CN108073670A - Business object recommends method, apparatus and electronic equipment - Google Patents
Business object recommends method, apparatus and electronic equipment Download PDFInfo
- Publication number
- CN108073670A CN108073670A CN201710236121.XA CN201710236121A CN108073670A CN 108073670 A CN108073670 A CN 108073670A CN 201710236121 A CN201710236121 A CN 201710236121A CN 108073670 A CN108073670 A CN 108073670A
- Authority
- CN
- China
- Prior art keywords
- business object
- attribute data
- attribute
- main broadcaster
- multiple business
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of business object and recommends method, apparatus and electronic equipment.The business object recommends method to include：Obtain main broadcaster's attribute data, Audience attribute data and the multiple business object attribute datas of direct broadcasting room；Based on main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas, the selection target business object in multiple business objects；Target service object is shown in direct broadcasting room.Using the embodiment of the present invention, the target service object with higher dispensing effect can be selected to be shown in direct broadcasting room, so that the business object in direct broadcasting room displaying has higher bandwagon effect, and improve the utilization rate of Internet resources.
Description
Technical field
The present invention relates to the information processing technologies more particularly to a kind of business object to recommend method, apparatus and electronic equipment.
Background technology
With the continuous development of image procossing and the information processing technology, net cast is due to having merged image, word harmony
The elements such as sound, excellent both in sound and shape have been increasingly becoming the mainstream expression way of internet.Internet video is considered various as a result,
The high-quality resource that business object is recommended.
At present, business object recommends method (such as advertisement recommendation) mostly by analyzing some features such as year of dispensing crowd
The information such as age, area are oriented dispensing, although there is some specific aims in terms of recommendation.But master can not be covered well
It broadcasts and carries out individual business object recommendation with the Comprehensive Characteristics of spectators, while cause the waste of Internet resources.
The content of the invention
The present invention provides the scheme that a kind of business object is recommended.
It is according to embodiments of the present invention in a first aspect, providing a kind of business object recommends method.The described method includes：It obtains
Main broadcaster's attribute data, Audience attribute data and the multiple business object attribute datas of direct broadcasting room；Based on main broadcaster's attribute number
According to, Audience attribute data and the multiple business object attribute data, the selection target business in multiple business objects
Object；The target service object is shown in the direct broadcasting room.
Optionally, it is described to be based on main broadcaster's attribute data, the attribute data and the multiple business object attribute
Data, the selection target business object in multiple business objects, including：Based on main broadcaster's attribute data, the Audience attribute
Effect value is launched in data and the multiple business object attribute data, the prediction for calculating the multiple business object respectively；Root
Effect value is launched according to the prediction of the multiple business object, the target service object is selected from the multiple business object.
Optionally, it is described to be based on main broadcaster's attribute data, the Audience attribute data and the multiple business object
Effect value is launched in attribute data, the prediction for calculating the multiple business object respectively, including：Based on main broadcaster's attribute data and
The Audience attribute data determine to characterize the user attribute data of the synthesized attribute of the main broadcaster and the spectators；According to described
Effect is launched in user attribute data and the multiple business object attribute data, the prediction for calculating the multiple business object respectively
Value.
Optionally, it is described according to the user attribute data and the multiple business object attribute data, institute is calculated respectively
Effect value is launched in the prediction for stating multiple business objects, including：The combination for establishing user property and business object attribute is thrown with prediction
Put the functional relation between the probability of Effect value；According to the user attribute data and the multiple business object attribute data,
Using logistic regression algorithm and the functional relation established, Effect value is launched in the prediction for calculating each business object respectively.
Optionally, it is described that Effect value is launched according to the prediction of the multiple business object, from the multiple business object
The target service object is selected, including：It will predict the business object launched Effect value and be greater than or equal to dispensing effect threshold value, really
It is set to the target service object.
Optionally, the user attribute data includes user property feature vector, and the business object attribute data includes
Business object attribute feature vector.
Optionally, the synthesized attribute includes at least one of：Essential attribute, figure and features feature, purchase pattern, behavior are special
Sign, psychological characteristics, Audience attribute, real-time status feature and commercial attribute, wherein, the Audience attribute include it is following at least it
One：Sex ratio, ratio of age, region ratio, the behaviour in service of Income situation and application program.
Optionally, Effect value is launched in the prediction includes clicking rate data and/or effectively viewing person-time, wherein, it is described to have
When effect viewing person-time is for being characterized in business object displaying, the duration of viewing business object is more than setting viewing duration in direct broadcasting room
Person-time.
Optionally, the business object includes：Include the special efficacy of advertising message.
Second aspect according to embodiments of the present invention provides a kind of business object recommendation apparatus.Described device includes：It obtains
Module, for obtaining main broadcaster's attribute data of direct broadcasting room, Audience attribute data and multiple business object attribute datas；Determine mould
Block, for being based on main broadcaster's attribute data, the Audience attribute data and the multiple business object attribute data, more
Selection target business object in a business object；Display module, for showing the target service object in the direct broadcasting room.
Optionally, the determining module includes：Computing unit, for being based on main broadcaster's attribute data, the spectators belong to
Property data and the multiple business object attribute data, the prediction for calculating the multiple business object respectively launches Effect value；
Determination unit for launching Effect value according to the prediction of the multiple business object, selects institute from the multiple business object
State target service object.
Optionally, the computing unit includes：First subelement, for being based on main broadcaster's attribute data and the spectators
Attribute data determines to characterize the user attribute data of the synthesized attribute of the main broadcaster and the spectators；Second subelement, for root
According to the user attribute data and the multiple business object attribute data, the prediction for calculating the multiple business object respectively is thrown
Put Effect value.
