CN108073672A - Business object recommends method, apparatus and electronic equipment - Google Patents
Business object recommends method, apparatus and electronic equipment Download PDFInfo
- Publication number
- CN108073672A CN108073672A CN201710236783.7A CN201710236783A CN108073672A CN 108073672 A CN108073672 A CN 108073672A CN 201710236783 A CN201710236783 A CN 201710236783A CN 108073672 A CN108073672 A CN 108073672A
- Authority
- CN
- China
- Prior art keywords
- business object
- main broadcaster
- target service
- attribute information
- 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
Abstract
The embodiment of the invention discloses a kind of business objects to recommend method, apparatus and electronic equipment, wherein, business object recommends method to include:Obtain main broadcaster's attribute information of direct broadcasting room and each business object attribute information;Based on main broadcaster's attribute information and each business object attribute information, target service object is determined;The target service object is shown in the direct broadcasting room.Can be that video main broadcaster selects matched business object from business objects library, which has better conformed to the demand of video main broadcaster, realizes the accurate recommendation of business object by the embodiment of the present invention.
Description
Technical field
The present embodiments relate to field of artificial intelligence more particularly to a kind of business object recommend method, apparatus and
Electronic equipment.
Background technology
At present in internet, the attribute data of user plays increasing work in many application fields such as advertisement field
With the attribute data of user can guide the input of advertisement.
In the analytical plan of existing user attribute data, mainly pass through the historical behavior data such as browser of user
Cookie data carries out user labeling processing, and then the classification of user is obtained by the realization of labeling treated data
The attribute data of user, and then, advertising input is guided according to the attribute data of the user.But this method can not instruct advertisement
Etc. the accurate of business objects recommend and launch.
The content of the invention
The embodiment of the present invention is designed to provide a kind of business object suggested design.
It is according to embodiments of the present invention in a first aspect, providing a kind of business object recommends method, including:Obtain direct broadcasting room
Main broadcaster's attribute information and each business object attribute information;Based on main broadcaster's attribute information and each business object attribute letter
Breath, determines target service object;The target service object is shown in the direct broadcasting room.
Optionally, it is described based on main broadcaster's attribute information and each business object attribute information, determine target service
Object, including:According to main broadcaster's attribute information, main broadcaster's label information is generated;According to business object attribute information, business is generated
Object tag information;Based on main broadcaster's label information and each business object label information, the target service pair is determined
As.
Optionally, it is described based on main broadcaster's label information and each business object label information, determine the target
Business object, including:Main broadcaster's label information is subjected to vectorization processing, generates main broadcaster's label vector;By each business
Object tag information carries out vectorization processing, generates each business object label vector;Based on main broadcaster's label vector and each institute
Business object label vector is stated, the prediction for calculating each business object enables rate;Prediction based on each business object enables rate,
Determine the target service object.
Optionally, the prediction based on each business object enables rate, determines the target service object, including:
Business object of the rate that enables more than given threshold will be predicted, as the target service object;Or, enable rate maximum by predicting
Business object, as the target service object.
Optionally, it is described based on main broadcaster's label vector and each business object label vector, calculate each business pair
The prediction of elephant enables rate, including:Obtain main broadcaster's label vector the first weight and the business object label vector
Two weights;Based on main broadcaster's label vector, the first weight, the business object label vector and the second weight, described in calculating
The prediction of business object enables rate.
Optionally, the prediction based on each business object enables rate, before determining the target service object, also
Including:It enables the prediction of each business object rate and carries out Regularization, the optimum prediction for obtaining business object enables rate.
Optionally, it is described to show the target service object in the direct broadcasting room, including:When there are multiple target services pair
As when, rate is enabled according to the prediction of the multiple target service object, it is corresponding to generate the multiple target service object
Show priority;According to the corresponding displaying priority of the multiple target service object, the multiple target service is shown
Object.
Optionally, main broadcaster's attribute information includes following at least one:The essential attribute of main broadcaster, figure and features feature, purchase
Type, behavioural characteristic, psychological characteristics, real-time status feature and Audience attribute.
Optionally, the Audience attribute includes following at least one:Sex ratio, age bracket ratio, region ratio and receipts
Enter situation.
Optionally, the business object attribute information includes following at least one:The fields of business object, affiliated product
Board, effect properties, triggering information, audience attributes and main broadcaster's attribute.
Optionally, the business object includes:Include the special efficacy of semantic information.
Second aspect according to embodiments of the present invention additionally provides a kind of business object recommendation apparatus, including:Obtain mould
Block, for obtaining main broadcaster's attribute information of direct broadcasting room and each business object attribute information;Determining module, for being based on the main broadcaster
Attribute information and each business object attribute information, determine target service object;Display module, in the direct broadcasting room exhibition
Show the target service object.
