect with second terminal by multi-screen interactive, acquisition described the
The single user internet log data of one terminal and multi-user's internet log data of the second terminal, wherein described first eventually
End is personal device, and the second terminal is multi-user shared equipment, and multi-user's internet log data include at least two
The internet log data that the user of first terminal is generated when using the second terminal;
Generation module is used for according to the single user internet log data and multi-user's internet log data, generation and institute
State the corresponding user's portrait of first terminal and the second terminal;
Second obtains module, for when detect the first terminal with second terminal multi-screen interactive and connect disconnect when, acquisition the
The current internet log data of two terminals;
Matching module, for by the current internet log data at least one user corresponding with the second terminal draw a portrait into
Row matching;
Determining module, for determining that the target user that match degree is greater than the preset threshold draws a portrait;
Recommending module recommends target information to the second terminal for drawing a portrait according to the target user.
5. device according to claim 4, which is characterized in that the generation module includes:
First extracting sub-module obtains corresponding to institute for carrying out attributive character extraction to the single user internet log data
State the first attributive character of first terminal;
Second extracting sub-module obtains corresponding to institute for carrying out attributive character extraction to multi-user's internet log data
State the second attributive character of second terminal;
First matched sub-block, for by first attributive character and second attributive character respectively with default multidimensional label
Attributive character in library is matched, and determines the first label corresponding with first attributive character, and belong to described second
Property corresponding second label of feature, wherein the default multidimensional tag library include trained label it is corresponding with attributive character close
System;
Submodule is constructed, for according to first object label identical in first label and second label building and institute
State the corresponding user's portrait of first terminal and the second terminal, wherein user's portrait includes the first object
Label.
6. device according to claim 5, which is characterized in that the matching module includes:
Third extracting sub-module obtains and described second for carrying out attributive character extraction to the current internet log data
The corresponding objective attribute target attribute feature of terminal;
Second matched sub-block, for carrying out the attributive character in the objective attribute target attribute feature and the default multidimensional tag library
Matching determines the second target labels corresponding with the objective attribute target attribute feature;
Third matched sub-block, for by the of second target labels each user portrait corresponding with the second terminal
One target labels are matched respectively, wherein the second terminal corresponds at least one user portrait;
The determining module includes:
It determines submodule, is used at least one user corresponding with second terminal portrait, determining and second mesh
Mark the corresponding target user's portrait of the label first object label that match degree is greater than the preset threshold.
7. a kind of server characterized by comprising memory, processor and be stored on the memory and can be described
The computer program run on processor is realized when the computer program is executed by the processor as in claims 1 to 3
The step of described in any item information recommendation methods.
8. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program, the computer program realize information recommendation method as claimed any one in claims 1 to 3 when being executed by processor
In step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810601202.XA CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810601202.XA CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109033149A true CN109033149A (en) | 2018-12-18 |
CN109033149B CN109033149B (en) | 2020-11-13 |
Family
ID=64612798
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810601202.XA Active CN109033149B (en) | 2018-06-12 | 2018-06-12 | Information recommendation method and device, server and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109033149B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532472A (en) * | 2019-08-28 | 2019-12-03 | 百度在线网络技术(北京)有限公司 | Content synchronization recommended method, device, electronic equipment and storage medium |