Optionally, second subelement is used for：The combination for establishing user property and business object attribute is launched with prediction
Functional relation between the probability of Effect value；According to the user attribute data and the multiple business object attribute data, profit
With logistic regression algorithm and the functional relation established, Effect value is launched in the prediction for calculating each business object respectively.
Optionally, the determination unit is used for：It will predict the business launched Effect value and be greater than or equal to dispensing effect threshold value
Object is determined as the target service object.
Optionally, the user attribute data includes user property feature vector, and the business object attribute data includes
Business object attribute feature vector.
Optionally, the synthesized attribute includes at least one of：Essential attribute, figure and features feature, purchase pattern, behavior are special
Sign, psychological characteristics, audient's feature, real-time status feature and commercial attribute, wherein, the audience feature include it is following at least it
One：Sex ratio, ratio of age, region ratio, the behaviour in service of Income situation and application program.
Optionally, Effect value is launched in the prediction includes clicking rate data and/or effectively viewing person-time, wherein, it is described to have
When effect viewing person-time is for being characterized in business object displaying, the duration of viewing business object is more than setting viewing duration in direct broadcasting room
Person-time.
Optionally, the business object includes：Include the special efficacy of advertising message.
The third aspect according to embodiments of the present invention, additionally provides a kind of electronic equipment, including：Processor, memory lead to
Cell part and communication bus, the processor, the memory and the communication device are completed mutual by the communication bus
Between communication；For the memory for storing an at least executable instruction, the executable instruction makes the processor perform such as
Any business object recommends the corresponding operation of method in first aspect.
Fourth aspect according to embodiments of the present invention additionally provides a kind of computer readable storage medium, the computer
Readable storage medium storing program for executing is stored with：For obtaining main broadcaster's attribute data of direct broadcasting room, Audience attribute data and multiple business objects
Attribute data；Based on main broadcaster's attribute data, the Audience attribute data and the multiple business object attribute data,
Selection target business object in multiple business objects；The executable instruction of the target service object is shown in the direct broadcasting room.
The business object provided according to embodiments of the present invention recommends method, apparatus and electronic equipment, by obtaining direct broadcasting room
Main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas, and according to video main broadcaster attribute data, see
Many attribute datas and multiple business object attribute datas, to select the target service object with higher dispensing effect, so as to
So that the target service object in direct broadcasting room displaying has higher bandwagon effect, and improve the utilization rate of Internet resources.
Description of the drawings
Fig. 1 shows it is that a kind of according to embodiments of the present invention one business object recommends the flow chart of method；
Fig. 2 shows it is that a kind of according to embodiments of the present invention three business object recommends the flow chart of method；
Fig. 3 show be a kind of according to embodiments of the present invention four business object recommendation apparatus logic diagram；
Fig. 4 show be a kind of according to embodiments of the present invention five business object recommendation apparatus logic diagram；
Fig. 5 is the structure diagram for a kind of electronic equipment for showing according to embodiments of the present invention six.
Specific embodiment
Detailed description of the present invention exemplary embodiment below in conjunction with the accompanying drawings.
Embodiment one
Fig. 1 is to show that a kind of according to embodiments of the present invention one business object recommends the flow chart of method.By including industry
The equipment of business object recommendation device performs the method as the background server of platform is broadcast live.
With reference to Fig. 1, in step S110, main broadcaster's attribute data, Audience attribute data and the multiple business of direct broadcasting room are obtained
Object attribute data.
Wherein, main broadcaster can be the main broadcaster of currently playing live streaming class video, which is regarded in real time in direct broadcasting room
Frequency is broadcast live.Correspondingly, spectators corresponding with main broadcaster can be the fan group of viewing main broadcaster.
Main broadcaster's attribute data is used to indicate the feature of main broadcaster, and main broadcaster's attribute data can the gender including main broadcaster, age, row
It is characterized.Audience attribute data are used to indicate the feature of spectators, Audience attribute data can include the gender of spectators, occupation,
Behavioural characteristic etc..Business object attribute data is used to indicate the feature of business object, and business object attribute data can include industry
The affiliated industry of business object orients group etc..
In step S120, based on main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas, more
Selection target business object in a business object.
According to main broadcaster's attribute data and Audience attribute data, it may be determined that the feature of main broadcaster and/or spectators, and then can be according to
According to multiple business object attribute datas, the business object for selecting to meet this feature from multiple business objects is as target service pair
As so that target service object is for main broadcaster/or crucial with higher dispensing effect.
In step S130, target service object is shown in direct broadcasting room.
The target service object determined in step S120 is shown in direct broadcasting room, for example, at the main broadcaster end of direct broadcasting room
And/or viewer end is shown.
The business object that there is provided according to embodiments of the present invention recommends method, by obtain direct broadcasting room main broadcaster's attribute data,
Audience attribute data and multiple business object attribute datas, and according to video main broadcaster attribute data, Audience attribute data and
Multiple business object attribute datas, to select the target service object with higher dispensing effect, so that in direct broadcasting room exhibition
The target service object shown has higher bandwagon effect, and improves the utilization rate of Internet resources.
Embodiment two
The business object recommendation method of the present embodiment can be considered a kind of optional embodiment of above-described embodiment one.
Referring again to Fig. 1, in step S110, main broadcaster's attribute data of direct broadcasting room, Audience attribute data and multiple are obtained
Business object attribute data.