Optionally, the determining module includes:First generation submodule, for according to main broadcaster's attribute information, generation
Main broadcaster's label information;Second generation submodule, for according to business object attribute information, generating business object label information;It is right
As determination sub-module, for being based on main broadcaster's label information and each business object label information, the target industry is determined
Business object.
Optionally, the object determination sub-module includes:Primary vector generation unit, for by main broadcaster's label information
Vectorization processing is carried out, generates main broadcaster's label vector;Secondary vector generation unit, for by each business object label information
Vectorization processing is carried out, generates each business object label vector;Computing unit, for being based on main broadcaster's label vector and each institute
Business object label vector is stated, the prediction for calculating each business object enables rate;Target service object determination unit, it is each for being based on
The prediction of the business object enables rate, determines the target service object.
Optionally, the target service object determination unit, for that will predict that the rate that enables is more than the business pair of given threshold
As the target service object;Or, will predict the business object for enabling rate maximum, as the target service object.
Optionally, the computing unit, for obtaining the first weight of main broadcaster's label vector and the business object
Second weight of label vector;Based on main broadcaster's label vector, the first weight, the business object label vector and the second power
Weight, the prediction for calculating the business object enable rate.
Optionally, the object determination sub-module further includes:Regularization unit, in the target service object
Prediction of the determination unit based on each business object enables rate, before determining the target service object, to each business
The prediction of object enables rate and carries out Regularization, and the optimum prediction for obtaining business object enables rate.
Optionally, the display module, for when there are during multiple target service objects, according to the multiple target service
The prediction of object enables rate, generates the corresponding displaying priority of the multiple target service object;According to the multiple mesh
The corresponding displaying priority of business object is marked, shows the multiple target service object.
Optionally, main broadcaster's attribute information includes following at least one:The essential attribute of main broadcaster, figure and features feature, purchase
Type, behavioural characteristic, psychological characteristics, real-time status feature and Audience attribute.
Optionally, the Audience attribute includes following at least one:Sex ratio, age bracket ratio, region ratio and receipts
Enter situation.
Optionally, the business object attribute information includes following at least one:The fields of business object, affiliated product
Board, effect properties, triggering information, audience attributes and main broadcaster's attribute.
Optionally, the business object includes:Include the special efficacy of semantic information.
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 of first aspect recommends method.
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 the executable finger of main broadcaster's attribute information of direct broadcasting room and each business object attribute information
Order;For being based on main broadcaster's attribute information and each business object attribute information, the executable of target service object is determined
Instruction;For showing the executable instruction of the target service object in the direct broadcasting room.
The business object suggested design of the embodiment of the present invention, main broadcaster's attribute letter of the video main broadcaster of the direct broadcasting room based on acquisition
The business object attribute information of breath and each business object, determines target service object, and then shows the target service in direct broadcasting room
Object, to be pushed to video main broadcaster.Main broadcaster's attribute information and each business object attribute information by video main broadcaster, Ke Yiwei
Video main broadcaster selects matched business object from business objects library, which has better conformed to video main broadcaster
Demand, realize the accurate recommendation of business object.
Description of the drawings
Fig. 1 is the step flow chart that a kind of business object that the embodiment of the present invention one provides recommends method;
Fig. 2 is the step flow chart that a kind of business object provided by Embodiment 2 of the present invention recommends method;
Fig. 3 is a kind of structure diagram for business object recommendation apparatus that the embodiment of the present invention three provides;
Fig. 4 is a kind of structure diagram for business object recommendation apparatus that the embodiment of the present invention four provides;
Fig. 5 is the structure diagram for a kind of electronic equipment that the embodiment of the present invention five provides.
Specific embodiment
(identical label represents identical element in several attached drawings) and embodiment below in conjunction with the accompanying drawings, implement the present invention
The specific embodiment of example is described in further detail.Following embodiment is not limited to for illustrating the embodiment of the present invention
The scope of the embodiment of the present invention.
It will be understood by those skilled in the art that the terms such as " first ", " second " in the embodiment of the present invention are only used for distinguishing
Different step, equipment or module etc. neither represent any particular technology meaning, also do not indicate that the inevitable logic between them is suitable
Sequence.
Embodiment one
With reference to Fig. 1, show that a kind of business object of the offer of the embodiment of the present invention one recommends the step flow chart of method.
The present embodiment recommends method by taking the background server under live scene as an example, to the business object of the embodiment of the present invention
It is explained.The business object of the present embodiment recommends method specifically to may include steps of:
Step 102, the main broadcaster's attribute information for obtaining direct broadcasting room and each business object attribute information.
