CN101107852A - Method and device for acquiring a common interest-degree of a user group - Google Patents
Method and device for acquiring a common interest-degree of a user group Download PDFInfo
- Publication number
- CN101107852A CN101107852A CNA2006800027845A CN200680002784A CN101107852A CN 101107852 A CN101107852 A CN 101107852A CN A2006800027845 A CNA2006800027845 A CN A2006800027845A CN 200680002784 A CN200680002784 A CN 200680002784A CN 101107852 A CN101107852 A CN 101107852A
- Authority
- CN
- China
- Prior art keywords
- user
- program
- customer group
- weight
- content characteristic
- 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
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
A method of acquiring a common interest- degree of a user group for a program, wherein each user of the user group corresponds to a user profile, and the method includes the following steps: receiving a program, which contains at least one content feature; acquiring like-degree, compromise-index and user weight of the user for the said content feature from the user profile; adjusting the user's like-degree for the content feature, with combination of user weight and comprise-degree of each user; acquiring the common interest-degree of the user group for the program according to the adjusted like-degree. In this invention, the compromise indexes of the various users, who are watching certain program, are adopted to adjust the corresponding user weights, so as to acquire the common interest-degree of the user group more accurately and comprehensively.
Description
Technical background
The present invention relates to a kind of method and device that obtains the user interest degree, relate in particular to a kind of method and device that obtains a customer group common interest-degree, and according to method and the device of this common interest-degree to this customer group recommendation information.
Along with the development of modern communication technology, people can obtain bulk information at any time.Yet the rapid increase of amount of information makes people often at a loss as to what to do, and people press for a kind of device that obtains the user interest degree, recommends its information of interest with the interest-degree according to the user to the user.
Being used for obtaining the method and the device of user interest degree at present, being generally used for obtaining the interest-degree of unique user to a program, is not a lot of and be used to obtain customer group (comprising at least two users) to the method and the device of the common interest-degree of a program.
But, in one family or a dormitory, generally include a customer group, and they can watch program the most of the time together.For example comprise father, mother and child in the one family; everyone has the interest of oneself; when selecting the program of watching jointly; rob remote controller through regular meeting; even phenomenon such as quarrel; so more need a kind of method and device that obtains the common interest-degree of a customer group, to recommend them to be total to programs of interest to these users.
Existing obtain customer group and normally utilize the user's weight of each user in the customer group that corresponding fancy grade adjustment is obtained the method for a program common interest-degree.
Wherein, this user's weight is meant the importance of each user in customer group, and some user relatively carries weight, and user's weight is bigger, and some user does not have authority in this customer group, and user's weight is then smaller etc.
(the application people is KONINKIJKEPHILIPS ELECTRONICS N.V. as International Patent Application PCT/IB02/01034, international filing date is 2002 03 month 28, and priority date is 03 month 28 days calendar year 2001) just mentioned the above-mentioned user's of utilization weight fancy grade adjustment has been obtained the method for customer group to the common interest-degree of a program.
Yet, in the above-mentioned international patent application each user to be used for adjusting its user's weight to the fancy grade of all programs all be identical, do not consider for different programs, each user's team spirit is to the influence of relative users weight in the customer group, wherein this team spirit is meant that each user in the customer group (or all) may compromise because of team spirit for specific program, thereby decision other users in customer group watch or do not watch together.
In sum, utilize the changeless user's weight of each user to adjust its fancy grade at present to a program, and then obtain the method for a customer group to the common interest-degree of this program, can't obtain the common interest-degree of customer group very accurately, all sidedly to program.
Therefore, the invention provides a kind of method and device that obtains the customer group common interest-degree, so that more comprehensively, recommend their common information of interest to customer group exactly.
Summary of the invention
One of purpose of the present invention is in order to obtain the common interest-degree of customer group to program more exactly, thus the program of recommending them to like jointly to this customer group more accurately.
An aspect of of the present present invention provides a kind of method that obtains a customer group to a program common interest-degree, the corresponding files on each of customers of each user in this customer group, the method comprising the steps of: receive a program, comprise at least one content characteristic in this program; From described each user's files on each of customers, obtain fancy grade, compromise index and the user weight of this user to described content characteristic; User's weight and compromise index in conjunction with each user are adjusted the fancy grade of this user to described content characteristic; With obtain the common interest-degree of this customer group to this program according to adjusted fancy grade.
In one embodiment of the present of invention, described compromise index is used to show the overall interests for this customer group, and the attitude at described content characteristic that each user adopted in the described customer group comprises compromise, uncompromising and do not mind.