In live video, main broadcaster has many features in itself.For example, main broadcaster's gender, age, face value, behavioural characteristic
Deng.These features can be considered as main broadcaster's attribute.Main broadcaster's attribute data may include following at least one as a result,：Essential attribute, figure and features
Feature, purchase pattern, behavioural characteristic, psychological characteristics, real-time status feature and commercial attribute, but not limited to this.Wherein, it is basic to belong to
Property can include gender, age, permanent area, occupation, education degree etc., figure and features feature can including height, weight, face value,
Whether dress etc., purchase pattern can include Income situation, whether have vehicle, buy house, type of do shopping, Brang Preference etc., behavior spy
Sign can include hobby, artistic speciality (singing/dancing), active degree etc., and it is (single that psychological characteristics can include affective state
Body/love/married), personality feature (optimistic/gentle and quiet/intellectual) etc., real-time status feature can include real-time location, table
Feelings, Real Time Effect power etc., commercial attribute can include the clicking rate for enabling rate, enabling advertisement of advertisement, be primarily upon commercial paper
Not (fast food, cosmetics, movement brand etc.) etc..
Similarly, certain feature can also be showed by watching the spectators group of main broadcaster.For example, masculinity proportion in spectators group
It is how manyFemale ratio is how manyA line city spectators how many etc..The feature that spectators group is presented can be considered as spectators
Attribute.Audience attribute data may include following at least one as a result,：Sex ratio, ratio of age, region ratio, Income situation,
Occupation and the behaviour in service of application program, but not limited to this.
Table 1 shows a kind of example of main broadcaster's attribute data and Audience attribute data.
Table 1
It can be by the category of main broadcaster by such as information such as gender, age, area, occupation, education degree of the attribute shown in table 1
The attribute of property and its audient determine substantially.For the ease of the dispensing effect of subsequent prediction business object, further, to main broadcaster's
Attribute and its attribute of spectators carry out the data that numeralization is handled, that is, the main broadcaster's attribute data and Audience attribute number obtained
According to.For example attribute information has male, women, primary school, middle school, training, undergraduate course, master, doctor ..., it is assumed that certain digital video main broadcaster
It is women, undergraduate course, then the corresponding one-dimensional vector of this main broadcaster is exactly (0,1,0,0,0,1,0,0 ...), that is to say, that if
Main broadcaster possesses certain attribute, which is just represented with " 1 ", conversely, the attribute is just represented with " 0 ".
After foregoing be described in detail, business object can be to include the special efficacy of advertising message.Special efficacy include 2D special efficacys,
3D special efficacys etc..It is to be appreciated that special efficacy is the understanding of broad sense, paster is usually the special efficacy of 2D forms.The patch in platform is broadcast live
Exemplified by the advertisement special efficacy of paper form, for advertisement in itself, it also has the attribute of itself.Table 2 shows the one of business object attribute
Kind example.
Table 2
It can by information such as example affiliated industry of the attribute shown in table 2, business object brand, bandwagon effect, triggering modes
Business object attribute data to be determined substantially.For the ease of the dispensing effect of subsequent prediction business object, further, to industry
Business object properties carry out the data that numeralization is handled, and are multiple business object attribute datas of acquisition.Specifically, compare
Each attribute in table 2, if business object possesses certain attribute, which is just represented with " 1 ", conversely, the attribute just uses " 0 "
To represent.For example, the affiliated industry of a certain advertisement is traffic class, advertising results are made laughs type for humour, and the gender for orienting spectators is
Female, then the attribute data of the advertisement can be (1,0,0,0,1,0,0,0,0,1,0,1,0,0,0).
In step S120, based on main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas, more
Selection target business object in a business object.
Exemplary embodiment according to the present invention, step S120 may include：Main broadcaster's attribute data and spectators based on acquisition
Attribute data determines the user attribute data of the synthesized attribute of characterization main broadcaster and spectators；According to user attribute data and multiple industry
Effect value is launched in business object attribute data, the prediction for calculating multiple business objects respectively；And according to multiple business objects of calculating
Prediction launch Effect value, the selection target business object from multiple business objects.
In the present embodiment, synthesized attribute may include but be not limited at least one of：Essential attribute, figure and features feature, purchase
Type, behavioural characteristic, psychological characteristics, Audience attribute, real-time status feature and commercial attribute.Wherein, Audience attribute may include but
It is not limited at least one of：Sex ratio, ratio of age, region ratio, the behaviour in service of Income situation and application program.In advance
Survey launch Effect value can be clicking rate data and/or effectively viewing person-time, wherein, effectively viewing person-time for represent in business
When object is shown, the duration of viewing business object is more than person-time of setting viewing duration in direct broadcasting room.
By taking live video as an example, either main broadcaster or spectators belong to the user of live video, simply role
It is different.There are many spectators of feature, each spectators in each corresponding spectators group of main broadcaster can pay close attention to the main broadcaster of various features.
For example, the spectators of various features are existing one of the characteristics of than regular meeting being main broadcaster.Therefore, in order to more accurately recommend business pair
As that cannot be merely to consider main broadcaster or instruction considers spectators, it is necessary in terms of two the characteristics of from the main broadcaster the characteristics of, spectators
It is combined to realize the recommendation of business object.That is, utilize the synthesized attribute that can cover main broadcaster and spectators well
User attribute data, to predict the dispensing Effect value of business object, so as to select launch the preferable business object of effect straight
It broadcasts in video and shows, improve the bandwagon effect of business object.
Specifically, Effect value can be launched according to the prediction of calculating, prediction dispensing Effect value is greater than or equal to and is set in advance
The business object of fixed dispensing effect threshold value, is determined as target service object, and then selects from multiple business objects to be recommended
Target service object.Certainly, in other embodiments, Effect value can also be launched according to the prediction of calculating to multiple business pair
As being ranked up, the business object for the preceding default quantity that sorts is determined as target service object to be recommended.
In step S130, target service object is shown in direct broadcasting room.