The embodiment of the present invention is applied under live scene, and first terminal (such as main broadcaster end) is whole by background server and second
Video communication connection is established at end (such as viewer end).
Background server obtains main broadcaster's attribute information of the current video main broadcaster of direct broadcasting room, is such as imaged by obtaining main broadcaster end
The permission of head, and by the image data of camera acquisition main broadcaster, main broadcaster's attribute of video main broadcaster is obtained further according to image data
Information, for another example by inquiry questionnaire form obtain video main broadcaster main broadcaster's attribute information.
Main broadcaster's attribute information includes but not limited to following at least one:Essential attribute, figure and features feature, the purchase class of main broadcaster
Type, behavioural characteristic, psychological characteristics, real-time status feature and Audience attribute.
In the background server, first terminal and second terminal of the present embodiment, business objects library is both provided with, and can be with
By the synchronization and update of real-time performance business object, wherein, multi-traffic object, business object bag are stored in business objects library
It includes but is not limited to the special efficacy for including semantic information, such as advertisement.
This step also obtains the attribute information of each business object in business objects library, that is, obtains each business object attribute letter
Breath, business object attribute information include but not limited to following at least one:The fields of business object, affiliated brand, effect
Attribute, triggering information, audience attributes and main broadcaster's attribute.
Wherein, main broadcaster's attribute information is capable of the feature of relatively accurately reflecting video main broadcaster, and business object attribute information
It then can relatively accurately reflect the feature of the business object, according to the feature of the two, subsequent target service pair can be carried out
As recommending.
Step 104, based on main broadcaster's attribute information and each business object attribute information, determine target service object.
In the present embodiment, to determine the business object of main broadcaster's attribute information of suitable video main broadcaster, accurate recommendation is reached
Purpose, the business object attribute information of main broadcaster's attribute information of video main broadcaster and each business object is combined, so really
Surely suitable target service object to be recommended, for example, using main broadcaster's attribute information and each business object attribute information as parameter,
It determines the business object attribute information to match with main broadcaster's attribute information, is determined according to the business object attribute information to match
Target service object to be recommended.
Step 106 shows target service object in direct broadcasting room.
After target service object to be recommended is determined in background server, target service object is shown in direct broadcasting room, with
It is pushed to video main broadcaster.
The business object of the present embodiment recommends method, main broadcaster's attribute information of the video main broadcaster of the direct broadcasting room based on acquisition and
The business object attribute information of each business object determines target service object, and then shows the target service object in direct broadcasting room,
To be pushed to video main broadcaster.Main broadcaster's attribute information and each business object attribute information by video main broadcaster can be video
Main broadcaster selects matched business object from business objects library, which has better conformed to the need of video main broadcaster
It asks, realizes the accurate recommendation of business object.
Embodiment two
With reference to Fig. 2, show that a kind of business object provided by Embodiment 2 of the present invention recommends the step flow chart of method, tool
Body may include steps of:
Step 202, the main broadcaster's attribute information for obtaining direct broadcasting room and each business object attribute information.
In the embodiment of the present invention, main broadcaster's attribute information includes but not limited to following at least one:The essential attribute of main broadcaster, body
Looks feature, purchase pattern, behavioural characteristic, psychological characteristics, real-time status feature and Audience attribute.Wherein, Audience attribute include but
It is not limited to following at least one:Sex ratio, age bracket ratio, region ratio and income situation.Audience attribute can be on backstage
Server is counted in advance, such as obtains all spectators of current video main broadcaster, counts the attribute information of each spectators respectively, after
Platform server carries out dynamic statistics to the attribute information of each spectators, you can be carried out at any time according to the variation of Audience attribute information
Dynamic adjusts.
Business object includes but not limited to:Include the special efficacy of semantic information, wherein special efficacy can be the spy of three dimensional form
Effect, as three dimensional form advertisement special efficacy (using 3D special efficacys form show advertisement) or two dimensional form paster, such as two
The advertising sticker special efficacy (advertisement shown using paster form) of dimension form, can also be particle effect.Language in business object
Adopted information can be advertising message, that is, business object can be the one or more in the above-mentioned special efficacy comprising advertising message.
But not limited to this, the business object of other forms is equally applicable the scheme that business object provided in an embodiment of the present invention is recommended,
Such as the explanatory note or introduction or the objects interacted with video spectators of certain forms of APP or other application, (such as electronics is doted on
Object) etc..Business object attribute information includes but not limited to following at least one:The fields of business object, affiliated brand, effect
Fruit attribute, triggering information, audience attributes and main broadcaster's attribute.
Step 204, according to main broadcaster's attribute information, generate main broadcaster's label information;According to business object attribute information, industry is generated
Business object tag information.