During of the present invention another implemented, described adjustment process in conjunction with compromise index and user's weight comprised step: according to described compromise index described user's weight is adjusted, to obtain adjusted user's weight; And adjust described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
Among the present invention, utilize the compromise index of each user in the customer group of watching program to adjust corresponding user's weight, not only considered each user's team spirit in the customer group (the compromise index of each user in customer group), but also watch under the situation of program non-all initial user groups, redistributed user's weight of just watching the program customer group, so that be more accurate, the comprehensive common interest-degree of this customer group acquisition.
Another aspect of the present invention provides a kind of to a method that customer group is programs recommended, the corresponding files on each of customers of each user in this customer group, and the method comprising the steps of: receive a program, comprise at least one content characteristic in this program; From described each user's files on each of customers, obtain fancy grade, compromise index and the user weight of this user to described content characteristic; User's weight and compromise index in conjunction with each user are adjusted the fancy grade of this user to described content characteristic; Obtain the common interest-degree of this customer group according to adjusted fancy grade to this program; Determine whether to recommend this program according to the common interest-degree of this customer group to this customer group to this program.
In one embodiment of the present of invention, described compromise index is used to show the overall interests for this customer group, and the attitude at described content characteristic that each user adopted in the described customer group comprises compromise, uncompromising and do not mind.
During of the present invention another implemented, described adjustment process in conjunction with compromise index and user's weight comprised step: according to described compromise index described user's weight is adjusted, to obtain adjusted user's weight; And adjust described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
Another aspect of the present invention is to carry a kind of device that obtains a customer group to the interest-degree of a program, the corresponding files on each of customers of each user in this customer group, this device comprises a receiving system, a deriving means, an adjusting device and a common interest analytical equipment.Wherein, this receiving system is used for receiving a program, comprises at least one content characteristic in this program; This deriving means is used for obtaining fancy grade, compromise index and the user weight of this user to described content characteristic from described each user's files on each of customers; This adjusting device is used for adjusting the fancy grade of this user to described content characteristic in conjunction with each user's user's weight and compromise index; This common interest analytical equipment is used for obtaining the common interest-degree of this customer group to this program according to adjusted fancy grade.
In the enforcement of the present invention, this adjusting device comprises one first adjusting device and one second adjusting device.Wherein, first adjusting device is used for according to described compromise index described user's weight being adjusted, to obtain adjusted user's weight; This second adjusting device is used for adjusting described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
The device of a kind of recommendation information that provide on the one hand more of the present invention to a customer group, the corresponding files on each of customers of each user in this customer group, this device comprises a receiving system, a deriving means, an adjusting device, a common interest analytical equipment and a recommendation apparatus.Wherein this receiving system is used for receiving a program, comprises at least one content characteristic in this program; This deriving means is used for obtaining fancy grade, compromise index and the user weight of this user to described content characteristic from described each user's files on each of customers; This adjusting device is used for adjusting the fancy grade of this user to described content characteristic in conjunction with each user's user's weight and compromise index; This common interest analytical equipment is used for obtaining the common interest-degree of this customer group to this program according to adjusted fancy grade; This recommendation apparatus is used for determining whether to recommend this program to this customer group according to the common interest-degree of this customer group to this program.
In one embodiment of the present of invention, this adjusting device comprises one first adjusting device and one second adjusting device.Wherein, first adjusting device is used for according to described compromise index described user's weight being adjusted, to obtain adjusted user's weight; This second adjusting device is used for adjusting described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
By following description and the claim that reference is carried out in conjunction with the accompanying drawings, other purpose of the present invention and achievement will be conspicuous, and the present invention is also had more comprehensively understanding.
Description of drawings
The present invention carries out detailed explanation by the mode of example with reference to accompanying drawing, wherein:
Fig. 1 is the structural representation of an information recommendation system according to an embodiment of the invention;
Fig. 2 is the method flow diagram of a recommendation information according to an embodiment of the invention.
In all accompanying drawings, identical reference number is represented similar or identical feature and function.
Embodiment
Fig. 1 is the structural representation of an information recommendation system according to an embodiment of the invention.
This files on each of customers management devices 107 is used for managing each user's of initial user group that at least two users form files on each of customers, as user's 1 archives, user's 2 archives and user N archives etc.Comprise in each files on each of customers that this user represents one or more content characteristic interest, as fancy grade, compromise index and user's weight.Certainly, also whole users among the initial user group can be represented to be placed in the total files on each of customers to the interest of content characteristic, also can be with initial user group's user grouping, the files on each of customers of the corresponding grouping of each group.Certainly, can also be directly at fancy grade, compromise index and the user weight of each user of program settings to this program.
