CN106612461A - A recommendation method, apparatus and system for a product package - Google Patents
A recommendation method, apparatus and system for a product package Download PDFInfo
- Publication number
- CN106612461A CN106612461A CN201510698000.8A CN201510698000A CN106612461A CN 106612461 A CN106612461 A CN 106612461A CN 201510698000 A CN201510698000 A CN 201510698000A CN 106612461 A CN106612461 A CN 106612461A
- Authority
- CN
- China
- Prior art keywords
- product bag
- user
- recommendation
- program
- product
- 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
-
- 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
-
- 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
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a recommendation method for a product package. The method comprises the steps of obtaining user behavior data obtained after statistical analysis by a big data platform; calculating to obtain a set of programs suitable for recommendation to a user based on the acquired user behavior data and a preset recommendation algorithm; selecting a program that satisfies a preset program condition from the set of programs; generating a product package to be recommended according to a preset product package generation format and the selected program; and pushing the relevant information of the product package to be recommended to a set top box for the recommendation of the product package. The invention also discloses a recommendation apparatus and system for the product package. According to the invention, through analysis of user behaviors, the product package in accordance with user interest preferences is generated and recommended in a targeted mode according to the user interest preferences, thereby raising the satisfaction degree of users as to the product package and the order rate.
Description
Technical field
The present invention relates to IPTV field, more particularly to the recommendation method of product bag, device and
System.
Background technology
In recent years, business is gradually for IPTV (Interactive Personality TV, IPTV)
Substitute traditional digital television business and become the main force of digital home.With big data and cloud computing
Rise, it all generates profound influence to all trades and professions, how that big data technology and IPTV service is perfect
With reference to, existing business is catalyzed then and finds new growth point, and then user experience is lifted, this
Have become current IPTV service in the urgent need to study work content.
Product bag specifically refers to operator by the packing of some programme contents and after unified price, then goes out to user
A kind of form sold, it is the main revenue source of IPTV service and approach that product bag is ordered.Existing product
Bag is that operator will again have user voluntarily to select after some content uniform packings, if the product bag that user selects
Can not watch, then point out user to be ordered, therefore, operator can not accomplish different for each user
Characteristic of Interest and intelligence generates different product bags to recommend different users, and then reduce user
Satisfaction and order rate to product bag.
The content of the invention
Present invention is primarily targeted at providing a kind of recommendation method, the apparatus and system of product bag, it is intended to
Solving existing mode intelligent for the different Characteristic of Interest of each user can not generate different product bags simultaneously
Recommend the technical problem of different users.
For achieving the above object, the present invention provides a kind of recommendation method of product bag, and the product bag is pushed away
The method of recommending includes：
Obtaining big data platform carries out user behavior data resulting after statistical analysis；
According to the user behavior data and default proposed algorithm that get, suitable recommendation is calculated
To the program set of user；
The program for meeting default program conditions is selected from the program set, according to default product Bao Sheng
Into form and selected program, product bag to be recommended is generated；
The relevant information of the product bag to be recommended is pushed to Set Top Box to carry out the recommendation of product bag.
Preferably, the proposed algorithm at least includes：Collaborative filtering based on user and/or based on section
Purpose collaborative filtering；The program conditions at least include：Program on-line time and/or play-on-demand program heat
Degree.
Preferably, the recommendation method of the product bag also includes：
Obtain scoring of some users for identical product bag；
According to default statistic algorithm, the TOP SCORES of Related product bag is calculated；
The relevant information for meeting the product bag of default scoring condition is pushed to respective set-top box to recommend phase
Using family.
Preferably, the recommendation method of the product bag also includes：
Obtain product bag and corresponding groups of users or good friend that user shares recommendation；
The relevant information that user is shared the product bag of recommendation pushes to corresponding groups of users or good friend
Set Top Box is recommending relative users.
Further, for achieving the above object, the present invention also provides a kind of recommendation apparatus of product bag, institute
Stating the recommendation apparatus of product bag includes：
Behavioral data acquisition module, for obtaining big data platform user resulting after statistical analysis is carried out
Behavioral data；
Program set calculation module, for according to the user behavior data and default recommendation for getting
Algorithm, is calculated and is adapted to the program set for recommending user；
Product bag generation module, for selecting to meet the program of default program conditions from the program set,
Form and selected program are generated according to default product bag, product bag to be recommended is generated；
The recommending module of product bag first, for the relevant information of the product bag to be recommended to be pushed to into machine
Top box is carrying out the recommendation of product bag.
Preferably, the proposed algorithm at least includes：Collaborative filtering based on user and/or based on section
Purpose collaborative filtering；The program conditions at least include：Program on-line time and/or play-on-demand program heat
Degree.
Preferably, the recommendation apparatus of the product bag also include：
Scoring acquisition module, for obtaining scoring of some users for identical product bag；
TOP SCORES computing module, for according to default statistic algorithm, being calculated Related product bag
TOP SCORES；
The recommending module of product bag second, the relevant information for the product bag by default scoring condition is met is pushed away
Deliver to respective set-top box to recommend relative users.
Preferably, the recommendation apparatus of the product bag also include：
Sharing data acquisition module, for obtaining user the product bag of recommendation and corresponding user are shared
Group or good friend；
The recommending module of product bag the 3rd, pushes for user to be shared the relevant information of product bag of recommendation
To the Set Top Box of corresponding groups of users or good friend recommending relative users.
Preferably, the recommendation apparatus of the product bag also include：
Message pushes processing module, for the relevant information of product bag to be pushed in the form of a message into Set Top Box；
And the time point that message is pushed is carried out after hashed, according to the push strategy of configuration, on machine top
Message push is carried out after box start.
Further, for achieving the above object, the present invention also provides a kind of commending system of product bag, institute
Stating the commending system of product bag includes the recommendation apparatus of the product bag described in any of the above-described；The product bag
Commending system also include big data platform and Set Top Box；The big data platform is used to gather the machine top
The user behavior data at box end simultaneously carries out statistical analysis process；The Set Top Box is used to provide described in display
The interface of the relevant information of the product bag to be recommended that EPG is pushed and user interface.
The present invention by using big data and cloud computing technology, to user behavior statistical analysis being carried out, from
And can targetedly be generated according to the interest preference of user and meet the product bag of user interest preference simultaneously
Recommended, so as to improve satisfaction and order rate of the user to product bag.Additionally, the present invention is extended
Sharing and scoring function for product bag, strengthens interacting between operator and user, further improves
The issue flow process of existing product bag, so as to further increase user experience.
Description of the drawings
Fig. 1 is the schematic flow sheet of the recommendation method first embodiment of product bag of the present invention；
Fig. 2 is the ordering page schematic diagram of product bag of the present invention；
Fig. 3 is that the message of product bag of the present invention recommends page schematic diagram；
Fig. 4 is the schematic flow sheet of the recommendation method second embodiment of product bag of the present invention；
Fig. 5 is the ordering page schematic diagram of product bag of the present invention；
Fig. 6 is the schematic flow sheet of the recommendation method 3rd embodiment of product bag of the present invention；
Fig. 7 is the recommendation page schematic diagram of product bag of the present invention；
Fig. 8 is the high-level schematic functional block diagram of the recommendation apparatus first embodiment of product bag of the present invention；
Fig. 9 is the high-level schematic functional block diagram of the recommendation apparatus second embodiment of product bag of the present invention；
Figure 10 is the high-level schematic functional block diagram of the recommendation apparatus 3rd embodiment of product bag of the present invention；
Figure 11 is the high-level schematic functional block diagram of the recommendation apparatus fourth embodiment of product bag of the present invention；
Figure 12 is the high-level schematic functional block diagram of the embodiment of commending system one of product bag of the present invention；
Figure 13 is the general frame schematic diagram of the embodiment of commending system one of product bag of the present invention.
The realization of the object of the invention, functional characteristics and advantage will be done referring to the drawings further in conjunction with the embodiments
Explanation.
Specific embodiment
It should be appreciated that specific embodiment described herein is not used to limit only to explain the present invention
The present invention.
With reference to Fig. 1, Fig. 1 is the schematic flow sheet of the recommendation method first embodiment of product bag of the present invention.This
In embodiment, the recommendation method of the product bag includes：
Step 110, obtaining big data platform carries out user behavior data resulting after statistical analysis；
In the present embodiment, big data platform specifically obtains the behavioral data of user, such as user from Set Top Box
Selected program platform and corresponding program category, viewing time, viewing duration, user's request program,
Searching programs etc. can serve as the behavioral data of user, be entered by the behavioral data of the user to getting
Rack calculating working process, such as counted, classified, being concluded, being excavated etc. and process, it is latent so as to obtain
Value information and user's request, then carry out subsequent treatment further according to the data after working process, than
Such as analyze the behavioural habits or TV programme interested of user.In the present embodiment, big data platform
The on-demand content data of user are mainly extracted to analyze preference of the user for programme content.
Step 120, according to the user behavior data and default proposed algorithm that get, is calculated
It is adapted to recommend the program set of user；
Existing proposed algorithm mainly includes：(1), content-based recommendation algorithm, it is past according to user
Browse the recommendation items for recording to be not in contact with to user recommended user；(2), collaborative filtering, in sea
Excavate fraction and sample similar user with you in amount data, by collaborative filtering by these user Cheng Xi
Joyous program recommends you.The characteristics of based on each proposed algorithm, preferably using based on user in the present embodiment
Collaborative filtering and/or the collaborative filtering based on program.
Based on the synergetic of user, by analyzing the use watched some contents jointly and produce between user
The set that family is liked certain content jointly, is to carry out cooperated computing according to viewing behavioral data between user
Go out the properties collection that certain user may be interested.Such as, party A-subscriber and party B-subscriber like seeing a film,
If party A-subscriber likes seeing science fiction movies and cartoon, then it is assumed that party B-subscriber is also to science fiction movies and cartoon sense
Interest.
And the synergetic for being based on content refer to must be certain user of network analysis behavioral data, according to content
Between similarity, calculate the properties collection that the user may be interested.Such as, party A-subscriber likes seeing
Film, if film is higher with the similarity of TV play, then it is assumed that party A-subscriber is also interested in TV play.
In the present embodiment, the user behavior data that obtained according to the big data platform statistical analysis for getting and
Default proposed algorithm, so as to be calculated by proposed algorithm the program set for recommending user is adapted to.
For example, if obtain user by big data Platform Analysis compares sense to the variety show of tri- platforms of A, B, C
Interest, then think that user is also interested in the variety show of the platforms such as D, E, F by proposed algorithm, therefore
It is adapted to recommend user.
Step 130, selects the program for meeting default program conditions, according to default from the program set
Product bag generates form and selected program, generates product bag to be recommended；
After obtaining being adapted to the program set for recommending user, all programs can all be recommended user,
Or selectively select some programs to recommend user.In the present embodiment, be improve Consumer's Experience and
Satisfaction, preferably selects optimal recommendation program according to program on-line time and/or play-on-demand program temperature.Than
If program on-line time is in one week, or program on-line time is in one month and program request number exceedes
More than 100000.
In the present embodiment, the generation form of product bag is not limited, and is configured with specific reference to being actually needed.Than
Such as include price, the program description of product bag of product bag, number of programs that product bag is included etc..
Step 140, the relevant information of the product bag to be recommended is pushed to Set Top Box to carry out product bag
Recommendation.
In the present embodiment, after product bag to be recommended is generated, need the relevant information of product bag, than
Such as by the bag name of product bag, the program content descriptions for including, price, effective time information pushing to machine
Top box is simultaneously on the tv screen shown the corresponding information for receiving by Set Top Box, right so as to complete
The product bag of user is recommended.In the present embodiment, because TV programme or user behavior change will cause to treat
Recommend the change of programme content, thus in requisition for the recommendation updated to product bag, therefore, the present embodiment
In preferably using push by the way of, carry out the transmission of the recommendation message of product bag.Such as, according to product bag
The renewal time carry out message push, or fixed intervals duration carries out periodic message push etc..
The ordering page of product bag as shown in Figure 2.In user's ordering products bag, EPG system is by root
According to the similarity between different product bag, all product bags that EPG system is intelligently generated under the user are matched,
And the higher product bag of the similarity of the product bag currently ordered with user is therefrom matched, and to matching
Product bag certain discount is given on the basis of total price, so as to improve the order rate of product bag.Such as,
The product to be recommended that EPG system is generated is surrounded by tetra- product bags of A, B, C, D, such as user selects
A product bags are ordered, then when user selects to order A product bags, shows tri- product bags of B, C, D
And inform with corresponding discount and show the price after giving a discount, more select so as to give user,
And then the order rate of raising product bag
The message of product bag as shown in Figure 3 recommends the page.EPG system will be for each user institute intelligence
The recommended products package informatin of generation is periodically pushed to Set Top Box, and Set Top Box is received after PUSH message, bullet
Go out prompting interface, after user selects, you can open the original list of the product bag that EPG system is recommended.
Additionally, recommend on the page in message as shown in Figure 3, while also show recommended products relevant historical record,
The such as price of product bag, grading information is commented, user can recommend on the page directly in the message of product bag
Order corresponding product bag.
In the present embodiment, by using big data and cloud computing technology, to user behavior statistical being carried out
Analysis such that it is able to the product for meeting user interest preference is targetedly generated according to the interest preference of user
Product bag is simultaneously recommended, so as to improve satisfaction and order rate of the user to product bag.
With reference to Fig. 4, Fig. 4 is the schematic flow sheet of the recommendation method second embodiment of product bag of the present invention.This
In embodiment, the recommendation method of the product bag also includes：
Step S210, obtains some users for the scoring of identical product bag；
Step S220, according to default statistic algorithm, is calculated the TOP SCORES of Related product bag；
Step S230, by the relevant information for meeting the product bag of default scoring condition respective set-top box is pushed to
To recommend relative users.
In the present embodiment, except the product bag that can meet user interest preference based on EPG system generation is gone forward side by side
Outside row is recommended, while the scoring that can also be based further on other users carries out the recommendation of product bag.Such as Fig. 5
The ordering page of shown product bag, user can enter after purchase product bag to the product bag bought
Row scoring, such as be set to 0-10 point by score value, and the more high then corresponding product customer satisfaction of score value is higher.
In the present embodiment, EPG system is by obtaining other users for the scoring of identical product bag, and root
According to default statistic algorithm, statistical computation obtains the TOP SCORES of the product bag with scoring.For example, have
100 users are scored A product bags；There are 300 users to score B product bags；
Then according to default statistic algorithm, such as it is 7.3 points that EPG system obtains the TOP SCORES of A product bags,
And the TOP SCORES for obtaining B product bags is 9.8 points.
When the TOP SCORES of product bag meets default scoring condition, then the product bag of scoring condition will be met
Relevant information to push to respective set-top box interested in program in the product bag corresponding to recommend
User.For example, default scoring condition is that TOP SCORES is more than 9.5 points, or evaluates user more than 200
People and TOP SCORES grades more than 8.5, is configured with specific reference to being actually needed.
In the present embodiment, scoring function can be set to product bag, further to improve user experience.
It is also possible to scoring other users as one kind foundation to active user's recommended products bag, from
And the way of recommendation of further perfect product bag is bringing user more experiences.Furthermore, it is necessary to
Further illustrate, the execution sequence between step S210-S230 and step S110-S140 is not limited,
It is configured with specific reference to being actually needed.
With reference to Fig. 6, Fig. 6 is the schematic flow sheet of the recommendation method 3rd embodiment of product bag of the present invention.This
In embodiment, the recommendation method of the product bag also includes：
Step S310, obtains product bag and corresponding groups of users or good friend that user shares recommendation；
Step S320, the relevant information that user is shared the product bag of recommendation pushes to corresponding customer group
The Set Top Box of group or good friend is recommending relative users.
Further to improve the way of recommendation of product bag, while the participation of user is improved, in the present embodiment,
Meet the product bag of user interest preference and recommended and based on it except being based on EPG system and generate
The scoring of his user is carried out outside the recommendation of product bag, while sharing for other users can also be based further on
Carry out the recommendation of product bag.The ordering page of product bag as shown in Figure 5, user is in purchase product bag
The product bag bought can be shared afterwards.
For example, user can arrange EPG system login account, and allow user addition good friend, newly-built group
Group etc..When user shares to the product bag bought, product bag can be shared with user and be located
Group, or the good friend for being shared with user.When EPG system monitors there is when sharing of product bag,
Share product bag and corresponding groups of users or the good friend of recommendation by obtaining user, so as to by user
The relevant information of the product bag of shared recommendation pushes to the Set Top Box of corresponding groups of users or good friend, enters
And recommend relevant groups user or good friend user.
The recommendation page of product bag as shown in Figure 7, product bag to be recommended will be shown on this page
The contents such as title, price, referrer, scoring, user with reference to above- mentioned information with choose whether order.
In the present embodiment, further sharing function can also be arranged to product bag, further to improve user
Experience.Meanwhile, also using other users share as the one kind to active user's recommended products bag according to
According to so as to the way of recommendation of further perfect product bag is bringing user more experiences.Additionally,
Need it is further noted that the execution sequence between step S310-S320 and step S110-S140 not
Limit, is configured with specific reference to being actually needed.
With reference to Fig. 8, Fig. 8 is the high-level schematic functional block diagram of the recommendation apparatus first embodiment of product bag of the present invention.
In the present embodiment, the recommendation apparatus of the product bag include：
Behavioral data acquisition module 110, for obtaining big data platform use resulting after statistical analysis is carried out
Family behavioral data；
In the present embodiment, big data platform mainly extract the on-demand content data of user with analyze user for
The preference of programme content, obtaining big data platform by behavioral data acquisition module 110 carries out statistical analysis
Resulting user behavior data afterwards.
Program set calculation module 120, for according to the user behavior data that gets and default pushing away
Algorithm is recommended, is calculated and is adapted to the program set for recommending user；
Preferably using the collaborative filtering and/or the collaborative filtering based on program based on user in the present embodiment
Algorithm.Based on the synergetic of user, produced by watching some contents jointly between analysis user
The set that user likes certain content jointly, is to carry out collaboration meter according to viewing behavioral data between user
Calculate the properties collection that certain user may be interested.Such as, party A-subscriber and party B-subscriber like seeing a film,
If party A-subscriber likes seeing science fiction movies and cartoon, then it is assumed that party B-subscriber is also to science fiction movies and cartoon sense
Interest.And the synergetic for being based on content refer to must be certain user of network analysis behavioral data, according to interior
Similarity between appearance, calculates the properties collection that the user may be interested.Such as, party A-subscriber likes
See a film, if film is higher with the similarity of TV play, then it is assumed that party A-subscriber is also interested in TV play.
In the present embodiment, program set calculation module 120 gets according to behavioral data acquisition module 110
The user behavior data that obtains of big data platform statistical analysis and default proposed algorithm, so as to pass through to push away
Recommend algorithm and be calculated and be adapted to the program set for recommending user.For example, if passing through big data Platform Analysis
The variety show that user is obtained to tri- platforms of A, B, C is interested, then think to use by proposed algorithm
Family is also interested in the variety show of the platforms such as D, E, F, therefore is adapted to recommend user.
Product bag generation module 130, for selecting to meet the section of default program conditions from the program set
Mesh, according to default product bag form and selected program are generated, and generate product bag to be recommended；
After obtaining being adapted to the program set for recommending user in program set calculation module 120, product Bao Sheng
All programs can all be recommended user into module 130, or selectively select some programs to push away
Recommend to user.It is to improve Consumer's Experience and satisfaction in the present embodiment, product bag generation module 130 is excellent
Select and optimal recommendation program is selected according to program on-line time and/or play-on-demand program temperature.Such as program is reached the standard grade
Time is in one week, or program on-line time is in one month and program request number is more than more than 100,000.
In the present embodiment, the generation form of product bag is not limited, and is configured with specific reference to being actually needed.Than
Such as include price, the program description of product bag of product bag, number of programs that product bag is included etc..
The first recommending module of product bag 140, for the relevant information of the product bag to be recommended to be pushed to
Set Top Box is carrying out the recommendation of product bag.
In the present embodiment, after the product bag that product bag generation module 130 generates to be recommended, product bag
One recommending module 140 is needed by the relevant information of product bag, such as by the bag name of product bag, the section for including
The information pushings such as mesh content introduction, price, effective time will be received to Set Top Box and by Set Top Box
Corresponding information shows on the tv screen, recommends so as to complete the product bag to user.The present embodiment
In, will cause the change of programme content to be recommended because TV programme or user behavior change, thus phase
In requisition for the recommendation updated to product bag, therefore, preferably carried out by the way of pushing in the present embodiment
The transmission of the recommendation message of product bag.Such as, message push is carried out according to the renewal time of product bag, or
Person's fixed intervals duration carries out periodic message push etc..
In the present embodiment, preferably the recommendation apparatus of product bag are arranged in EPG system, namely this enforcement
EPG system in example has generation and the recommendation function of product bag.By to using big data and cloud computing
Technology, carries out statistical analysis such that it is able to targeted according to the interest preference of user to user behavior
Generation meet the product bag of user interest preference and recommended, product bag is expired so as to improve user
Meaning degree and order rate.
With reference to Fig. 9, Fig. 9 is the high-level schematic functional block diagram of the recommendation apparatus second embodiment of product bag of the present invention.
In the present embodiment, the recommendation apparatus of the product bag include：
Scoring acquisition module 210, for obtaining scoring of some users for identical product bag；
TOP SCORES computing module 220, for according to default statistic algorithm, being calculated Related product bag
TOP SCORES；
The second recommending module of product bag 230, for the relevant information of the product bag by default scoring condition is met
Push to respective set-top box to recommend relative users.
In the present embodiment, except the product bag that can meet user interest preference based on EPG system generation is gone forward side by side
Outside row is recommended, while the scoring that can also be based further on other users carries out the recommendation of product bag.Such as Fig. 5
The ordering page of shown product bag, user can enter after purchase product bag to the product bag bought
Row scoring, such as be set to 0-10 point by score value, and the more high then corresponding product customer satisfaction of score value is higher.
In the present embodiment, scoring acquisition module 210 is by obtaining other users commenting for identical product bag
Point, according to default statistic algorithm, statistical computation is obtained with scoring TOP SCORES computing module 220
The TOP SCORES of product bag.For example, 100 users score A product bags；There are 300
User is scored B product bags；Then according to default statistic algorithm, such as EPG system obtains A
The TOP SCORES of product bag is 7.3 points, and the TOP SCORES for obtaining B product bags is 9.8 points.
When the TOP SCORES of product bag meets default scoring condition, the second recommending module of product bag 230 is then
The relevant information for meeting the product bag of scoring condition is pushed to into respective set-top box to recommend to the product bag
Interior program relative users interested.For example, default scoring condition is that TOP SCORES is more than 9.5 points,
Or evaluate user is more than 200 people and TOP SCORES grades more than 8.5, set with specific reference to being actually needed
Put.
In the present embodiment, scoring function can be set to product bag, further to improve user experience.
It is also possible to scoring other users as one kind foundation to active user's recommended products bag, from
And the way of recommendation of further perfect product bag is bringing user more experiences.
With reference to Figure 10, Figure 10 is that the functional module of the recommendation apparatus 3rd embodiment of product bag of the present invention is illustrated
Figure.In the present embodiment, the recommendation apparatus of the product bag include：
Sharing data acquisition module 310, for obtaining product bag and corresponding use that user shares recommendation
Family group or good friend；
The recommending module 320 of product bag the 3rd, pushes away for user to be shared the relevant information of product bag of recommendation
Deliver to the Set Top Box of corresponding groups of users or good friend to recommend relative users.
Further to improve the way of recommendation of product bag, while the participation of user is improved, in the present embodiment,
Meet the product bag of user interest preference and recommended and based on it except being based on EPG system and generate
The scoring of his user is carried out outside the recommendation of product bag, while sharing for other users can also be based further on
Carry out the recommendation of product bag.The ordering page of product bag as shown in Figure 5, user is in purchase product bag
The product bag bought can be shared afterwards.
For example, user can arrange EPG system login account, and allow user addition good friend, newly-built group
Group etc..When user shares to the product bag bought, product bag can be shared with user and be located
Group, or the good friend for being shared with user.When monitoring there is when sharing of product bag, by sharing
Data acquisition module 310 obtains product bag and corresponding groups of users or the good friend that user shares recommendation,
The recommending module 320 of product bag the 3rd user is shared the relevant information of the product bag of recommendation and pushes to correspondence
Groups of users or good friend Set Top Box, and then recommend relevant groups user or good friend user.
In the present embodiment, further sharing function can also be arranged to product bag, further to improve user
Experience.Meanwhile, also using other users share as the one kind to active user's recommended products bag according to
According to so as to the way of recommendation of further perfect product bag is bringing user more experiences.
With reference to Figure 11, Figure 11 is that the functional module of the recommendation apparatus fourth embodiment of product bag of the present invention is illustrated
Figure.In the present embodiment, the recommendation apparatus of the product bag also include：
Message pushes processing module 410, for the relevant information of product bag to be pushed in the form of a message into machine top
Box；And by message push time point carry out after hashed, according to configuration push strategy,
Message push is carried out after set-top-box opening.
In the present embodiment, because TV programme or user behavior change will cause programme content to be recommended
Change, thus in requisition for the recommendation updated to product bag, therefore, message is preferably adopted in the present embodiment
The mode of push, carries out the transmission of the recommendation message of product bag.
In the present embodiment, processing module 410 is pushed by the relevant information of product bag with message shape by message
Formula pushes to Set Top Box.Additionally, to prevent the concurrency moment of EPG system from leaping high, being pushed by message
The time point that message is pushed is carried out hashed by processing module 410, and according to the push strategy of configuration,
Message push is carried out after set-top-box opening, such as, message push is carried out according to the renewal time of product bag,
Or fixed intervals duration carries out periodic message push etc..
With reference to Figure 12, Figure 12 is the high-level schematic functional block diagram of the embodiment of commending system one of product bag of the present invention.
In the present embodiment, the commending system of the product bag includes recommendation apparatus 510, the big data platform of product bag
520 and Set Top Box 530.
Wherein, big data platform 520 is gone forward side by side for gathering the user behavior data preserved on Set Top Box 530
Row statistical analysis is processed；Set Top Box 530 is used to provide what the recommendation apparatus 510 for showing product bag were pushed
The interface of the relevant information of product bag to be recommended and user interface, it is concrete such as Fig. 2,3,5,7
It is shown.
In the present embodiment, the commending system of product bag includes the recommendation apparatus 510 of product bag, big data platform
520 and Set Top Box 530.Set Top Box 530 provides a series of user-friendly interface and fills with business support
The recommendation apparatus 510 for putting product bag are interacted, while big data platform 520 gathers user data, divides
The behavior of analysis user, so as to provide gross data for the recommendation apparatus 510 of product bag, and then improves to producing
The generation of product bag and the accuracy and accuracy recommended.
Need it is further noted that product bag recommendation apparatus 510 can be a single device,
Can also be disposed in EPG system, the present invention is preferably arranged at the recommendation apparatus 510 of product bag
In EPG system, namely the EPG system in the present invention has generation and the recommendation function of product bag, such as schemes
Shown in 13, big data platform obtains the user behavior data preserved on Set Top Box, and is carried out by internet
Cloud process, the result after then cloud is processed again is sent to EPG system for generating corresponding product bag；
EPG system again sends the relevant information of the product bag of generation to Set Top Box, while EPG system is also automatic
Obtain the related data of user operation on Set Top Box, such as user to the scoring of product bag, evaluate and use
The selection operation at family etc..
The preferred embodiments of the present invention are these are only, the scope of the claims of the present invention is not thereby limited, it is every
The equivalent structure made using description of the invention and accompanying drawing content or equivalent flow conversion, or directly or
Connect and be used in other related technical fields, be included within the scope of the present invention.
Claims (10)
1. a kind of recommendation method of product bag, it is characterised in that the recommendation method of the product bag includes：
Obtaining big data platform carries out user behavior data resulting after statistical analysis；
According to the user behavior data and default proposed algorithm that get, suitable recommendation is calculated
To the program set of user；
The program for meeting default program conditions is selected from the program set, according to default product Bao Sheng
Into form and selected program, product bag to be recommended is generated；
The relevant information of the product bag to be recommended is pushed to Set Top Box to carry out the recommendation of product bag.
2. the recommendation method of product bag as claimed in claim 1, it is characterised in that the proposed algorithm
At least include：Collaborative filtering based on user and/or the collaborative filtering based on program；The section
Mesh condition at least includes：Program on-line time and/or play-on-demand program temperature.
3. the recommendation method of product bag as claimed in claim 2, it is characterised in that the product bag
Recommendation method also includes：
Obtain scoring of some users for identical product bag；
According to default statistic algorithm, the TOP SCORES of Related product bag is calculated；
The relevant information for meeting the product bag of default scoring condition is pushed to respective set-top box to recommend phase
Using family.
4. the recommendation method of the product bag as any one of claim 1-3, it is characterised in that institute
Stating the recommendation method of product bag also includes：
Obtain product bag and corresponding groups of users or good friend that user shares recommendation；
The relevant information that user is shared the product bag of recommendation pushes to corresponding groups of users or good friend
Set Top Box is recommending relative users.
5. a kind of recommendation apparatus of product bag, it is characterised in that the recommendation apparatus of the product bag include：
Behavioral data acquisition module, for obtaining big data platform user resulting after statistical analysis is carried out
Behavioral data；
Program set calculation module, for according to the user behavior data and default recommendation for getting
Algorithm, is calculated and is adapted to the program set for recommending user；
Product bag generation module, for selecting to meet the program of default program conditions from the program set,
Form and selected program are generated according to default product bag, product bag to be recommended is generated；
The recommending module of product bag first, for the relevant information of the product bag to be recommended to be pushed to into machine
Top box is carrying out the recommendation of product bag.
6. recommendation apparatus of product bag as claimed in claim 5, it is characterised in that the proposed algorithm
At least include：Collaborative filtering based on user and/or the collaborative filtering based on program；The section
Mesh condition at least includes：Program on-line time and/or play-on-demand program temperature.
7. recommendation apparatus of product bag as claimed in claim 6, it is characterised in that the product bag
Recommendation apparatus also include：
Scoring acquisition module, for obtaining scoring of some users for identical product bag；
TOP SCORES computing module, for according to default statistic algorithm, being calculated Related product bag
TOP SCORES；
The recommending module of product bag second, the relevant information for the product bag by default scoring condition is met is pushed away
Deliver to respective set-top box to recommend relative users.
8. recommendation apparatus of the product bag as any one of claim 5-7, it is characterised in that institute
Stating the recommendation apparatus of product bag also includes：
Sharing data acquisition module, for obtaining user the product bag of recommendation and corresponding user are shared
Group or good friend；
The recommending module of product bag the 3rd, pushes for user to be shared the relevant information of product bag of recommendation
To the Set Top Box of corresponding groups of users or good friend recommending relative users.
9. recommendation apparatus of product bag as claimed in claim 8, it is characterised in that the product bag
Recommendation apparatus also include：
Message pushes processing module, for the relevant information of product bag to be pushed in the form of a message into Set Top Box；
And the time point that message is pushed is carried out after hashed, according to the push strategy of configuration, on machine top
Message push is carried out after box start.
10. a kind of commending system of product bag, it is characterised in that the commending system of the product bag includes
The recommendation apparatus of the product bag any one of claim 5-9；The commending system of the product bag is also wrapped
Include big data platform and Set Top Box；
The big data platform is used to gather the user behavior data of the set top box side and carry out statistical analysis
Process；
The Set Top Box is used to provide the product to be recommended for showing that the recommendation apparatus of the product bag are pushed
The interface of the relevant information of bag and user interface.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510698000.8A CN106612461A (en) | 2015-10-23 | 2015-10-23 | A recommendation method, apparatus and system for a product package |
| PCT/CN2016/103081 WO2017067525A1 (en) | 2015-10-23 | 2016-10-24 | Product package recommendation method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510698000.8A CN106612461A (en) | 2015-10-23 | 2015-10-23 | A recommendation method, apparatus and system for a product package |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106612461A true CN106612461A (en) | 2017-05-03 |
Family
ID=58556657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510698000.8A Pending CN106612461A (en) | 2015-10-23 | 2015-10-23 | A recommendation method, apparatus and system for a product package |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106612461A (en) |
| WO (1) | WO2017067525A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107831963A (en) * | 2017-08-17 | 2018-03-23 | 平安科技（深圳）有限公司 | Financial product display methods, device, equipment and storage medium |
| CN109121006A (en) * | 2018-08-02 | 2019-01-01 | 中国联合网络通信集团有限公司 | A kind of marketing method and platform based on live streaming viewing user |
| WO2019006757A1 (en) * | 2017-07-07 | 2019-01-10 | Arris Enterprises Llc | Method for providing reminders based on viewing history information |
| CN109583937A (en) * | 2018-10-26 | 2019-04-05 | 平安科技（深圳）有限公司 | A kind of Products Show method and apparatus |
| CN114513700A (en) * | 2020-11-16 | 2022-05-17 | 中国移动通信集团有限公司 | Method, device and equipment for recommending video and storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110913249B (en) * | 2018-09-18 | 2023-07-21 | 深圳市茁壮网络股份有限公司 | Program recommendation method and system |
| CN109840800A (en) * | 2018-12-14 | 2019-06-04 | 深圳壹账通智能科技有限公司 | A kind of Products Show method, apparatus, storage medium and server based on integral |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101141607A (en) * | 2006-09-08 | 2008-03-12 | 百视通网络电视技术发展有限责任公司 | Mutual correlation method for IPTV and implementing system thereof |
| CN101482884A (en) * | 2009-01-21 | 2009-07-15 | 华东师范大学 | Cooperation recommending system based on user predilection grade distribution |
| KR20120003362A (en) * | 2010-07-02 | 2012-01-10 | 아코지토(주) | Recommendation system on personalized favorite programs/channels for internet protocol tv users by using collaborative filtering algorithm |
| CN102164315B (en) * | 2011-02-14 | 2014-01-01 | 深圳市龙视传媒有限公司 | Network personal video recording data recommending method and system in digital television |
| CN102780920A (en) * | 2011-07-05 | 2012-11-14 | 上海奂讯通信安装工程有限公司 | Television program recommending method and system |
-
2015
- 2015-10-23 CN CN201510698000.8A patent/CN106612461A/en active Pending
-
2016
- 2016-10-24 WO PCT/CN2016/103081 patent/WO2017067525A1/en active Application Filing
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019006757A1 (en) * | 2017-07-07 | 2019-01-10 | Arris Enterprises Llc | Method for providing reminders based on viewing history information |
| CN107831963A (en) * | 2017-08-17 | 2018-03-23 | 平安科技（深圳）有限公司 | Financial product display methods, device, equipment and storage medium |
| CN109121006A (en) * | 2018-08-02 | 2019-01-01 | 中国联合网络通信集团有限公司 | A kind of marketing method and platform based on live streaming viewing user |
| CN109121006B (en) * | 2018-08-02 | 2021-02-02 | 中国联合网络通信集团有限公司 | Marketing method and platform based on live broadcast watching user |
| CN109583937A (en) * | 2018-10-26 | 2019-04-05 | 平安科技（深圳）有限公司 | A kind of Products Show method and apparatus |
| CN114513700A (en) * | 2020-11-16 | 2022-05-17 | 中国移动通信集团有限公司 | Method, device and equipment for recommending video and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017067525A1 (en) | 2017-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106612461A (en) | A recommendation method, apparatus and system for a product package | |
| US9235574B2 (en) | Systems and methods for providing media recommendations | |
| Acikgoz et al. | The influence of'influencer marketing'on YouTube influencers | |
| US8151194B1 (en) | Visual presentation of video usage statistics | |
| US9473730B1 (en) | Method and system for personalized recommendation modeling | |
| US8799936B2 (en) | Cooperative filtering algorithm-based personal preference program recommendation system for IPTV | |
| US20150067061A1 (en) | Systems and methods for predicting and characterizing social media effectiveness | |
| CN103649981B (en) | Method and apparatus for delivering targeted content | |
| CN107205178A (en) | Direct broadcasting room recommends method and device | |
| US20110288912A1 (en) | Content Recommendation System | |
| JP2017045466A (en) | Media asset usage data reporting that indicates corresponding content creator | |
| JP2009536413A (en) | Fuzzy logic based viewer identification for targeted asset delivery system | |
| CN1352776A (en) | Smart agent based on habit, statistical inference and psycho-demographic profiling | |
| WO2013184875A2 (en) | Systems and methods for compiling media information based on privacy and reliability metrics | |
| CN101764661A (en) | Data fusion based video program recommendation system | |
| EP2735140A1 (en) | Method and apparatus for delivering targeted content to television viewers | |
| US20140006150A1 (en) | Systems and methods for targeting advertisements based on product lifetimes | |
| JP2011039909A (en) | Method and system for optimizing presentation information | |
| EP1891588A1 (en) | Method and apparatus for estimating total interest of a group of users directing to a content | |
| CA2774075A1 (en) | Synthesizing messaging using context provided by consumers | |
| CN101088288A (en) | Method and device for commending contents | |
| CN111435371B (en) | Video recommendation method and system, computer program product and readable storage medium | |
| Fudurić et al. | Understanding the drivers of cable TV cord shaving with big data | |
| An et al. | Validating social media data for automatic persona generation | |
| Kui et al. | Tvseer: A visual analytics system for television ratings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170503 |
|
| WD01 | Invention patent application deemed withdrawn after publication |