Before video main broadcaster is broadcast live or during live streaming, the main broadcaster for getting current video main broadcaster belongs to background server
Property information after, main broadcaster's label information is generated according to main broadcaster's attribute information for getting, such as according to the classification of main broadcaster's attribute information life
Into main broadcaster's label information, main broadcaster's label information can be generated in the form of list item in the present embodiment.For business object attribute
Information can classify according to business object attribute information, and then generate corresponding business object label according to classification results
Information, in the present embodiment business object label information can show as the form of list item.
In the present embodiment, a kind of main broadcaster's label information is specifically as shown in table 1.
Essential attribute:Gender, age, permanent area, occupation, education degree etc.. |
Figure and features feature:Height, weight, face value, dress etc.. |
Purchase pattern:Whether whether Income situation have vehicle, buy house, type of doing shopping, Brang Preference etc.. |
Behavioural characteristic:Hobby, artistic speciality (singing/dancing), active degree. |
Psychological characteristics:Affective state (unmarried/love), personality feature (optimistic/gentle and quiet/intellectual). |
Audience attribute:Sex ratio, ratio of age, region ratio, main foreigner tourists income situation etc.. |
Real-time status feature:Real-time location, expression, Real Time Effect power. |
Table 1
In a kind of optional mode of the embodiment of the present invention, Audience attribute and real-time status feature can be by background servers
All attendance datas of current video main broadcaster are counted, then carry out data analysis acquisition.
In the present embodiment, a kind of business object label information is as shown in table 2.
Table 2
In specific implementation, following place can be used in the process that corresponding label information is generated to the attribute information collected
Reason:
(1) data cleansing
The attribute information collected may be there are a certain proportion of junk information, can be by appropriate ways such as by different
Constant value (such as the age was more than 200 years old etc.) filter type removes certain junk information.For some duplicate messages (as on the other hand
Machine number registers situations such as multiple id) it is filtered duplicate removal processing.At the same time it can also carry out a certain proportion of sampling Detection, understand
Data distribution rule, to remove junk information (such as a large amount of areas are arranged on the id of certain unknown island).
(2) default value is handled
In practical applications, it is commonly present because user information fills in use that is sufficiently complete or can not obtaining by application permission
Family information causes the situation of loss of learning.At this point it is possible to carry out information filling processing, such as filled up using the default value set,
In, default value ordinary circumstance is represented using average value, mode or particular value (representing null value).
(3) labeling of data
After being handled by above-mentioned (1) and (2), the attribute information got still cannot be directly as the category of generation label information
Property information use, it is necessary to be further processed.For example, for the numeric type information such as age (1~13 years old, 14~20 years old, 21~30
Year etc.), income (monthly pay is below 5000, monthly pay 10000 is with first-class) etc. carry out discretization, such as using equivalent division or equivalent division
Deng by classifying and clustering acquisition label.
Step 206, based on main broadcaster's label information and each business object label information, determine target service object.
After main broadcaster's label information and each business object label information is determined, it can be determined based on the matching degree of the two
Target service object.
In one implementation, optionally, main broadcaster's label information can also be carried out to vectorization processing, generation main broadcaster's mark
Label vector;Each business object label information is subjected to vectorization processing, generates each business object label vector;Based on main broadcaster's label
Vectorial and each business object label vector, the prediction for calculating each business object enable rate;Prediction based on each business object enables
Rate determines target service object.Wherein, it is a kind of prediction whether being activated to business object that prediction, which enables rate, and prediction enables
Rate is higher, and the possibility being activated is also higher.
It, can be with to reduce main broadcaster's label information and each business object label information statistical disposition workload in the above process
Binary set processing is carried out to main broadcaster's label information and each business object label information, i.e., is the project of "Yes" in label information
It is represented with " 1 ", is that the project of "No" is represented with " 0 ", it is a kind of that vectorization treated result such as table 3 is carried out to main broadcaster's label information
It is shown, it is a kind of vectorization to be carried out to business object label information treated that the results are shown in Table 4.
Table 3
Table 4
After main broadcaster's label vector and each business object label vector is obtained, the prediction that can calculate each business object is opened
With rate.
For example, represent main broadcaster's label vector using u (n), wherein, n represents the vector dimension of main broadcaster's label vector, such as table 3
Shown in, u (n) is main broadcaster's label vector of each vector value composition, and n is the total number of vector value in table 3, should in actual practicality
Vector dimension is different and different with the number of options under number of labels and each label;Business object label is represented using a (m)
Vector, wherein, m represents the vector dimension of business object label vector, and as shown in table 4, a (m) is the industry of each vector value composition
Object tag of being engaged in vector, m are the total number of vector value in table 4, and in actual practicality, the vector dimension is with number of labels and each mark
The number of options signed it is different and different;The feature vector of u (n) and a (m) combinations is represented using x (a, u).