Here, target service object can simultaneously be shown at main broadcaster end and viewer end.For example, the backstage of net cast platform
The business object that server performs the present embodiment recommends method, by the information (such as ID of target service object) of target service object
Main broadcaster end and viewer end are sent to, target service object is shown by main broadcaster end and viewer end simultaneously.
In addition, in other embodiments, the business object that the present embodiment can also be performed by main broadcaster end or viewer end pushes away
Recommend method.For example, in concrete implementation mode, from the point of view of video main broadcaster, the letter of target service object to be recommended
Breath can be sent to video main broadcaster, and business object is selected from the target service object of recommendation to show by video main broadcaster, alternatively,
The priority of target service object to be recommended can be improved or sorted forward in business object recommendation list so that video
The probability bigger for the target service object that main broadcaster chooses these to be recommended.In addition, from the point of view of spectators, target to be recommended
The information of business object can also directly issue spectators, alternatively, the business object material database being synchronized in the terminal device of spectators.
That is, the information of target service object to be recommended is sent to the terminal device of video main broadcaster, alternatively, will mesh to be recommended be included
It marks the information of business object and its business object recommendation list of precedence information pushes to the terminal device of video main broadcaster, so that
The terminal device of video main broadcaster, to the selection operation of business object, choosing is drawn using computer graphics mode in response to video main broadcaster
In business object.Alternatively, the information of target service object to be recommended is sent to the terminal device of spectators, so that the end of spectators
End equipment draws business object to be recommended using computer graphics mode, alternatively, the information of business object to be recommended is same
It walks to the business object material database being stored in the terminal device of spectators.
For example, being sent to the target service object to be recommended of a certain main broadcaster includes the advertisement spy of multiple paster forms
Effect, main broadcaster click on the advertisement special efficacy of one of paster form, and correspondingly, the terminal device of main broadcaster will be drawn out selected
Advertisement special efficacy, so as to show the advertisement special efficacy to watch the spectators of the main broadcaster.
The business object provided through this embodiment recommends method, by the main broadcaster's attribute data, the spectators that obtain direct broadcasting room
Attribute data and multiple business object attribute datas, and according to video main broadcaster attribute data, Audience attribute data and multiple
Business object attribute data carrys out selection target business object so that direct broadcasting room displaying target service object have compared with
High bandwagon effect improves the utilization rate of Internet resources.
Further, in selection target object, determine that user belongs to according to main broadcaster's attribute data and Audience attribute data
Property data, to characterize the synthesized attribute of spectators main broadcaster and spectators, and according to user attribute data and multiple business object attribute numbers
According to, Effect value is launched to calculate the prediction of multiple business objects respectively, and then predict the dispensing effect of multiple business objects, so as to
The dispensing preferable target service object of effect can be selected to be shown in direct broadcasting room, realize the synthesis of covering main broadcaster and spectators
Attribute carries out individual business object recommendation, improves business object bandwagon effect.
In addition, the embodiment of the present invention also has the following technical effect that：
It on the one hand, can be by regarding by the way that the information of business object to be recommended to be sent to the terminal device of video main broadcaster
Frequency main broadcaster neatly chooses business object therein and is shown；
On the other hand, the information of business object to be recommended is directly transmitted to the terminal device of spectators or is synchronized to sight
The business object material database of many terminal device storages so that the way of recommendation of business object is more flexible, variation.
Embodiment three
Fig. 2 shows it is that a kind of according to embodiments of the present invention three business object recommends the flow chart of method.Can in such as Fig. 3 or
This method is performed on business object recommendation apparatus shown in 4.
With reference to Fig. 2, in step S210, attribute data, the attribute of spectators corresponding with video main broadcaster of acquisition video main broadcaster
The attribute data of data and multiple business objects.
Here, user attribute data can include characterization video main broadcaster and spectators synthesized attribute user property feature to
Amount, business object attribute data can include business object attribute feature vector.
Wherein, in the step content of above-mentioned steps S210 and above-described embodiment one (or embodiment two) the step of step S110
Content is identical, and details are not described herein.
In step S220, the attribute data of attribute data and spectators based on video main broadcaster, determine characterization video main broadcaster and
The user attribute data of the synthesized attribute of spectators.
For example, user attribute data is { u1,u2...un, one-dimensional vector { u1,u2...unIn part vector value come
From the numeralization of the attribute in the main broadcaster as shown in table 1 in embodiment one, while another part vector comes from such as embodiment one
The numeralization of the attribute of spectators' (fan group) shown in middle table 1.Assuming that the fan group of the main broadcaster has 1,000,000 beans vermicelli, then base
The vector obtained after the attribute number value of fan group can be obtained in this 1,000,000 respective attributes of bean vermicelli.It can be seen that user belongs to
Property data cover the Comprehensive Characteristics of main broadcaster and spectators well.
In step S230, establish between the combination of user property and business object attribute and the probability of prediction dispensing Effect value
Functional relation.
In step S240, according to user attribute data and multiple business object attribute datas, using logistic regression algorithm and
Effect value is launched in the functional relation of foundation, the prediction for calculating each business object respectively.
In step S250, it will predict and launch Effect value more than or equal to the business object for launching effect threshold value, be determined as
Business object to be recommended.
Previous embodiment is it is stated that default Effect value of launching can include clicking rate data and/or effectively viewing person-time.Under
Face is described in detail step S230~S250 with the clicking rate data instance of advertisement special efficacy.
User (including main broadcaster and/or spectators) depends on ad features and user's feature for the interest of an advertisement, and
User most can intuitively be expressed for the interest and degree of recognition of advertisement with clicking rate.Click event (h) is regarded as one
The stochastic variable of a binary value, then its value is that the probability of true (click=1) is exactly clicking rate.Therefore, event is clicked on
The binomial (Binomial) using clicking rate μ as parameter that distribution can be write as shown in following formula (1) is distributed：
P (h)=μh(1-μ)1-h... ... ... ... ... ... ... ... ... ... formula (1)
Wherein, p (h) is the distribution of click event (h), and μ is clicking rate, and h is value in the binary variable of { 0,1 }.
The purpose for predicting clicking rate is built between the combination of user property and business object attribute and the probability of clicking rate
Vertical functional relation, therefore can conceptually be expressed as the probability Estimation problem shown in following formula (2)：
μ (a, u)=p (h=1 | a, u) ... ... ... ... ... ... ... ... ... ... formula (2)
Wherein, μ is clicking rate, and h is value in the binary variable of { 0,1 }, a be the attribute of characterization advertisement special efficacy feature to
Amount, a={ a1,a2...an, u be characterization video main broadcaster and spectators synthesized attribute user property feature vector, u={ u1,
u2...un}。
Since h is value in the binary variable of { 0,1 }, the logistic regression (Logistic represented using following formula (3)
Regression, LR) model prediction clicking rate：
P (h=1 | a, u)=σ (wTX (a, u)) ... ... ... ... ... ... ... ... ... formula (3)
Wherein, x be (a, u) combination on feature vector, w be each feature weighting coefficient, that is, this model needs it is excellent
The parameter of change, wTIn T for transposition, wTThe output of this model of x by Logisticsigmoid Function Mappings to (0,1) it
Between, this mapping function form is following formula (4)：
Wherein, σ (z) is the mapping result of z, and z is the output of Logic Regression Models as a result, z=wTx(a,u)。
Assuming that the clicking rate that 4 advertisement special efficacys predict respectively is 0.5,0.6,0.8,1, the clicking rate threshold value of setting is
0.7, the clicking rate that can choose prediction as a result, is 0.8 and 1 corresponding advertisement special efficacy as advertisement special efficacy to be recommended.
In step S260, target service object is shown in direct broadcasting room.
Wherein, in the step content of above-mentioned steps S260 and above-described embodiment one (or embodiment two) the step of step S130
Content is identical, and details are not described herein.
The business object provided through this embodiment recommends method, on the basis of embodiment one, also with following technology
Effect：First, the attribute of the synthesized attribute and business object of video main broadcaster and spectators has feature vector expression, convenient for follow-up
The processing of Effect value is launched in the prediction for calculating business object；Secondly, using logistic regression algorithm, more accurate business is calculated
Effect value is launched in the prediction of object, and then selects the target service object with higher dispensing effect exactly, is further improved
In the bandwagon effect of the target service object of direct broadcasting room displaying.
Example IV
Reference Fig. 3 shows a kind of structure diagram of according to embodiments of the present invention four business object recommendation apparatus.
The business object recommendation apparatus of the present embodiment includes：Acquisition module 302, determining module 304 and display module 306.
Wherein, acquisition module 302 is used to obtain main broadcaster's attribute data, Audience attribute data and the multiple business object attributes of direct broadcasting room
Data；Determining module 304 is used for based on main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas,
Selection target business object in multiple business objects；Display module 306 is used to show target service object in direct broadcasting room.
According to business object recommendation apparatus provided in this embodiment, by the main broadcaster's attribute data, the spectators that obtain direct broadcasting room
Attribute data and multiple business object attribute datas, and according to video main broadcaster attribute data, Audience attribute data and multiple
Business object attribute data carrys out selection target business object so that direct broadcasting room displaying target service object have compared with
High bandwagon effect, and improve the utilization rate of Internet resources.
Embodiment five
Reference Fig. 4 shows a kind of structure diagram of according to embodiments of the present invention five business object recommendation apparatus.
The business object recommendation apparatus of the present embodiment includes：Acquisition module 302, determining module 304 and display module 306.
Wherein, acquisition module 302 is used to obtain main broadcaster's attribute data, Audience attribute data and the multiple business object attributes of direct broadcasting room
Data；Determining module 304 is used for based on main broadcaster's attribute data, Audience attribute data and multiple business object attribute datas,
Selection target business object in multiple business objects；Display module 306 is used to show target service object in direct broadcasting room.
Optionally it is determined that module 304 includes computing unit and determination unit 3046, computing unit is used for based on main broadcaster's attribute
Effect is launched in data, Audience attribute data and multiple business object attribute datas, the prediction for calculating multiple business objects respectively
Value；Determination unit 3046 is used to launch Effect value, the selection target from multiple business objects according to the prediction of multiple business objects
Business object.
Optionally, computing unit includes the first subelement 3042 and the second subelement 3044, and the first subelement 3042 is used for
Based on main broadcaster's attribute data and Audience attribute data, determine to characterize the user attribute data of the synthesized attribute of main broadcaster and spectators；The
Two subelements 3044 are used for according to user attribute data and multiple business object attribute datas, calculate multiple business objects respectively
Effect value is launched in prediction.
Optionally, the second subelement 3044 is used to establish user property and the combination of business object attribute launches effect with prediction
Functional relation between the probability of fruit value；According to user attribute data and multiple business object attribute datas, logistic regression is utilized
Effect value is launched in algorithm and the functional relation established, the prediction for calculating each business object respectively.
Optionally it is determined that unit 3046 is used to predict that launching Effect value to be greater than or equal to the business pair for launching effect threshold value
As being determined as target service object.
Optionally, user attribute data includes user property feature vector, and business object attribute data includes business object
Attribute feature vector.
Optionally, synthesized attribute includes at least one of：Essential attribute, figure and features feature, purchase pattern, behavioural characteristic,
Psychological characteristics, audient's feature, real-time status feature and commercial attribute, wherein, audience feature includes at least one of：Sex ratio
Example, ratio of age, region ratio, the behaviour in service of Income situation and application program.
Optionally, Effect value is launched in prediction includes clicking rate data and/or effectively viewing person-time, wherein, effectively watch people
It is secondary for being characterized in business object displaying when, the duration of viewing business object is more than person-time of setting viewing duration in direct broadcasting room.
Optionally, business object includes：Include the special efficacy of advertising message.
Business object recommendation apparatus through this embodiment can perform the business pair in above-described embodiment one to embodiment three
As recommending method, and the advantageous effect of this method is obtained, therefore not to repeat here.
Embodiment six
The embodiment of the present invention five provides a kind of electronic equipment, such as can be mobile terminal, personal computer (PC), put down
Plate computer, server etc..Below with reference to Fig. 5, it illustrates suitable for being used for realizing the terminal device of the embodiment of the present invention or service
The structure diagram of the electronic equipment 500 of device：As shown in figure 5, electronic equipment 500 includes one or more processors, communication member
Part etc., one or more of processors are for example：One or more central processing unit (CPU) 501 and/or one or more
Image processor (GPU) 513 etc., processor can according to the executable instruction being stored in read-only memory (ROM) 502 or
From the storage executable instruction that is loaded into random access storage device (RAM) 503 of part 508 perform various appropriate actions and
Processing.Communication device includes communication component 512 and/or communication interface 509.Wherein, communication component 512 may include but be not limited to net
Card, the network interface card may include but be not limited to IB (Infiniband) network interface card, and communication interface 509 includes such as LAN card, modulation /demodulation
The communication interface of the network interface card of device etc., communication interface 509 perform communication process via the network of such as internet.
Processor can communicate with read-only memory 502 and/or random access storage device 503 to perform executable instruction,
It is connected by communication bus 504 with communication component 512 and is communicated through communication component 512 with other target devices, so as to completes this
Any one business object that inventive embodiments provide recommends the corresponding operation of method, for example, obtaining main broadcaster's attribute number of direct broadcasting room
According to, Audience attribute data and multiple business object attribute datas；Based on main broadcaster's attribute data, the Audience attribute data
And the multiple business object attribute data, the selection target business object in multiple business objects；In the direct broadcasting room exhibition
Show the target service object.
In addition, in RAM 503, various programs and data needed for device operation can be also stored with.CPU501 or
GPU513, ROM502 and RAM503 are connected with each other by communication bus 504.In the case where there is RAM503, ROM502 is can
Modeling block.RAM503 stores executable instruction or executable instruction is operationally write into ROM502, and executable instruction makes place
It manages device 50 and performs the corresponding operation of the above method.Input/output (I/O) interface 505 is also connected to communication bus 504.Communication set
Part 512 can be integrally disposed, may be set to be with multiple submodule (such as multiple IB network interface cards), and is linked in communication bus
On.
I/O interfaces 505 are connected to lower component：Importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage part 508 including hard disk etc.；
And the communication interface 509 of the network interface card including LAN card, modem etc..50 drivers 510 are also according to needs
It is connected to I/O interfaces 505.Detachable media 511, such as disk, CD, magneto-optic disk, semiconductor memory etc., as needed
On driver 510, in order to which the computer program read from it is mounted into storage part 508 as needed.
Need what is illustrated, framework as shown in Figure 5 is only a kind of optional realization method, can root during concrete practice
The component count amount and type of above-mentioned Fig. 5 are made choice, deleted, increased or replaced according to actual needs；It is set in difference in functionality component
Put, can also be used it is separately positioned or integrally disposed and other implementations, such as GPU and CPU separate setting or can be by GPU collection
Into on CPU, communication device separates setting, can also be integrally disposed on CPU or GPU, etc..These interchangeable embodiment party
Formula each falls within protection scope of the present invention.
Particularly, according to embodiments of the present invention, it is soft to may be implemented as computer for the process above with reference to flow chart description
Part program.For example, the embodiment of the present invention includes a kind of computer program product, including being tangibly embodied in machine readable media
On computer program, computer program included for the program code of the method shown in execution flow chart, and program code can wrap
The corresponding instruction of corresponding execution method and step provided in an embodiment of the present invention is included, for example, main broadcaster's attribute data of acquisition direct broadcasting room,
Audience attribute data and multiple business object attribute datas；Based on main broadcaster's attribute data, the Audience attribute data with
And the multiple business object attribute data, the selection target business object in multiple business objects；It is shown in the direct broadcasting room
The target service object.In such embodiments, which can be downloaded by communication device from network
And installation and/or from detachable media 511 be mounted.When the computer program is executed by processor, performs the present invention and implement
The above-mentioned function of being limited in the method for example.
It may be noted that according to the needs of implementation, each step/component described in this application can be split as more multistep
The part operation of two or more step/components or step/component can be also combined into new step/component by suddenly/component,
To achieve the object of the present invention.
Above-mentioned the method according to the invention can be realized or be implemented as in hardware, firmware to be storable in recording medium
Software or computer code in (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk) are implemented through network download
Original storage in long-range recording medium or nonvolatile machine readable media and the meter that will be stored in local recording medium
Calculation machine code, so as to which method described here can be stored in using all-purpose computer, application specific processor or programmable or special
With such software processing in the recording medium of hardware (such as ASIC or FPGA).It is appreciated that computer, processor, micro-
Processor controller or programmable hardware include can storing or receive software or computer code storage assembly (for example, RAM,
ROM, flash memory etc.), when the software or computer code are by computer, processor or hardware access and when performing, realize herein
The processing method of description.In addition, when all-purpose computer access is used to implement the code for the processing being shown in which, the execution of code
All-purpose computer is converted to perform the special purpose computer for the processing being shown in which.
Those of ordinary skill in the art may realize that each exemplary lists described with reference to the embodiments described herein
Member and method and step can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is performed with hardware or software mode, specific application and design constraint depending on technical solution.Professional technician
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the embodiment of the present invention.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in change or replacement, should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of business object recommends method, the described method includes：
Obtain main broadcaster's attribute data, Audience attribute data and the multiple business object attribute datas of direct broadcasting room；
Based on main broadcaster's attribute data, the Audience attribute data and the multiple business object attribute data, multiple
Selection target business object in business object；
The target service object is shown in the direct broadcasting room.
It is 2. described based on main broadcaster's attribute data, the Audience attribute data according to the method described in claim 1, wherein
And the multiple business object attribute data, the selection target business object in multiple business objects, including：
Based on main broadcaster's attribute data, the Audience attribute data and the multiple business object attribute data, count respectively
Effect value is launched in the prediction for calculating the multiple business object；
Effect value is launched according to the prediction of the multiple business object, the target service is selected from the multiple business object
Object.
It is 3. described based on main broadcaster's attribute data, the Audience attribute data according to the method described in claim 2, wherein
And Effect value is launched in the multiple business object attribute data, the prediction for calculating the multiple business object respectively, including：
Based on main broadcaster's attribute data and the Audience attribute data, determine to characterize the comprehensive category of the main broadcaster and the spectators
The user attribute data of property；
According to the user attribute data and the multiple business object attribute data, the multiple business object is calculated respectively
Effect value is launched in prediction.
It is 4. described according to the user attribute data and the multiple business object according to the method described in claim 3, wherein
Effect value is launched in attribute data, the prediction for calculating the multiple business object respectively, including：
Establish the functional relation between the combination of user property and business object attribute and the probability of prediction dispensing Effect value；
According to the user attribute data and the multiple business object attribute data, logistic regression algorithm and the institute established are utilized
Functional relation is stated, Effect value is launched in the prediction for calculating each business object respectively.
5. according to any method in claim 2~4, wherein, it is described to be thrown according to the prediction of the multiple business object
Effect value is put, the target service object is selected from the multiple business object, including：
It will predict the business object launched Effect value and be greater than or equal to dispensing effect threshold value, be determined as the target service object.
6. the method according to claim 3 or 4, wherein, the user attribute data includes user property feature vector, institute
Stating business object attribute data includes business object attribute feature vector.
7. the method according to claim 3 or 4, wherein, the synthesized attribute includes at least one of：Essential attribute,
Figure and features feature, purchase pattern, behavioural characteristic, psychological characteristics, Audience attribute, real-time status feature and commercial attribute, wherein, it is described
Audience attribute includes at least one of：The use of sex ratio, ratio of age, region ratio, Income situation and application program
Situation.
8. according to any method in claim 2~7, wherein, Effect value is launched in the prediction includes clicking rate data
And/or effectively viewing person-time, wherein, when effective viewing person-time is for being characterized in business object displaying, viewing in direct broadcasting room
The duration of business object is more than person-time of setting viewing duration.
9. a kind of business object recommendation apparatus, described device include：
Acquisition module, for obtaining main broadcaster's attribute data of direct broadcasting room, Audience attribute data and multiple business object attribute numbers
According to；
Determining module, for being based on main broadcaster's attribute data, the Audience attribute data and the multiple business object category
Property data, the selection target business object in multiple business objects；
Display module, for showing the target service object in the direct broadcasting room.
10. a kind of electronic equipment, including：Processor, memory, communication device and communication bus, the processor, the storage
Device and the communication device complete mutual communication by the communication bus；
For the memory for storing an at least executable instruction, the executable instruction makes the processor perform right such as will
Any business object in 1~8 is asked to recommend the corresponding operation of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710236121.XA CN108073670A (en) | 2017-04-12 | 2017-04-12 | Business object recommends method, apparatus and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710236121.XA CN108073670A (en) | 2017-04-12 | 2017-04-12 | Business object recommends method, apparatus and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108073670A true CN108073670A (en) | 2018-05-25 |
Family
ID=62159082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710236121.XA Pending CN108073670A (en) | 2017-04-12 | 2017-04-12 | Business object recommends method, apparatus and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073670A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019232674A1 (en) * | 2018-06-04 | 2019-12-12 | Weng Shaoming | Community media live-streaming information advertisement method |
| CN110826799A (en) * | 2019-11-05 | 2020-02-21 | 广州虎牙科技有限公司 | Service prediction method, device, server and readable storage medium |
| CN111159562A (en) * | 2019-12-31 | 2020-05-15 | 广州酷狗计算机科技有限公司 | Method, device, system, equipment and storage medium for recommending splicing live broadcast |
| CN111669607A (en) * | 2020-04-30 | 2020-09-15 | 火币（广州）区块链科技有限公司 | Digital interactive text creation system of live broadcast platform |
| CN111711828A (en) * | 2020-05-18 | 2020-09-25 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN112070524A (en) * | 2020-07-24 | 2020-12-11 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
| CN112218105A (en) * | 2020-09-04 | 2021-01-12 | 北京达佳互联信息技术有限公司 | Multimedia service interaction method and device |
| CN113205382A (en) * | 2021-04-30 | 2021-08-03 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113850416A (en) * | 2021-08-26 | 2021-12-28 | 武汉卓尔数字传媒科技有限公司 | Advertisement promotion cooperation object determining method and device |
| CN113949890A (en) * | 2021-09-28 | 2022-01-18 | 北京达佳互联信息技术有限公司 | Object delivery processing method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140123161A1 (en) * | 2012-10-24 | 2014-05-01 | Bart P.E. van Coppenolle | Video presentation interface with enhanced navigation features |
| US20150026718A1 (en) * | 2013-07-19 | 2015-01-22 | United Video Properties, Inc. | Systems and methods for displaying a selectable advertisement when video has a background advertisement |
| KR20150068531A (en) * | 2013-12-11 | 2015-06-22 | 주식회사 쿠노소프트 | Method and apparatus for providing advertisement using linkage live broadcast |
| CN106294831A (en) * | 2016-08-18 | 2017-01-04 | 北京奇虎科技有限公司 | A kind of information recommendation method and electronic equipment |
| CN106507120A (en) * | 2016-10-13 | 2017-03-15 | 北京奇虎科技有限公司 | A kind of processing method of business object, server, terminal and system |
-
2017
- 2017-04-12 CN CN201710236121.XA patent/CN108073670A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140123161A1 (en) * | 2012-10-24 | 2014-05-01 | Bart P.E. van Coppenolle | Video presentation interface with enhanced navigation features |
| US20150026718A1 (en) * | 2013-07-19 | 2015-01-22 | United Video Properties, Inc. | Systems and methods for displaying a selectable advertisement when video has a background advertisement |
| KR20150068531A (en) * | 2013-12-11 | 2015-06-22 | 주식회사 쿠노소프트 | Method and apparatus for providing advertisement using linkage live broadcast |
| CN106294831A (en) * | 2016-08-18 | 2017-01-04 | 北京奇虎科技有限公司 | A kind of information recommendation method and electronic equipment |
| CN106507120A (en) * | 2016-10-13 | 2017-03-15 | 北京奇虎科技有限公司 | A kind of processing method of business object, server, terminal and system |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019232674A1 (en) * | 2018-06-04 | 2019-12-12 | Weng Shaoming | Community media live-streaming information advertisement method |
| CN110826799A (en) * | 2019-11-05 | 2020-02-21 | 广州虎牙科技有限公司 | Service prediction method, device, server and readable storage medium |
| CN111159562A (en) * | 2019-12-31 | 2020-05-15 | 广州酷狗计算机科技有限公司 | Method, device, system, equipment and storage medium for recommending splicing live broadcast |
| CN111159562B (en) * | 2019-12-31 | 2024-05-24 | 广州酷狗计算机科技有限公司 | Method, device, system, equipment and storage medium for recommending specific live broadcast |
| CN111669607A (en) * | 2020-04-30 | 2020-09-15 | 火币（广州）区块链科技有限公司 | Digital interactive text creation system of live broadcast platform |
| CN111711828A (en) * | 2020-05-18 | 2020-09-25 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN111711828B (en) * | 2020-05-18 | 2022-04-05 | 北京字节跳动网络技术有限公司 | Information processing method and device and electronic equipment |
| CN112070524B (en) * | 2020-07-24 | 2024-02-13 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
| CN112070524A (en) * | 2020-07-24 | 2020-12-11 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
| CN112218105A (en) * | 2020-09-04 | 2021-01-12 | 北京达佳互联信息技术有限公司 | Multimedia service interaction method and device |
| CN113205382A (en) * | 2021-04-30 | 2021-08-03 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113205382B (en) * | 2021-04-30 | 2024-02-20 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113850416A (en) * | 2021-08-26 | 2021-12-28 | 武汉卓尔数字传媒科技有限公司 | Advertisement promotion cooperation object determining method and device |
| CN113949890B (en) * | 2021-09-28 | 2023-09-29 | 北京达佳互联信息技术有限公司 | Object delivery processing method and device, electronic equipment and storage medium |
| WO2023050974A1 (en) * | 2021-09-28 | 2023-04-06 | 北京达佳互联信息技术有限公司 | Object delivery processing method and apparatus, electronic device, and storage medium |
| CN113949890A (en) * | 2021-09-28 | 2022-01-18 | 北京达佳互联信息技术有限公司 | Object delivery processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108073670A (en) | Business object recommends method, apparatus and electronic equipment | |
| CN110570232B (en) | Internet advertisement putting method and device, server and storage medium | |
| US11523177B2 (en) | Methods and apparatus to replicate panelists using a local minimum solution of an integer least squares problem | |
| CN108073671A (en) | Business object recommends method, apparatus and electronic equipment | |
| CN108076353A (en) | Business object recommends method, apparatus, storage medium and electronic equipment | |
| CN108476334A (en) | What advertisement was launched optimizes across screen | |
| CN103295148B (en) | The method and apparatus generating and realizing data model | |
| TW201939400A (en) | Method and device for determining group of target users | |
| CN105608125B (en) | Information processing method and server | |
| CN110602514B (en) | Live channel recommendation method and device, electronic equipment and storage medium | |
| KR20100114860A (en) | Touchpoint customization system | |
| CN111062735A (en) | Advertisement putting method, device, system, terminal and computer readable storage medium | |
| CN105210143A (en) | Augmented reality auction platform | |
| CN108629608A (en) | User data processing method and processing device | |
| CN110072116A (en) | Virtual newscaster's recommended method, device and direct broadcast server | |
| CN108900924A (en) | The method and apparatus of commending friends in direct broadcasting room | |
| JP2020517038A (en) | Business object recommendation method, device, electronic device and storage medium | |
| US20210382609A1 (en) | Method and device for displaying multimedia resource | |
| CN108073672A (en) | Business object recommends method, apparatus and electronic equipment | |
| CN113535991A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN107067142A (en) | The dynamic adjusting method and device of resource contention parameter threshold in resource contention | |
| CN108076373A (en) | Processing method, device and the electronic equipment of video image | |
| CN106156351A (en) | Multimedia resource recommendation information generates method and device | |
| CN107507022A (en) | A kind of advertising results appraisal procedure and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180525 |