CN110941738A (en) * | 2019-11-27 | 2020-03-31 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
CN111479143A (en) * | 2020-03-12 | 2020-07-31 | 深圳市酷开网络科技有限公司 | Television advertisement pushing method based on user portrait and electronic equipment |
CN112055075A (en) * | 2020-09-02 | 2020-12-08 | 韦张恒 | Internet product monitoring method, device, server and readable storage medium |
WO2020252742A1 (en) * | 2019-06-20 | 2020-12-24 | 深圳市云中飞网络科技有限公司 | Resource pushing method and related product |
CN112188287A (en) * | 2020-10-14 | 2021-01-05 | 广州欢网科技有限责任公司 | Method, system and equipment for identifying film viewing subject |
CN112650883A (en) * | 2020-12-10 | 2021-04-13 | 聚源众视(天津)信息技术有限公司 | Video recommendation method for multi-dimension analysis of multiple users |
CN112749292A (en) * | 2019-10-31 | 2021-05-04 | 深圳云天励飞技术有限公司 | User label generation method and device, computer device and storage medium |
CN113383360A (en) * | 2019-06-26 | 2021-09-10 | 深圳市欢太科技有限公司 | Content pushing method and device, server and storage medium |
CN113596898A (en) * | 2020-04-30 | 2021-11-02 | 华为技术有限公司 | Method, device, equipment, storage medium and system for determining terminal portrait |
CN113936765A (en) * | 2021-12-17 | 2022-01-14 | 北京因数健康科技有限公司 | Method and device for generating periodic behavior report, storage medium and electronic equipment |
CN115695897A (en) * | 2022-09-29 | 2023-02-03 | 中国广播电视网络集团有限公司 | Multi-role-based multi-screen interactive content recommendation method, storage medium and equipment |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002024694A (en) * | 2000-07-11 | 2002-01-25 | Nippon Telegr & Teleph Corp <Ntt> | Recommendatory information introducing method, recommendatory information introducing system, and recording medium with recommendatory information introducing program recorded thereon |
CN103324636A (en) * | 2012-03-22 | 2013-09-25 | 三星电子(中国)研发中心 | System and method for recommending friend in social network |
CN103354518A (en) * | 2013-07-24 | 2013-10-16 | 江苏晓山信息产业股份有限公司 | Web log mining-based intelligent household gateway and web log mining-based intelligent household system |
CN104717366A (en) * | 2015-03-31 | 2015-06-17 | 小米科技有限责任公司 | Method and device for recommending contact photos |
CN105447147A (en) * | 2015-11-26 | 2016-03-30 | 晶赞广告(上海)有限公司 | Data processing method and apparatus |
CN105630918A (en) * | 2015-12-22 | 2016-06-01 | 青岛海贝易通信息技术有限公司 | Whole-network user tag fusion and user identification unifying method |
CN105677844A (en) * | 2016-01-06 | 2016-06-15 | 北京摩比万思科技有限公司 | Mobile advertisement big data directional pushing and user cross-screen recognition method |
KR20160120238A (en) * | 2015-04-07 | 2016-10-17 | 주식회사 컴퍼니원헌드레드 | Clothes recommendation system |
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
-
2018
- 2018-06-12 CN CN201810601202.XA patent/CN109033149B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002024694A (en) * | 2000-07-11 | 2002-01-25 | Nippon Telegr & Teleph Corp <Ntt> | Recommendatory information introducing method, recommendatory information introducing system, and recording medium with recommendatory information introducing program recorded thereon |
CN103324636A (en) * | 2012-03-22 | 2013-09-25 | 三星电子(中国)研发中心 | System and method for recommending friend in social network |
CN103354518A (en) * | 2013-07-24 | 2013-10-16 | 江苏晓山信息产业股份有限公司 | Web log mining-based intelligent household gateway and web log mining-based intelligent household system |
CN104717366A (en) * | 2015-03-31 | 2015-06-17 | 小米科技有限责任公司 | Method and device for recommending contact photos |
KR20160120238A (en) * | 2015-04-07 | 2016-10-17 | 주식회사 컴퍼니원헌드레드 | Clothes recommendation system |
CN106504099A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of system for building user's portrait |
CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
CN105447147A (en) * | 2015-11-26 | 2016-03-30 | 晶赞广告(上海)有限公司 | Data processing method and apparatus |
CN105630918A (en) * | 2015-12-22 | 2016-06-01 | 青岛海贝易通信息技术有限公司 | Whole-network user tag fusion and user identification unifying method |
CN105677844A (en) * | 2016-01-06 | 2016-06-15 | 北京摩比万思科技有限公司 | Mobile advertisement big data directional pushing and user cross-screen recognition method |
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN107451217A (en) * | 2017-07-17 | 2017-12-08 | 广州特道信息科技有限公司 | Information recommends method and device |
Non-Patent Citations (1)
Title |
---|
王冬羽: "基于移动互联网行为分析的用户画像***设计", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020252742A1 (en) * | 2019-06-20 | 2020-12-24 | 深圳市云中飞网络科技有限公司 | Resource pushing method and related product |