Based on this, it is as follows that a kind of use basic model logistic regression prediction enables the adoptable formula of rate:
Wherein, p (h>0 | a, u) represent that the prediction of business object enables rate, x (a, u) represents the spy of u (n) and a (m) combinations
Sign vector, ω represent the parameter that the weighting coefficient of each feature and this model needs optimize in x (a, u);ωTRepresent turning for ω
It puts;(2h-1)ωTS type Sigmoid function σ (z)=(1+e is passed through in the output of x (a, u) this linear function-z)-1Be mapped to (0,
1) in section, wherein h for value in the binary variable of { 0,1 }, (2h-1) be in order to will the click of { 0,1,2,3 ... ..., N } change
Amount (variable for being clicked number of business object) is transformed in set { -1,1 }.
In a kind of alternative, to make the calculating that prediction enables rate more accurate, can by those skilled in the art according to
Actual demand sets the weight of vectorization treated main broadcaster's label vector and business object label vector.Then calculating business pair
When the prediction of elephant enables rate, the first weight of main broadcaster's label vector and the second power of business object label vector can also be obtained
Weight;Based on main broadcaster's label vector and the first weight and business object label vector and the second weight, the pre- of business object is calculated
Survey enables rate.Such as, the weighting coefficient that the weighting coefficient of u (n) is 0.5, a (m) is 0.5.
In a kind of alternative, due to above-mentioned prediction, to enable the feature that rate uses more, but a portion feature can
The number that actually can occur or use is simultaneously few, to avoid over-fitting, can also enable rate in the prediction based on each business object
Before determining target service object, enable the prediction of each business object rate and carry out Regularization, obtain business object most
Excellent prediction enables rate.In specific calculate, a kind of feasible pattern adds in regularization term, following institute when being included in maximal possibility estimation
Show:
Wherein,Represent the fitting degree of maximal possibility estimation,Table
Show regularization term, min expressions are minimized.
Based on the above process, in definite target service object, business of the rate that enables more than given threshold can will be predicted
Object, as target service object;Alternatively, the business object for enabling rate maximum will be predicted, as target service object.
For example, the prediction of business object is enabled business object of the rate more than given threshold a is determined as target to be recommended
Business object, if a is 0.6, the average value that can enable rate according to the prediction of whole business object in the present embodiment a is set
Fixed, the present embodiment is not especially limited this.
Step 208 shows target service object in direct broadcasting room.
When only existing a qualified target service object, directly the target service object is shown in direct broadcasting room;
When there are during multiple target service objects, then can enabling rate according to the prediction of multiple target service objects, generate multiple targets
The corresponding displaying priority of business object;According to the corresponding displaying priority of multiple target service objects, displaying is more
A target service object.
In addition, in embodiments of the present invention, to prevent target service number of objects excessive, mesh to be recommended can also be set
The quantity of business object is marked, is such as no more than 20.
When showing target service object, the mode pushed to video main broadcaster may be employed, it is alternatively possible to first eventually
It holds and recommends target service object to video main broadcaster in the form of a list on (main broadcaster end), video main broadcaster can be by clicking operation
Trigger the displaying of corresponding target service object.
The business object of the embodiment of the present invention recommends method, and main broadcaster is determined by main broadcaster's attribute information according to video main broadcaster
Label information determines corresponding business object label information, by main broadcaster's label information and industry according to each business object attribute information
The object tag information of being engaged in carries out vectorization processing, based on vectorization treated main broadcaster's label vector and business object label vector
Determine that the prediction of business object enables rate, the prediction of business object is enabled rate is determined as treating more than the business object of given threshold
The target service object of recommendation is pushed to video main broadcaster.It, can be from business objects library by main broadcaster's attribute data of video main broadcaster
In determine matched business object, business object maximization ground has met the demand of main broadcaster, realizes business pair
The accurate recommendation of elephant.
It will be understood by those skilled in the art that in the above method of specific embodiment of the embodiment of the present invention, each step
Sequence number size be not meant to the priority of execution sequence, the execution sequence of each step should be determined with its function and internal logic,
Implementation process without tackling specific embodiment of the embodiment of the present invention forms any restriction.
Embodiment three
Reference Fig. 3 shows a kind of structure diagram for business object recommendation apparatus that the embodiment of the present invention three provides.
The business object recommendation apparatus of the present embodiment includes:Acquisition module 302, for obtaining main broadcaster's attribute of direct broadcasting room letter
Breath and each business object attribute information;Determining module 304, for being based on main broadcaster's attribute information and each business object attribute information,
Determine target service object;Display module 306, for showing target service object in direct broadcasting room.
The business object recommendation apparatus of the embodiment of the present invention, main broadcaster's attribute letter of the video main broadcaster of the direct broadcasting room based on acquisition
The business object attribute information of breath and each business object, determines target service object, and then shows the target service in direct broadcasting room
Object, to be pushed to video main broadcaster.Main broadcaster's attribute information and each business object attribute information by video main broadcaster, Ke Yiwei
Video main broadcaster selects matched business object from business objects library, which has better conformed to video main broadcaster
Demand, realize the accurate recommendation of business object.
Example IV
Reference Fig. 4 shows a kind of structure diagram for business object recommendation apparatus that the embodiment of the present invention four provides.
The business object recommendation apparatus of the present embodiment includes:Acquisition module 402, for obtaining main broadcaster's attribute of direct broadcasting room letter
Breath and each business object attribute information;Determining module 404, for being based on main broadcaster's attribute information and each business object attribute information,
Determine target service object;Display module 406, for showing target service object in direct broadcasting room.
Optionally it is determined that module 404 includes:First generation submodule 4042, for according to main broadcaster's attribute information, generation master
Broadcast label information;Second generation submodule 4044, for according to business object attribute information, generating business object label information;
Object determination sub-module 4046 for being based on main broadcaster's label information and each business object label information, determines target service object.
Optionally, object determination sub-module 4046 includes:Primary vector generation unit 40462, for main broadcaster's label to be believed
Breath carries out vectorization processing, generates main broadcaster's label vector;Secondary vector generation unit 40464, for by each business object label
Information carries out vectorization processing, generates each business object label vector;Computing unit 40466, for being based on main broadcaster's label vector
And each business object label vector, the prediction for calculating each business object enable rate;Target service object determination unit 40468 is used
Rate is enabled in the prediction based on each business object, determines target service object.
Optionally, target service object determination unit 40468 is used to predict that the rate that enables is more than the business pair of given threshold
As target service object;Or, will predict the business object for enabling rate maximum, as target service object.
Optionally, computing unit 40466 is used to obtain the first weight of main broadcaster's label vector and business object label vector
The second weight;Based on main broadcaster's label vector, the first weight, business object label vector and the second weight, business object is calculated
Prediction enable rate.
Optionally, object determination sub-module 4046 further includes:Regularization unit 40469, in target service pair
As prediction of the determination unit 40468 based on each business object enables rate, before determining target service object, to each business object
Prediction enables rate and carries out Regularization, and the optimum prediction for obtaining business object enables rate.
Optionally, display module 406 is used for when there are during multiple target service objects, according to multiple target service objects
Prediction enables rate, generates the corresponding displaying priority of multiple target service objects;Distinguish according to multiple target service objects
Corresponding displaying priority shows multiple target service objects.
Optionally, main broadcaster's attribute information includes following at least one:The essential attribute of main broadcaster, figure and features feature, purchase pattern,
Behavioural characteristic, psychological characteristics, real-time status feature and Audience attribute.
Optionally, Audience attribute includes following at least one:Sex ratio, age bracket ratio, region ratio and income feelings
Condition.
Optionally, business object attribute information includes following at least one:The fields of business object, affiliated brand,
Effect properties, triggering information, audience attributes and main broadcaster's attribute.
Optionally, business object includes:Include the special efficacy of semantic information.
The business object recommendation apparatus of the present embodiment is used to implement corresponding business object in aforesaid plurality of embodiment of the method
Recommendation method, and the advantageous effect with corresponding embodiment of the method, details are not described herein.
Embodiment five
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
The corresponding operation of data analysing method for any one business object that inventive embodiments provide, for example, obtaining the main broadcaster of direct broadcasting room
Attribute information and each business object attribute information;Based on main broadcaster's attribute information and each business object attribute information, target industry is determined
Business object;Target service object is shown in direct broadcasting room.
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 and performs the corresponding operation of above-mentioned communication means.Input/output (I/O) interface 505 is also connected to communication bus 504.Communication
Component 512 can be integrally disposed, may be set to be with multiple submodule (such as multiple IB network interface cards), and in communication bus chain
It connects.
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..Driver 510 is also according to needing to connect
It is connected to I/O interfaces 505.Detachable media 511, such as disk, CD, magneto-optic disk, semiconductor memory etc. are pacified 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, obtaining main broadcaster's attribute information of direct broadcasting room
And each business object attribute information;Based on main broadcaster's attribute information and each business object attribute information, target service object is determined;
Direct broadcasting room shows target service object.In such embodiments, which can be by communication device from network
It is downloaded and installed and/or is mounted from detachable media 511.When the computer program is executed by processor, this hair is performed
The above-mentioned function of being limited in the method for bright embodiment.
It may be noted that according to the needs of implementation, all parts/step described in the embodiment of the present invention can be split as more
The part operation of two or more components/steps or components/steps can be also combined into new component/step by multi-part/step
Suddenly, to realize the purpose of the embodiment of the present invention.
It is above-mentioned to realize or be implemented as in hardware, firmware according to the method for the embodiment of the present invention to be storable in note
Software or computer code in recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk) are implemented through net
The original storage that network is downloaded is in long-range recording medium or nonvolatile machine readable media and will be stored in local recording medium
In computer code, can be stored in using all-purpose computer, application specific processor or can compile so as to method described here
Such software processing in journey or the recording medium of specialized hardware (such as ASIC or FPGA).It is appreciated that computer, processing
Device, microprocessor 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
Processing method described here.In addition, when all-purpose computer access is used to implement the code for the processing being shown in which, code
It performs and is converted to all-purpose computer 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.
Embodiment of above is merely to illustrate the embodiment of the present invention, and is not the limitation to the embodiment of the present invention, related skill
The those of ordinary skill in art field in the case where not departing from the spirit and scope of the embodiment of the present invention, can also make various
Variation and modification, therefore all equivalent technical solutions fall within the scope of the embodiment of the present invention, the patent of the embodiment of the present invention
Protection domain should be defined by the claims.
Claims (10)
1. a kind of business object recommends method, which is characterized in that including:
Obtain main broadcaster's attribute information of direct broadcasting room and each business object attribute information;
Based on main broadcaster's attribute information and each business object attribute information, target service object is determined;
The target service object is shown in the direct broadcasting room.
2. according to the method described in claim 1, it is characterized in that, described be based on main broadcaster's attribute information and each business
Object properties information determines target service object, including:
According to main broadcaster's attribute information, main broadcaster's label information is generated;
According to business object attribute information, business object label information is generated;
Based on main broadcaster's label information and each business object label information, the target service object is determined.
3. according to the method described in claim 2, it is characterized in that, described be based on main broadcaster's label information and each business
Object tag information determines the target service object, including:
Main broadcaster's label information is subjected to vectorization processing, generates main broadcaster's label vector;
Each business object label information is subjected to vectorization processing, generates each business object label vector;
Rate is enabled based on main broadcaster's label vector and each business object label vector, the prediction for calculating each business object;
Prediction based on each business object enables rate, determines the target service object.
4. according to the method described in claim 3, it is characterized in that, the prediction based on each business object enables rate,
Determine the target service object, including:
Business object of the rate that enables more than given threshold will be predicted, as the target service object;Or,
The business object for enabling rate maximum will be predicted, as the target service object.
5. the method according to claim 3 or 4, which is characterized in that described based on main broadcaster's label vector and each described
Business object label vector, the prediction for calculating each business object enable rate, including:
Obtain the first weight of main broadcaster's label vector and the second weight of the business object label vector;
Based on main broadcaster's label vector, the first weight, the business object label vector and the second weight, the business is calculated
The prediction of object enables rate.
6. according to claim 3-5 any one of them methods, which is characterized in that the prediction based on each business object
Rate is enabled, before determining the target service object, is further included:
It enables the prediction of each business object rate and carries out Regularization, the optimum prediction for obtaining business object enables rate.
7. according to claim 3-6 any one of them methods, which is characterized in that described to show the target in the direct broadcasting room
Business object, including:
When there are during multiple target service objects, enabling rate according to the prediction of the multiple target service object, generation is described more
The corresponding displaying priority of a target service object;
According to the corresponding displaying priority of the multiple target service object, the multiple target service object is shown.
8. according to claim 1-7 any one of them methods, which is characterized in that main broadcaster's attribute information include it is following at least
One:Essential attribute, figure and features feature, purchase pattern, behavioural characteristic, psychological characteristics, real-time status feature and the spectators of main broadcaster belong to
Property.
9. a kind of business object recommendation apparatus, which is characterized in that including:
Acquisition module, for obtaining main broadcaster's attribute information of direct broadcasting room and each business object attribute information;
Determining module for being based on main broadcaster's attribute information and each business object attribute information, determines target service pair
As;
Display module, for showing the target service object in the direct broadcasting room.
10. a kind of electronic equipment, which is characterized in that including:Processor, memory, communication device and communication bus, the processing
Device, the memory 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 objects of 1-8 is asked to recommend method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710236783.7A CN108073672A (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 |
---|---|---|---|
CN201710236783.7A CN108073672A (en) | 2017-04-12 | 2017-04-12 | Business object recommends method, apparatus and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108073672A true CN108073672A (en) | 2018-05-25 |
Family
ID=62159069
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710236783.7A Pending CN108073672A (en) | 2017-04-12 | 2017-04-12 | Business object recommends method, apparatus and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108073672A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111147887A (en) * | 2020-01-06 | 2020-05-12 | 网易(杭州)网络有限公司 | Live broadcast service control method and device, computer readable medium and electronic equipment |
CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
CN111488529A (en) * | 2020-06-28 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Information processing method, information processing apparatus, server, and storage medium |
CN113660203A (en) * | 2021-07-09 | 2021-11-16 | 北京达佳互联信息技术有限公司 | Anchor account processing method, device and system, electronic equipment and storage medium |
CN116205536A (en) * | 2023-03-06 | 2023-06-02 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
Citations (6)
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 |
CN104394126A (en) * | 2014-11-07 | 2015-03-04 | 广州酷狗计算机科技有限公司 | Information recommendation method, server, client side and system |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
CN105978888A (en) * | 2016-06-20 | 2016-09-28 | 郝运峰 | Live broadcast studio virtual present recommendation method and system |
CN106375792A (en) * | 2016-10-13 | 2017-02-01 | 北京奇虎科技有限公司 | Service object pushing and displaying method, server, terminals and system |
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 CN201710236783.7A patent/CN108073672A/en active Pending
Patent Citations (6)
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 |
CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
CN104394126A (en) * | 2014-11-07 | 2015-03-04 | 广州酷狗计算机科技有限公司 | Information recommendation method, server, client side and system |
CN105978888A (en) * | 2016-06-20 | 2016-09-28 | 郝运峰 | Live broadcast studio virtual present recommendation method and system |
CN106375792A (en) * | 2016-10-13 | 2017-02-01 | 北京奇虎科技有限公司 | Service object pushing and displaying method, server, terminals and system |
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 (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111147887A (en) * | 2020-01-06 | 2020-05-12 | 网易(杭州)网络有限公司 | Live broadcast service control method and device, computer readable medium and electronic equipment |
CN111311420A (en) * | 2020-02-21 | 2020-06-19 | 深圳市思迪信息技术股份有限公司 | Business data pushing method and device |
CN111488529A (en) * | 2020-06-28 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Information processing method, information processing apparatus, server, and storage medium |
CN111488529B (en) * | 2020-06-28 | 2020-09-29 | 腾讯科技(深圳)有限公司 | Information processing method, information processing apparatus, server, and storage medium |
CN113660203A (en) * | 2021-07-09 | 2021-11-16 | 北京达佳互联信息技术有限公司 | Anchor account processing method, device and system, electronic equipment and storage medium |
CN116205536A (en) * | 2023-03-06 | 2023-06-02 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
CN116205536B (en) * | 2023-03-06 | 2023-10-13 | 阿里巴巴(中国)有限公司 | Object evaluation method, computing device, and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110909176B (en) | Data recommendation method and device, computer equipment and storage medium | |
CN107273454B (en) | User data classification method, device, server and computer readable storage medium | |
CN108073672A (en) | Business object recommends method, apparatus and electronic equipment | |
US8543518B2 (en) | Deducing shadow user profiles for ad campaigns | |
CN107346496B (en) | Target user orientation method and device | |
CN102737334B (en) | Micro-segment definition system | |
CN108021929A (en) | Mobile terminal electric business user based on big data, which draws a portrait, to establish and analysis method and system | |
CN108073671A (en) | Business object recommends method, apparatus and electronic equipment | |
CN110472154B (en) | Resource pushing method and device, electronic equipment and readable storage medium | |
CN108090107A (en) | Business object recommends method, apparatus, electronic equipment and storage medium | |
CN108280104A (en) | The characteristics information extraction method and device of target object | |
CN108777701B (en) | Method and device for determining information audience | |
Wang et al. | Large-scale ensemble model for customer churn prediction in search ads | |
CN109785064A (en) | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion | |
KR20190015333A (en) | Dynamic creative optimization to deliver content effectively | |
CN105678317B (en) | Information processing method and server | |
CN109033408A (en) | Information-pushing method and device, computer readable storage medium, electronic equipment | |
CN108073670A (en) | Business object recommends method, apparatus and electronic equipment | |
CN108076387A (en) | Business object method for pushing and device, electronic equipment | |
CN110109901A (en) | The method and apparatus for screening target object | |
CN110717597A (en) | Method and device for acquiring time sequence characteristics by using machine learning model | |
CN116862592B (en) | Automatic push method for SOP private marketing information based on user behavior | |
Gao et al. | Application of artificial intelligence and big data technology in digital marketing | |
CN110428277B (en) | Touch method of recommended product, storage medium and program product | |
Zheng et al. | A scalable purchase intention prediction system using extreme gradient boosting machines with browsing content entropy |
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 |
Application publication date: 20180525 |
|
RJ01 | Rejection of invention patent application after publication |