A files on each of customers is corresponding to a user in the present embodiment, and each files on each of customers comprises fancy grade, compromise index and the user weight of this user to content characteristic.
Colony's total number of persons that wherein above-mentioned initial user group sets when referring to the initialization files on each of customers, at least comprise two users, and usually the customer group of indication is meant the customer group of watching program (or the customer group of listening program, or use the customer group of product or content, aftermentioned is example with the TV programme).For example an initial user group comprises 5 users, and the customer group of watching program these 5 users always not sometimes can be 3, and 4,2 etc., still, a customer group comprises at least two users.
Above-mentioned content characteristic is meant the performer that comprises in the program (Fan Bingbing, Pueraria lobota excellent), program category (cartoon, literary film, romance movie, military film etc.), director (Zhang Yimou, Feng Xiaogang etc.) etc., these content characteristics can be from information sources such as broadcasting, TV or internet, the most representatively sends to the user by electronic program guide of digital television (EPG) with program exactly.
Content characteristic in the files on each of customers can be one, as has only certain performer.Certainly, the content characteristic in the files on each of customers also can have a plurality of, and at this moment, corresponding recommendation results will be more accurate.
This fancy grade is meant the sensation of user to each content characteristic, can represent by the fixed number range of user preset, as [0,100].
This compromise index is the overall interests that are used to show for the initial user group, the attitude that each user taked among the initial user group at each content characteristic, to embody the team spirit of each user among the initial user group, promptly be ready to compromise and watch the program that comprises this content characteristic with other members at some member of content characteristic, and at another content characteristic, these members are unwilling to watch the program that comprises this another content characteristic with other members.
This compromise index can oneself be presetted and be revised according to the wish of oneself at any time by each user, also can also watch the historical information of program to revise according to the user at any time by system's automatic setting.As, establish this compromise index and be a value in [0,1,2], wherein 0 expression is compromised, and 1 expression does not mind that 2 expressions are uncompromising.Certainly, this compromise index also can be set at a scope, and as [0,2] etc., each user may set different values in this scope to different content characteristics.
This user's weight is meant the important journey of each user in the initial user group, and some user relatively carries weight, and user's weight is bigger, and some user does not have authority in this customer group, and user's weight is then smaller etc.User's weight of each user is predefined by common negotiation of each member in the customer group, remodifies after also can consulting jointly.
Certainly, above-mentioned user's weight also can not need to revise, because user's weight can be adjusted by the compromise index and change in the present embodiment.Each user may be different to the compromise index of different content feature and may be revised at any time by this user, has also influenced the variation of relative users weight.
In the initial user group, each user's weight sum is 1, and user's weight of watching each user in the customer group of program is in the adjusted user's weight of quilt compromise index and still 1.
Above-mentioned files on each of customers can be filled in and carried out initialization by user oneself.Certainly, this is not unique mode, can obtain files on each of customers by other approach, as by production firm this commending system being carried out the files on each of customers initialization according to user basic information (as sex, the age) yet.
This deriving means 108 is used for obtaining in the customer group each user to the information such as fancy grade, compromise index and user's weight of each content characteristic from this files on each of customers management devices 107.
This adjusting device 109 is used for adjusting the corresponding above-mentioned fancy grade that obtains according to the above-mentioned user's weight obtained and compromise index.
This adjusting device 109 comprises one first adjusting device 1092 and one second adjusting device 1094.Wherein first adjusting device 1092 is to utilize the compromise index to adjust user's weight, and this second adjusting device 1094 is to utilize to be adjusted corresponding fancy grade by the adjusted user's weight of compromise index.
This common interest analytical equipment 110 is used for obtaining the common interest-degree of customer group to a program according to above-mentioned adjusted fancy grade, and judges that whether this common interest-degree is greater than a threshold value.This threshold value can be preestablished jointly by customer group, such as being 60.
This common interest analytical equipment 110 comprises a common fancy grade deriving means 112, a common interest-degree deriving means 114 and a judgment means 116.
This common fancy grade deriving means 112 is used for drawing the common fancy grade of customer group to each content characteristic.Available above-mentioned customer group is used as the common fancy grade of this customer group to this content characteristic to the adjusted fancy grade sum of each content characteristic.
This common interest-degree deriving means 114 is used for according to customer group the common fancy grade of all the elements feature in the program being drawn the common interest-degree of this customer group to this program, with customer group the mean value of the common fancy grade of all the elements feature in this program is used as the common interest-degree of this customer group to this program usually.
Certainly, if have only a content characteristic in this program, then need not to obtain the mean value of customer group, but directly the common fancy grade of this content characteristic is used as the common interest-degree of this customer group to this program with this customer group to the common fancy grade of all the elements feature in this program.
The files on each of customers of present embodiment also can comprise the content weight, and this content weight is meant the user when selecting program, various dissimilar content characteristics, as, performer, director, program category etc. are to the influence of its selection result.What also we can say the user when the program of selecting oneself to like, be standard normally with, promptly still directs according to performer, program category and wait the program of selecting it to like.Wherein all performers' content weight can be the same, and the content weight of all program categories can be the same, and all directors' content weight also can be the same.Described content weight also can preset a number range by supplier, as [0,50].
Present embodiment also can draw the common interest-degree of customer group in conjunction with foregoing weight and fancy grade.
This judgment means 116 be used for judging the customer group that drawn to the common interest-degree of above-mentioned program whether greater than above-mentioned threshold value.If greater than this threshold value, then recommend this program to give this customer group; If be less than or equal to this threshold value, then do not recommend this program to give this customer group.
This system 100 also comprises a programme information receiving system 101, recommendation apparatus 102, interactive device 103, a feedback information processing unit 104 and a correcting device 106.
Wherein this programme information receiving system 101 is used for program receiving information and with the corresponding electronic program guide of digital television of program (EPG) etc.
This recommendation apparatus 102 is used for providing a recommendation list according to the judged result of programme information that is received and common interest-degree analytical equipment 110 to customer group, comprises the program that customer group may be liked in this recommendation list.
This interactive device 103 is used for presenting information such as program or recommendation list and gives the user, also be used for receiving the feedback information of user to institute's recommend programs or the program watched, such as, select to watch a recommended program, do not watch a recommend programs, watch the time span of a program, to the fancy grade and the compromise index of program or content characteristic, revise user's weight etc.
Certainly, this interactive device 103 also can be used to receive the current customer group information about firms of watching program, such as, the user arrives this interactive device 103 by the current user profile of TV of seeing of inputs such as remote controller or camera (not shown), so that knowing the member who has among which initial user group, this system 100 seeing TV, promptly determine current customer group of watching program, so that recommend their common programs of interest to this customer group.
This feedback information processing unit 104 is used for handling the field feedback that interactive device 103 is received, to draw each user's interests change.
This correcting device 106 is used for revising information in each files on each of customers according to user's interests change.
Files on each of customers management devices 107 in the said system 100 can be a memory (as, hard disk), and other each device all can carry out work under a central processing unit (CPU) is supported.
Fig. 2 is that a recommendation information is given the flow chart of the method for customer group according to an embodiment of the invention.The program of following indication can be for video frequency program, also can be audio program, product, content etc., and aftermentioned all is that example is illustrated with the video frequency program.
The first step is set up the files on each of customers (step S210) of each user among the initial user group.Comprise fancy grade, compromise index and the user weight of this user in each files on each of customers at least one content characteristic.Certainly, if each files on each of customers among this initial user group exists, then can save this step.Certainly, can also be directly at fancy grade, compromise index and the user weight of each user of program settings to this program.
A files on each of customers is corresponding to a user in the present embodiment, and each files on each of customers comprises fancy grade, compromise index and the user weight of this user to content characteristic.
Colony's total number of persons that wherein above-mentioned initial user group sets when referring to the initialization files on each of customers comprises two users at least, and the customer group of indication is meant the customer group of watching program usually.For example an initial user group comprises 5 users, and the customer group of watching program these 5 users always not sometimes can be 3,4,2 etc., comprises two users at least in the customer group that is watched program.
Content characteristic in the files on each of customers can be one, as has only certain performer.Certainly, the content characteristic in the files on each of customers also can have a plurality of, and at this moment, corresponding recommendation results will be more accurate.
If in above-mentioned each user's files on each of customers, comprise a series of content characteristic.Each content characteristic comprises a quaternary array (content characteristic term, favorable rating Like-Degree, compromise index Compromise Index, user's weight Individual Weight).Like this, this files on each of customers (User Profile is called for short UP) can be expressed as the vector (t of a quaternary array, ld, ci, iw), if m different content characteristic is arranged in files on each of customers, wherein the user j among n user can be expressed as the interest of these content characteristics:
UP
j＝((t
1，ld
1，ci
1，iw
j)，(t
2，ld
2，ci
2，iw
j)，....(t
i，ld
i，ci
i，iw
j).....，(t
m，ld
m，ci
m，iw
j)) (1)
Here t
iBe a content characteristic, i is content characteristic t
iSequence number, ld
iBe for this content characteristic t
iFancy grade, ci
iBe that user j is to content characteristic t
iThe compromise index, iw
jIt is user's weight of user j.
The scope of supposing the fancy grade in the files on each of customers is [1,100]; The compromise index is [0,1,2], and wherein 0 expression is compromised, and 1 expression does not mind that 2 expressions are uncompromising; Each user's weight sum equals 1.
User's weight sum of all users can not surpass 100% among initial user group.As, an initial user group comprises 4 members, is respectively father, mother, son and daughter.Their user's weight can not be 30%, 30%, 20% and 20%, and these user's weight sums are 100%.
Among the wherein above-mentioned initial user group who comprises father, mother, son and daughter, comprise in each user's the files on each of customers that each user represents the interest of content characteristic performer A and military film:
Father:
Performer A:ld=90; Ci=2; Iw=30% (performer A, 60,1,30%)
Military film: ld=70; Ci=1; Iw=20% (military film, 90,2,30%)
Mother:
Performer A:ld=30; Ci=1; Iw=0.3 (performer A, 80,0,30%)
Military film: ci=0; Ld=20; Iw=0.3 (military film, 30,0,30%)
Son:
Performer A:ld=30; Ci=1; Iw=0.3 (performer A, 50,1,20%)
Military film: ci=0; Ld=20; Iw=0.3 (military film, 70,1,20%)
Daughter:
Performer A:ld=30; Ci=1; Iw=0.3 (performer A, 90,1,30%)
Military film: ci=0; Ld=20; Iw=0.3 (military film, 70,0,20%)
If the user does not set the quaternary array to certain content characteristic, then give tacit consent to ld=0, ci=0, iw are that this user is identical to the iw of other guide feature.
For n user the interest of m content characteristic is represented, also can be represented by form as follows:
Second goes on foot, and determines to watch among the initial user group user (step S215) of program.This step can obtain current customer group of watching program by elements such as remote controller or camera (not shown).
Among for example above-mentioned initial user group who forms by father, mother, son and daughter four, the current customer group of having only 3 users to form of just watching program, father, mother and son.
In the 3rd step, receive a program (step S220).Can comprise at least one content characteristic in this program, be the content characteristic that relates to program category as this programs feature, as military film.
In the 4th step, from each files on each of customers of above-mentioned customer group, obtain fancy grade, compromise index and the user weight (step S230) of this user to a content characteristic in this program.
For example, above-mentionedly form the customer group of watching program by father, mother and son, they are expressed as follows shown in the table 1 interest of 1 pair of military film of content characteristic:
Table 1
In the 5th step, utilize that each user handles the relative users weight the compromise index of this content characteristic in this customer group, to obtain the composite index (step S240) of each user to this content characteristic.
This step specifically can be realized with three processes by following:
(1) earlier with the compromise index and corresponding user multiplied by weight, father: 30%*2=60% of each user to this content characteristic; Mother 30%*0=0; Son 20%*1=20%.
(2) draw summation after multiplying each other again: 60%+0+20%+0=80%
(3) will multiply each other the back each user user's weight divided by above-mentioned summation, to draw adjusted each user's weight, promptly above-mentioned composite index:
User's weight of father becomes: 60%/80%=75%; User's weight of mother becomes: 0/80%=0; User's weight of son becomes: 20%/80%=25%.
Also above-mentioned user can be listed in the table below 2 to fancy grade, compromise index and the above-mentioned composite index of this content characteristic of group's military film:
Table 2
Each user's composite index sum in the above-mentioned table 2, promptly adjusted each user's weight sum also equals 1, has redistributed current user's weight of watching each user of program.
By above-mentioned adjustment, not only considered each user's team spirit in the customer group (the compromise index of each user in customer group), but also watch under the situation of program non-all initial user groups, redistributed user's weight of just watching the program customer group, so that be more accurate, the comprehensive common interest-degree of this customer group acquisition.
In the 6th step, according to each user in this customer group the composite index of this content characteristic is adjusted corresponding fancy grade, to obtain the comprehensive fancy grade (step S250) of each user to this content characteristic.
This process can multiply each other above-mentioned composite index and obtain the comprehensive fancy grade of each user to this military film with corresponding fancy grade, as shown in table 3 below:
Table 3
The 7th step, obtain this customer group to the comprehensive fancy grade of this content characteristic and, to obtain the common fancy grade (step S260) of this customer group to this content characteristic.
This step normally with each user in the above-mentioned table 3 to the comprehensive fancy grade addition of this military film and get, as 67.5+17.5=85, represent that promptly this customer group is 85 to the common fancy grade of this content characteristic.
In the 8th step, judge in this program whether also have other content characteristic, and also do not obtain the common fancy grade (step S265) of this customer group to this other content characteristic.
Through above-mentioned judgement, if do not obtain the content characteristic of common fancy grade in addition, then be back to step S230, and repeat abovementioned steps.
Through above-mentioned judgement, if there is not other content characteristic, then obtain the mean value of customer group, to obtain the common interest-degree (step S270) of this customer group to this program to the common fancy grade of all the elements feature in this program.Certainly, if having only a content characteristic, then need not to average again.
For example, above-mentioned program comprises two content characteristics, and one is military film, and another is performer A.Above-mentioned customer group is 85 to the common fancy grade of military film in the program, and is 56 (not listing the detailed calculated process identical with military film at this) to the common fancy grade of this program performer A.Then this customer group is (56+85)/2=70.5 to the common interest-degree of this program.
The 8th step, judge the above-mentioned customer group that obtains to the common interest-degree of this program whether greater than a threshold value (step S270).
This threshold value can be preestablished by the initial user group, and for example 60.
Through above-mentioned judgement, if the user to the common interest-degree of this program greater than a threshold value, then recommend this program (step S290) to this customer group, afterwards, finish whole recommendation process.
In above-mentioned example, the common interest-degree to this program of this customer group is 70.5＞60, so can recommend this program to this customer group.
Certainly,,, then directly finish whole process, do not recommend this program to give this customer group if the user is not more than this threshold value to the common interest-degree of this program through above-mentioned judgement.
In the present embodiment, utilize the compromise index of each user in the customer group of watching program to adjust corresponding user's weight, not only considered each user's team spirit in the customer group (the compromise index of each user in customer group), but also watch under the situation of program non-all initial user groups, redistributed user's weight of just watching the program customer group, so that be more accurate, the comprehensive common interest-degree of this customer group acquisition.
The foregoing description be in obtaining customer group each user to a program in behind the comprehensive fancy grade of each content characteristic; This customer group of reentrying to the comprehensive fancy grade of this content characteristic and, to draw the common fancy grade of this customer group to this content characteristic; Obtain the mean value of this customer group at last, to draw the common interest-degree of this customer group to this program to the common fancy grade of all the elements feature in this program.Certainly, in the foregoing description,, then need not the process of averaging if having only a content characteristic.
Certainly, also can obtain the common interest-degree of customer group with order as follows to a program: in obtaining customer group each user to a program in behind the comprehensive fancy grade of each content characteristic; Each user is to the mean value (same, as if having only a content characteristic, then to need not the process of averaging) of the comprehensive fancy grade of all the elements feature in this program, to draw the personal interest degree of each user to this program in the customer group of reentrying; Obtain at last each user in this customer group to interest-degree in this program and, to draw the common interest-degree of this customer group to this program.
Also can be with aforesaid composite index replace compromising index and user's weight in the files on each of customers of the present invention, this composite index can be discussed by the initial user group and be set and discuss together at any time modification, automatically adjust this composite index by system again, make the composite index sum of the customer group of watching program equal 1.
Files on each of customers of the present invention also can comprise the content weight, and this content weight is meant the user when selecting program, various dissimilar content characteristics, as, performer, director, program category etc. are to the influence of its selection result.What also we can say the user when the program of selecting oneself to like, be standard normally with, promptly still directs according to performer, program category and wait the program of selecting it to like.Wherein all performers' content weight can be the same, and the content weight of all program categories can be the same, and all directors' content weight also can be the same.Described content weight also can preset a number range by supplier, as [0,50].
The present invention also can adjust the content weight of each user of customer group to content characteristic in conjunction with compromise index and user's weight, and the process of its process and above-mentioned adjustment fancy grade can be the same.Draw the common interest-degree of customer group in conjunction with content weight and fancy grade again to a program.
The method of obtaining the customer group common interest-degree of the present invention, all right other programs of user, product and content etc.
Though through the present invention is described in conjunction with specific embodiments, for the skilled personage in present technique field, will be conspicuous according to manyly substituting of making of narration above, modifications and variations.Therefore, when such substituting, in the spirit and scope that modifications and variations fall into attached claim the time, should being included among the present invention.
Claims (11)
1. method that obtains a customer group to the common interest-degree of a program, the corresponding files on each of customers of each user in this customer group, the method comprising the steps of:
(a) receive a program, comprise at least one content characteristic in this program;
(b) from described each user's files on each of customers, obtain fancy grade, compromise index and the user weight of this user to described content characteristic;
(c) adjust the fancy grade of this user in conjunction with each user's user's weight and compromise index to described content characteristic; With
(d) obtain the common interest-degree of this customer group according to adjusted fancy grade to this program.
2. the method for claim 1, wherein said compromise index is used to show the overall interests for this customer group, the attitude at described content characteristic that each user adopted in the described customer group comprises compromise, uncompromising and do not mind.
3. the method for claim 1, wherein said user's weight is used for showing the importance of each user in this customer group of described customer group.
4. the method for claim 1, wherein step (c) comprises step:
(c1) according to described compromise index described user's weight is adjusted, to obtain adjusted user's weight; With
(c2) adjust described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
5. one kind to a method that customer group is programs recommended, the corresponding files on each of customers of each user in this customer group, and the method comprising the steps of:
(a) receive a program, comprise at least one content characteristic in this program;
(b) from described each user's files on each of customers, obtain fancy grade, compromise index and the user weight of this user to described content characteristic;
(c) adjust the fancy grade of this user in conjunction with each user's user's weight and compromise index to described content characteristic;
(d) obtain the common interest-degree of this customer group according to adjusted fancy grade to this program; With
(e) determine whether to recommend this program according to the common interest-degree of this customer group to this customer group to this program.
6. method as claimed in claim 5, wherein said compromise index is used to show the overall interests for this customer group, the attitude at described content characteristic that each user adopted in the described customer group comprises compromise, uncompromising and do not mind.
7. method as claimed in claim 5, wherein step (c) comprises step:
(c1) according to described compromise index described user's weight is adjusted, to obtain adjusted user's weight; With
(c2) adjust described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
8. device that obtains a customer group to the common interest-degree of a program, the corresponding files on each of customers of each user in this customer group, this device comprises:
A receiving system is used for receiving a program, comprises at least one content characteristic in this program;
A deriving means is used for obtaining fancy grade, compromise index and the user weight of this user to described content characteristic from described each user's files on each of customers;
An adjusting device is used for adjusting the fancy grade of this user to described content characteristic in conjunction with each user's user's weight and compromise index; With
A common interest analytical equipment is used for obtaining the common interest-degree of this customer group to this program according to adjusted fancy grade.
9. device as claimed in claim 8, wherein this adjusting device comprises:
One first adjusting device is used for according to described compromise index described user's weight being adjusted, to obtain adjusted user's weight; With
One second adjusting device is used for adjusting described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
10. a recommendation information is given the device of a customer group, the corresponding files on each of customers of each user in this customer group, and this device comprises:
A receiving system is used for receiving a program, comprises at least one content characteristic in this program;
A deriving means is used for obtaining fancy grade, compromise index and the user weight of this user to described content characteristic from described each user's files on each of customers;
An adjusting device is used for adjusting the fancy grade of this user to described content characteristic in conjunction with each user's user's weight and compromise index;
A common interest analytical equipment is used for obtaining the common interest-degree of this customer group to this program according to adjusted fancy grade; With
A recommendation apparatus is used for determining whether to recommend this program to this customer group according to the common interest-degree of this customer group to this program.
11. device as claimed in claim 10, wherein this adjusting device comprises:
One first adjusting device is used for according to described compromise index described user's weight being adjusted, to obtain adjusted user's weight; With
One second adjusting device is used for adjusting described fancy grade according to described adjusted user's weight, to obtain the fancy grade of described adjusted each user to described content characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006800027845A CN101107852A (en) | 2005-01-21 | 2006-01-13 | Method and device for acquiring a common interest-degree of a user group |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200510006216.X | 2005-01-21 | ||
| CN200510006216 | 2005-01-21 | ||
| CNA2006800027845A CN101107852A (en) | 2005-01-21 | 2006-01-13 | Method and device for acquiring a common interest-degree of a user group |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101107852A true CN101107852A (en) | 2008-01-16 |
Family
ID=39000657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006800027845A Pending CN101107852A (en) | 2005-01-21 | 2006-01-13 | Method and device for acquiring a common interest-degree of a user group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101107852A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056463A1 (en) * | 2010-10-29 | 2012-05-03 | Hewlett-Packard Development Company, L.P. | Content recommendation for groups |
| CN103546778A (en) * | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN104869131A (en) * | 2014-02-21 | 2015-08-26 | 冠捷投资有限公司 | Multi-electronic-device interaction method based on user's intention and system thereof |
| CN105574015A (en) * | 2014-10-13 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Search recommendation method and device |
| CN110147481A (en) * | 2017-08-24 | 2019-08-20 | 腾讯科技（北京）有限公司 | Media content method for pushing, device and storage medium |
-
2006
- 2006-01-13 CN CNA2006800027845A patent/CN101107852A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056463A1 (en) * | 2010-10-29 | 2012-05-03 | Hewlett-Packard Development Company, L.P. | Content recommendation for groups |
| US9311308B2 (en) | 2010-10-29 | 2016-04-12 | Hewlett-Packard Development Company, L.P. | Content recommendation for groups |
| CN103546778A (en) * | 2013-07-17 | 2014-01-29 | Tcl集团股份有限公司 | Television program recommendation method and system, and implementation method of system |
| CN104869131A (en) * | 2014-02-21 | 2015-08-26 | 冠捷投资有限公司 | Multi-electronic-device interaction method based on user's intention and system thereof |
| CN104869131B (en) * | 2014-02-21 | 2018-04-13 | 冠捷投资有限公司 | Multiple electronic device interactive approaches and its system based on user's purpose |
| CN105574015A (en) * | 2014-10-13 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Search recommendation method and device |
| CN110147481A (en) * | 2017-08-24 | 2019-08-20 | 腾讯科技（北京）有限公司 | Media content method for pushing, device and storage medium |
| CN110147481B (en) * | 2017-08-24 | 2023-03-17 | 腾讯科技（北京）有限公司 | Media content pushing method and device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8789106B2 (en) | Channel contract proposing apparatus, method, program and integrated circuit | |
| JP2006509399A (en) | Recommend video content based on user profiles of users with similar viewing habits | |
| KR20070099654A (en) | Method and apparatus for acquiring a common interest-degree of a user group | |
| CN100499760C (en) | Method and apparatus for generating recommendation scores using implicit and explicit viewing preference | |
| US8626587B2 (en) | Artificial intelligence-based recommender and self-provisioner | |
| US20060026642A1 (en) | Method and apparatus for predicting a number of individuals interested in an item based on recommendations of such item | |
| US20010039657A1 (en) | Methods, systems and devices for selectively presenting and sorting data content | |
| WO2001015449A1 (en) | Method and apparatus for creating recommendations from users profile built interactively | |
| GB2358263A (en) | Generating user profile data | |
| US20090138326A1 (en) | Apparatus and method for updating user profile | |
| US20140136621A1 (en) | Automatic determination of genre-specific relevance of recommendations in a social network | |
| CA2700955A1 (en) | Social network based recommendation method and system | |
| CN101107852A (en) | Method and device for acquiring a common interest-degree of a user group | |
| US20050171924A1 (en) | System for recommending program information in accordance with user preferences | |
| CN101088288A (en) | Method and device for commending contents | |
| US20030229896A1 (en) | Decision fusion of recommender scores through fuzzy aggregation connectives | |
| US20110041157A1 (en) | Systems and Methods for Selecting Content For a Subscriber of a Content Service Provider | |
| KR101772404B1 (en) | Method and apparatus of enhancing accuracy of inferencing contents preference of viewer | |
| JP6641204B2 (en) | Program recommendation device, program recommendation method, and program recommendation program | |
| KR20120127031A (en) | Method for Recommending Contents Based on User Watch History | |
| KR101271237B1 (en) | System and Method for providing customized custom-view | |
| JP4006773B2 (en) | Information distribution apparatus and information distribution method | |
| CN103782296B (en) | The method and apparatus for generating list of ranked items | |
| US20110029996A1 (en) | System for and method of analysing the consumption of transmitted audio visual content | |
| EP1117056A2 (en) | Method and apparatus for generating profile data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: PACE MICRO TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: KONINKLIJKE PHILIPS ELECTRONICS N.V. Effective date: 20080808 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20080808 Address after: West Yorkshire Applicant after: Koninkl Philips Electronics NV Address before: Holland Ian Deho Finn Applicant before: Koninklijke Philips Electronics N.V. |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20080116 |