CN113383360A (en) * | 2019-06-26 | 2021-09-10 | 深圳市欢太科技有限公司 | Content pushing method and device, server and storage medium |
CN113383360B (en) * | 2019-06-26 | 2023-11-24 | 深圳市欢太科技有限公司 | Content pushing method, device, server side and storage medium |
CN110532472B (en) * | 2019-08-28 | 2022-09-27 | 百度在线网络技术(北京)有限公司 | Content synchronous recommendation method and device, electronic equipment and storage medium |
CN110532472A (en) * | 2019-08-28 | 2019-12-03 | 百度在线网络技术(北京)有限公司 | Content synchronization recommended method, device, electronic equipment and storage medium |
CN112749292B (en) * | 2019-10-31 | 2024-05-03 | 深圳云天励飞技术有限公司 | User tag generation method and device, computer device and storage medium |
CN112749292A (en) * | 2019-10-31 | 2021-05-04 | 深圳云天励飞技术有限公司 | User label generation method and device, computer device and storage medium |
CN110941738B (en) * | 2019-11-27 | 2023-03-28 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
CN110941738A (en) * | 2019-11-27 | 2020-03-31 | 北京奇艺世纪科技有限公司 | Recommendation method and device, electronic equipment and computer-readable storage medium |
CN111479143A (en) * | 2020-03-12 | 2020-07-31 | 深圳市酷开网络科技有限公司 | Television advertisement pushing method based on user portrait and electronic equipment |
CN113596898A (en) * | 2020-04-30 | 2021-11-02 | 华为技术有限公司 | Method, device, equipment, storage medium and system for determining terminal portrait |
CN112055075A (en) * | 2020-09-02 | 2020-12-08 | 韦张恒 | Internet product monitoring method, device, server and readable storage medium |
CN112188287A (en) * | 2020-10-14 | 2021-01-05 | 广州欢网科技有限责任公司 | Method, system and equipment for identifying film viewing subject |
CN112650883B (en) * | 2020-12-10 | 2022-11-22 | 聚源众视(天津)信息技术有限公司 | Video recommendation method for multi-dimension analysis of multiple users |
CN112650883A (en) * | 2020-12-10 | 2021-04-13 | 聚源众视(天津)信息技术有限公司 | Video recommendation method for multi-dimension analysis of multiple users |
CN113936765A (en) * | 2021-12-17 | 2022-01-14 | 北京因数健康科技有限公司 | Method and device for generating periodic behavior report, storage medium and electronic equipment |
CN115695897A (en) * | 2022-09-29 | 2023-02-03 | 中国广播电视网络集团有限公司 | Multi-role-based multi-screen interactive content recommendation method, storage medium and equipment |
CN115695897B (en) * | 2022-09-29 | 2024-04-30 | 中国广播电视网络集团有限公司 | Multi-role-based multi-screen interactive content recommendation method, storage medium and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109033149B (en) | 2020-11-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109033149A (en) | Information recommendation method, device, server and storage medium | |
US11037222B1 (en) | Dynamic recommendations personalized by historical data | |
CN107404656B (en) | Live video recommended method, device and server | |
CN104462292B (en) | Socially collaborative filtering | |
CN108960975A (en) | Personalized Precision Marketing Method, server and storage medium based on user's portrait | |
JP2021103543A (en) | Use of machine learning for recommending live-stream content | |
US10440435B1 (en) | Performing searches while viewing video content | |
CN105488154A (en) | Theme application recommendation method and device | |
CN103678647A (en) | Method and system for recommending information | |
KR20140108495A (en) | Apparatus and method for processing a multimedia commerce service | |
CN111708948B (en) | Content item recommendation method, device, server and computer readable storage medium | |
CN105657558B (en) | A kind of information providing method, methods of exhibiting, device and smart television | |
KR101728099B1 (en) | Product Information Providing Apparatus for Electrical Transaction using Scenario-based Combined Story Contents | |
WO2017080173A1 (en) | Nature information recognition-based push system and method and client | |
CN102421062A (en) | Method and system for pushing application information | |
CN108595493A (en) | Method for pushing and device, storage medium, the electronic device of media content | |
WO2022247220A1 (en) | Interface processing method and apparatus | |
US20130117784A1 (en) | System and method for displaying information of television advertised product and recording media thereof | |
CN108700928A (en) | Content is managed based on battery utilization rate when showing content on device | |
CN111722766A (en) | Multimedia resource display method and device | |
CN112396456A (en) | Advertisement pushing method and device, storage medium and terminal | |
CN110020162A (en) | User identification method and device | |
Barragáns-Martínez et al. | Developing a recommender system in a consumer electronic device | |
US8725795B1 (en) | Content segment optimization techniques | |
US20200034917A1 (en) | Communication via simulated user |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |