CN109561350A - The evaluation method and system of user interest degree - Google Patents
The evaluation method and system of user interest degree Download PDFInfo
- Publication number
- CN109561350A CN109561350A CN201710888524.2A CN201710888524A CN109561350A CN 109561350 A CN109561350 A CN 109561350A CN 201710888524 A CN201710888524 A CN 201710888524A CN 109561350 A CN109561350 A CN 109561350A
- Authority
- CN
- China
- Prior art keywords
- program
- label
- user
- index parameter
- under
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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]
- H04N21/40—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
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
-
- 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
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, 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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of evaluation method of user interest degree and systems, and by establishing interest tags library, interest tags library includes each program parameter under program label and program label;Program index parameter of the user on each program label is calculated based on program label;Program index parameter of the normalized active user under each program label not relative value relative to whole users, obtains the corresponding normalized value of each program index parameter;The corresponding normalized value of each program index parameter under the corresponding each program label of weighted calculation active user, obtains active user to the interest-degree of the corresponding program of each program label.By method disclosed above, the calculating for interest-degree is obtained based on the program index parameter on the program label pre-established, and process is succinct.Therefore, the evaluation method of user interest degree disclosed by the invention can fast and accurately obtain user to the interest-degree of each program label.
Description
Technical field
The present invention relates to New Media Technology fields, a kind of evaluation method more specifically to user interest degree and are
System.
Background technique
With the fast development of new media industry, doing different push for different user's portraits, to have become its important
One of business.Wherein, the rating preference of user is that it carries out important component during user's portrait again.The rating of user
Preference mainly passes through user interest degree and is measured.User interest degree then refers to user to the interested degree of each interest tags.
Calculating for user interest degree is based primarily upon topic model to different user in different periods in the prior art
The probability value of viewing interests preference is calculated.The topic model mainly realizes the meter to user interest degree by trained mode
It calculates.But topic model is when calculating user interest degree, complexity is high, poor universality, and the theme that trains of topic model compared with
Be it is abstract, it is explanatory not strong, and there is also certain differences between different themes model.Therefore, it is used based on the prior art
Not only process is complicated for family interest-degree, and inaccuracy.
Summary of the invention
In view of this, quickly obtaining standard this application provides a kind of evaluation method of user interest degree and system to realize
The purpose of true user interest degree.
To achieve the goals above, it is proposed that scheme it is as follows:
First aspect present invention discloses a kind of evaluation method of user interest degree, comprising:
Interest tags library is established, the interest tags library includes each section under program label and the program label
Mesh parameter, the program label include program generic;
Program index parameter of the user on each program label is calculated based on the program label;
Program index parameter of the presently described user of normalized under each program label is relative to whole use
The relative value at family obtains the corresponding normalized value of each program index parameter;
Each program index parameter pair under the corresponding each program label of the presently described user of weighted calculation
The normalized value answered obtains presently described user to the interest-degree of the corresponding program of each program label.
Preferably, the program parameter includes at least: the duration of programm name and program itself;
The program generic includes at least: the classification according to division of teaching contents and/or the class according to the division of program subject matter
Not, the classification according to division of teaching contents includes: plot, comedy or reality TV show, the classification packet divided according to program subject matter
It includes: TV play, film or variety.
Preferably, the program index parameter includes: rating duration, watches completion rate, number of programs and watch number of days.
Preferably, if the program index parameter includes rating duration, user is calculated each based on the program label
Program index parameter on program label, comprising:
Determine each program label;
Obtain the duration for the program that the user watches under each program label
Wherein, tiIndicate that the user watches the duration of the program under actual program label every time, i and n indicate the use
The number that family is watched under certain label, i are more than or equal to 1, n and are greater than i.
Preferably, if the program index parameter includes: to watch completion rate, based on the program label calculate for
Program index parameter on each program label, comprising:
Determine each program label;
Obtain the number that the user watches each program under the program label, each time watch duration and each
The original duration of program, obtains watching completion rate
Wherein, tiIndicate that the user watches the duration of the program under actual program label every time, i and n indicate the use
The number that family is watched under certain label, i are more than or equal to 1, n and are greater than i, piIndicate that user watches the section under actual program label every time
Purpose predicts playing duration.
Preferably, normalized active user is in the program index parameter of each program label relative to complete
The relative value of portion user obtains corresponding normalized value, comprising:
Obtain the number for watching the corresponding whole users of program under each program label and each program label
Under the corresponding program index parameter of each user;
Determine presently described user each program label the program index parameter relative to whole users'
Relative value;
Based on the normalized calculation method of max min and the corresponding program index parameter of each user, obtain
Presently described user watches number of days relative to the opposite of whole users in the program index parameter of each program label
Value, using obtained each relative value as the normalized value of the program index parameter under respective corresponding program label.
Preferably, if the program index parameter includes: rating duration, watches completion rate, number of programs and watch number of days;
The then corresponding normalizing of each program index parameter under the corresponding each program label of the presently described user of the weighted calculation
Change value obtains presently described user to the interest-degree of the corresponding program of each program label, comprising:
It obtains each rating duration under the corresponding each program label of presently described user, described watch completion
Rate, the number of programs and described watch the corresponding normalized value of number of days;
For each program label, it is based on H=aT '+bP '+cR '+dD ', obtains presently described user to each institute
State the interest-degree H of the corresponding program of program label, wherein T ' is the corresponding normalization of rating duration described under actual program label
Value, P ' are the corresponding normalized value of number of programs described under actual program label, and R ' watches completion to be described under actual program label
The corresponding normalized value of rate, D ' watch the corresponding normalized value of number of days to be described under actual program label, and a, b, c, d are to divide in advance
The weighted value matched, and a+b+c+d=1.
Second aspect of the present invention discloses a kind of evaluation system of user interest degree, comprising:
Pretreatment unit, for establishing interest tags library, the interest tags library includes program label and the program
Each program parameter under label, the program label include program generic;
Indicator calculating unit, for calculating program index ginseng of the user on each program label based on the program label
Number;
Normalized unit refers to for program of the presently described user of normalized under each program label
Relative value of the parameter relative to whole users is marked, the corresponding normalized value of each program index parameter is obtained;
Interest-degree computing unit, for each under the corresponding each program label of the presently described user of weighted calculation
The corresponding normalized value of the program index parameter obtains presently described user to the corresponding program of each program label
Interest-degree.
Third aspect present invention discloses a kind of storage medium, and the storage medium includes the program of storage, wherein in institute
Equipment where controlling the storage medium when stating program operation executes commenting for the user interest degree as disclosed in first aspect present invention
Valence method.
Fourth aspect present invention discloses a kind of processor, and the processor is for running program, wherein described program fortune
The evaluation method of the user interest degree as disclosed in first aspect present invention is executed when row.
As can be seen from the above technical solutions, the present invention discloses the evaluation method and system of a kind of user interest degree, by building
Vertical interest tags library, interest tags library includes each program parameter under program label and program label, and program label includes
Program generic;Program index parameter of the user on each program label is calculated based on program label;Normalized is current
Program index parameter of the user under each program label not relative value relative to whole users obtains each program index ginseng
The corresponding normalized value of number;Each program index parameter under the corresponding each program label of weighted calculation active user is corresponding
Normalized value obtains active user to the interest-degree of the corresponding program of each program label.Pass through user interest disclosed above
The evaluation method of degree, obtained interest-degree approximate Gaussian distributed on number of users, and the size of obtained interest-degree can be with
True reflection user is to the interest-degree of the program under the program label, and above-mentioned calculating is based on the program label pre-established
Program index parameter obtain, process is succinct.Therefore, the evaluation method of user interest degree disclosed by the invention can be quick
And user is accurately obtained to the interest-degree of each program label.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow diagram of the evaluation method of user interest degree disclosed by the embodiments of the present invention;
Fig. 2 is the flow diagram of normalized disclosed by the embodiments of the present invention;
Fig. 3 is a kind of structural schematic diagram of the evaluation system of user interest degree disclosed by the embodiments of the present invention;
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
It can be seen from background technology that in the prior art, it is emerging in different periods rating to different user to be based primarily upon topic model
The probability value of interesting preference is calculated.But topic model, when calculating user interest degree, complexity is high, poor universality, and main
It is more abstract to inscribe the theme that model training goes out, it is explanatory not strong, there is also certain difference between different themes model, cause to obtain
Obtaining user interest degree, not only process is complicated, and inaccuracy.Therefore, the invention discloses a kind of evaluation method of user interest degree,
To realize the purpose for quickly obtaining accurate user interest degree.
As shown in Figure 1, being a kind of flow diagram of the evaluation method of user interest degree disclosed by the embodiments of the present invention.
Step S101: establishing interest tags library, and the interest tags library includes under program label and the program label
Each program parameter, the program label includes program generic.
Execute during step S101 establishes interest tags library, mainly according to program generic to each program into
Row classification, and establish corresponding program label.It and include each program parameter under the program label after division.
It should be noted that program generic refers to according to the classification of division of teaching contents and/or according to the division of program subject matter
Classification, the classification according to division of teaching contents include: plot, comedy or reality TV show, the classification divided according to program subject matter
It include: TV play, film or variety.Certainly, the embodiment of the present invention is not limited in content included in above-mentioned classification,
It can also include such as parent-offspring's class according to the classification of division of teaching contents, educational.It is gone back in the classification such as divided according to program subject matter
It may include animation, music etc..
Further, the embodiment of the present invention is not limited in program generic above several, can also include it
His classification etc. includes: such as short-sighted frequency and long video according to the classification that program duration divides.
It should be noted that program parameter includes the duration of programm name and program itself.Further, can also include
What user watched the program every time watches duration, period etc. content.
Preferably, the interest tags library based on program label building, can be by arriving the label mapping of existing program
In constructed interest tags library.
It should be noted that may include multiple program generics in each program parameter, constructed interest mark
The corresponding relationship in library is signed, such as: the name of the people: TV play/plot;I is singer: variety/select-elite etc..
Step S102: program index parameter of the user on each program label is calculated based on the program label.
When executing step S102 and carrying out the calculating of program index parameter, the program that can calculate in embodiments of the present invention
Index parameter can be configured in advance.The program index parameter include: rating duration, watch completion rate, number of programs and
Watch number of days etc., but the embodiment of the present invention, which does not limit, only has above four kinds of program index parameters.
It should be noted that at least needing to calculate above-mentioned four kinds during specifically carrying out calculating program index parameter
Two kinds of program index parameters in program index parameter, but do not set the upper limit.
Step S103: program index parameter of the presently described user of normalized under each program label is opposite
In the relative value of whole users, the corresponding normalized value of each program index parameter is obtained.
During executing step S103, program index parameter of the user under each program label is calculated relative to every
The relative case of the program index parameter of whole users under a program label.
Detailed process is as shown in Figure 2, comprising:
Step S201: the number of the corresponding whole users of the program watched under each program label is obtained, and every
The corresponding program index parameter of each user under a program label.
Step S202: determine presently described user each program label the program index parameter relative to complete
The relative value of portion user.
Step S203: the normalized calculation method of max min and the corresponding program index of each user are based on
Parameter, the program index parameter for obtaining presently described user in each program label watch number of days relative to whole use
The relative value at family, using obtained each relative value as the normalized value of the program index parameter under respective corresponding program label.
Based on above-mentioned specific implementation process, citing is illustrated here:
When program label is TV play, program index parameter is rating duration, watches that the total number of users of the TV play was total
Share 5, including current calculative user.5 users are obtained respectively to watch TV acute rating duration are as follows: 20 minutes,
30 minutes, 45 minutes, 15 minutes and 60 minutes.Then the rating duration of current calculative user (first user) is carried out
Normalized, the normalized value of obtained rating duration are as follows: (20-15)/(60-15)=0.11.
The normalization of other program index parameters is also calculated using the normalization mode of this kind of max min.
Program index parameter is all normalized in [0,1] section.The evaluation of more conducively subsequent interest-degree.
Step S104: each program under the corresponding each program label of the presently described user of weighted calculation refers to
The corresponding normalized value of parameter is marked, obtains presently described user to the interest-degree of the corresponding program of each program label.
During executing step S104, to each under the corresponding each program label of obtained presently described user
The corresponding normalized value of program index parameter is weighted.Specifically added by the corresponding normalized value of each program index parameter
Weight can be adjusted according to type of service, can also be configured in advance.It is according to the actual situation different programs
The corresponding normalized value of index parameter distributes different weights, but needs to meet the corresponding normalization of each program index parameter
The summation of the added weight of value is 1.
Further, it should be noted that during being weighted, can delete and select multiple program index parameters pair
The normalized value answered is weighted, and does not need whole.
The embodiment of the present invention includes under program label and program label by establishing interest tags library, interest tags library
Each program parameter, program label includes program generic;User is calculated on each program label based on program label
Program index parameter;Program index parameter of the normalized active user under each program label be not relative to whole users
Relative value, obtain the corresponding normalized value of each program index parameter;The corresponding each program mark of weighted calculation active user
The corresponding normalized value of each program index parameter signed, obtains active user to the emerging of the corresponding program of each program label
Interesting degree.By the evaluation method of user interest degree disclosed above, obtained interest-degree is approximate on number of users to obey Gauss point
Cloth, and the size of obtained interest-degree can really reflect user to the interest-degree of the program under the program label, and it is above-mentioned
Calculating is obtained based on the program index parameter on the program label pre-established, and process is succinct.Therefore, disclosed by the invention
The evaluation method of user interest degree can fast and accurately obtain user to the interest-degree of each program label.
Based on the evaluation method of user interest degree disclosed in the embodiments of the present invention, calculates and use in executing step S102
Family is during the program index parameter on each program label, different program index parameters, and calculation is different, lifts here
Example explanation.
If the program index parameter includes rating duration, user is calculated in each program label based on the program label
On program index parameter, detailed process includes:
Firstly, determining each program label.
Then, the duration T that user watches the program under each program label is obtained.
Wherein, the t in formula (1)iIndicate that user watches the duration of the program under actual program label every time, i and n are indicated
The number that user watches under certain label, i are more than or equal to 1, n and are greater than i.
If the program index parameter includes number of programs, user is calculated on each program label based on the program label
Program index parameter, detailed process includes:
Firstly, determining each program label.
Then, it is determined that the different programs that user watches under each program label, which can pass through program names
Claim or program subject matter is determined, wherein the program with the same or similar programm name or program subject matter, number of programs P
It is denoted as 1.
For example, determining that program label is that the program that user is watched under variety and the program label includes: which father goes
Youngster 1 and father go where 2.Because programm name is similar, then the number of programs that user watches in the case where program label is by variety is 1.
For example, determining that program label is that the program that user is watched under variety and the program label includes: which father goes
Youngster 1, father go where 2 and I be singer 3.Because father goes where 1 to go where 2 programm names are similar with father, then 1 is denoted as.
I is that singer 3 is then individually denoted as 1.Therefore, the number of programs which watches in the case where program label is by variety is 2.
If the program index parameter includes: to watch completion rate, calculated based on the program label in each program
Program index parameter on label, detailed process include:
Firstly, determining each program label.
Then, obtain user and watch the number of each program under the program label, each time watch duration and each
The original duration of a program obtains watching completion rate R.
Wherein, the t in formula (2)iIndicate that user watches the duration of the program under actual program label every time, i and n table
Show that the number that user watches under certain label, i are more than or equal to 1, n and are greater than i, piIndicate that user is watched every time under actual program label
Program advance notice playing duration.
Such as: determine that a program label is TV play, and user has watched the name of 3 people on TV play label.
And watch the people name first collect when it is 20 minutes a length of, watch the people name second collection when it is 40 minutes a length of, watch
Military counsellor alliance the 5th collect when it is 20 minutes a length of.Wherein, the total duration of the name of the people is 50 minutes, the total duration of military counsellor alliance
It is 45 minutes.Based on above-mentioned formula (2), the completion rate for watching program of user under the available program label are as follows: (20/50+
40/50+20/45)/3=0.55.
If the program index parameter includes watching number of days, user is calculated in each program label based on the program label
On program index parameter, detailed process includes:
Firstly, determining each program label.
Then, it is determined that the number of days D that user watched under each program label.
For example, program label is TV play, user has 3 days to see TV play, then user is in TV play in program label
Watch number of days be 3.
Further, it based on the program label parameter of above-mentioned determination, the step of executing above-mentioned normalized, respectively obtains
The corresponding normalized value T ' of rating duration, the corresponding normalized value P ' of number of programs watch the corresponding normalized value R ' of completion rate, receive
See the corresponding normalized value D ' of number of days.
Further, based on after above-mentioned normalization rating duration, watch completion rate, number of programs and watch number of days, then
The corresponding normalized value of each program index parameter under the corresponding each program label of the weighted calculation active user, obtains
To active user to the interest-degree of the corresponding program of each program label, detailed process includes:
Firstly, obtaining each rating duration under the corresponding each program label of presently described user, the receipts
It sees completion rate, the number of programs and described watches the corresponding normalized value of number of days;
Then, it for each program label, is weighted based on formula (3), obtains presently described user couple
The interest-degree H of the corresponding program of each program label.
H=aT '+bP '+cR '+dD ' (3)
Wherein, T ' is the corresponding normalized value of rating duration described under actual program label, and P ' is under actual program label
The corresponding normalized value of the number of programs, R ' are described under actual program label to watch that the corresponding normalized value of completion rate, D ' are
Described under actual program label to watch the corresponding normalized value of number of days, a, b, c, d are pre-assigned weighted value, and a+b+c+d
=1.
The embodiment of the present invention is by the evaluation method of user interest degree disclosed above, based on what is established in advance according to interest
Each program label calculates program index parameter of the user on each program label, and to the program under obtained each program label
Index parameter is normalized respectively, finally obtain using the weighted results of the program index parameter after normalized as
The interest-degree of the user of corresponding program label.
Based on the evaluation method of user interest degree disclosed in the embodiments of the present invention, the embodiment of the present invention is also corresponding open
A kind of evaluation system of user interest degree, as shown in figure 3, the evaluation system 300 of the user interest degree specifically includes that
Pretreatment unit 301, for establishing interest tags library, the interest tags library includes program label and described
Each program parameter under program label, the program label include program generic.
Indicator calculating unit 302, for calculating program index of the user on each program label based on the program label
Parameter.
Normalized unit 303, for section of the presently described user of normalized under each program label
Relative value of the mesh index parameter relative to whole users obtains the corresponding normalized value of each program index parameter.
Interest-degree computing unit 304, under the corresponding each program label of the presently described user of weighted calculation
The corresponding normalized value of each program index parameter obtains presently described user to the corresponding section of each program label
Purpose interest-degree.
Further, include: in the indicator calculating unit 302
Duration calculation module, for determining each program label;It obtains user and watches the section under each program label
Purpose durationWherein, tiIndicate that user watches the duration of the program under actual program label, i and n table every time
Show that the number that user watches under certain label, i are more than or equal to 1, n and are greater than i.
And/or
Completion rate computing module is watched, for determining each program label;The user is obtained to receive under the program label
See the number of each program, the original duration for watching duration and each program each time obtains watching completion rate
Wherein, tiIndicate that user watches the duration of the program under actual program label every time, i and n indicate that user watches under certain label
Number, i be more than or equal to 1, n be greater than i, piWhen indicating that user watches that the advance notice of the program under actual program label plays every time
It is long.
And/or
Number of programs computing module, the number of programs watched under each program label for determining the user, wherein phase
Program with program subject matter is denoted as 1.
And/or
Watch number of days computing module, the number of days watched under each program label for determining the user.
Further, include: in the interest-degree computing unit 304
Module is obtained, when for obtaining each rating under the corresponding each program label of presently described user
It is long, described to watch completion rate, the number of programs and described watch the corresponding normalized value of number of days;
Interest-degree computing module is based on H=aT for being directed to each program label′+bP′+ cR '+dD ', is worked as
Interest-degree H of the preceding user to the corresponding program of each program label, wherein T ' is the receipts under actual program label
The long corresponding normalized value of apparent time, P ' are the corresponding normalized value of number of programs described under actual program label, and R ' is actual program
It is described under label to watch that the corresponding normalized value of completion rate, D ' watch the corresponding normalization of number of days to be described under actual program label
Value, a, b, c, d are pre-assigned weighted value, and a+b+c+d=1.
Each unit and module in the evaluation system of user interest degree disclosed in the embodiments of the present invention is specifically former
Reason and implementation procedure, it is identical as the evaluation method of user interest degree disclosed in the embodiments of the present invention, reference can be made to above-mentioned hair
Corresponding part, is not discussed here in the evaluation method of user interest degree disclosed in bright embodiment.
Based on the evaluation system of user interest degree disclosed in the embodiments of the present invention, above-mentioned each unit and module can be with
It is realized by a kind of hardware device being made of processor and memory.Specifically: above-mentioned each unit and module are as program
Unit is stored in memory, and executes above procedure unit stored in memory by processor to realize user interest degree
Evaluation.
Wherein, include kernel in processor, gone in memory to transfer corresponding program unit by kernel.Kernel can be set
One or more realizes the evaluation to user interest degree by adjusting kernel parameter.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include that at least one is deposited
Store up chip.
Further, the embodiment of the invention provides a kind of processors, and the processor is for running program, wherein institute
State the evaluation method that the user interest degree is executed when program operation.
Further, the embodiment of the invention provides a kind of equipment, equipment includes processor, memory and is stored in storage
On device and the program that can run on a processor, processor performs the steps of when executing program and establishes interest tags library, described
Interest tags library includes each program parameter under program label and the program label, and the program label includes program
Generic;Program index parameter of the user on each program label is calculated based on the program label;Normalized is current
Relative value of program index parameter of the user under each program label relative to whole users, obtains each program
The corresponding normalized value of index parameter;Each program under the corresponding each program label of weighted calculation active user
The corresponding normalized value of index parameter obtains active user to the interest-degree of the corresponding program of each program label.
Wherein, if the program index parameter includes rating duration, user is calculated in each section based on the program label
The program index parameter that target is signed, comprising: determine each program label;User is obtained to watch under each program label
The duration of programWherein, tiIndicate that user watches the duration of the program under actual program label, i and n every time
Indicate that the number that user watches under certain label, i are more than or equal to 1, n and are greater than i.
If the program index parameter includes: to watch completion rate, calculated based on the program label in each program
Program index parameter on label, comprising: determine each program label;It obtains user and watches each section under the program label
Purpose number, the original duration for watching duration and each program each time, obtains watching completion rateWherein, ti
Indicate that user watches the duration of the program under actual program label every time, i and n indicate the number that user watches under certain label,
I is more than or equal to 1, n and is greater than i, piIndicate that user watches the advance notice playing duration of the program under actual program label every time.
Wherein, normalized active user is in the program index parameter of each program label relative to whole
The relative value of user obtains corresponding normalized value, comprising: it is corresponding complete to obtain the program watched under each program label
The corresponding program index parameter of each user under the number of portion user and each program label;Determine active user each
Relative value of the program index parameter of the program label relative to whole users;It is normalized based on max min
Calculation method and the corresponding program index parameter of each user obtain active user described in each program label
Program index parameter watches relative value of the number of days relative to whole users, using obtained each relative value as respective corresponding program
The normalized value of program index parameter under label.
Wherein, if the program index parameter includes: rating duration, watches completion rate, number of programs and watch number of days;Then
The corresponding normalized value of each program index parameter under the corresponding each program label of the weighted calculation active user, obtains
To active user to the interest-degree of the corresponding program of each program label, comprising: obtain the corresponding each institute of active user
Each rating duration under program label is stated, described completion rate, the number of programs watched and described watches that number of days is corresponding
Normalized value;For each program label, it is based on H=aT '+bP '+cR '+dD ', obtains active user to each section
The interest-degree H of the corresponding program of target label, wherein T ' is the corresponding normalized value of rating duration described under actual program label,
P ' is the corresponding normalized value of number of programs described under actual program label, and R ' watches completion rate pair to be described under actual program label
The normalized value answered, D ' watch the corresponding normalized value of number of days to be described under actual program label, and a, b, c, d are pre-assigned
Weighted value, and a+b+c+d=1.
Equipment disclosed in the embodiment of the present invention can be server, PC, PAD, mobile phone etc..
Further, the embodiment of the invention also provides a kind of storage medium, it is stored thereon with program, the program is processed
Device realizes the evaluation method of the user interest degree when executing.
Present invention also provides a kind of computer program products, when executing on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step: interest tags library is established, the interest tags library includes program label and the section
Each program parameter that target is signed, the program label include program generic;User is calculated based on the program label
Program index parameter on each program label;Program index of the normalized active user under each program label
Relative value of the parameter relative to whole users obtains the corresponding normalized value of each program index parameter;Weighted calculation is worked as
The corresponding normalized value of each program index parameter under the corresponding each program label of preceding user, is currently used
Interest-degree of the family to the corresponding program of each program label.
Wherein, if the program index parameter includes rating duration, user is calculated in each section based on the program label
The program index parameter that target is signed, comprising: determine each program label;User is obtained to watch under each program label
The duration of programWherein, tiIndicate that user watches the duration of the program under actual program label, i and n every time
Indicate that the number that user watches under certain label, i are more than or equal to 1, n and are greater than i.
If the program index parameter includes: to watch completion rate, calculated based on the program label in each program
Program index parameter on label, comprising: determine each program label;It obtains user and watches each section under the program label
Purpose number, the original duration for watching duration and each program each time, obtains watching completion rateWherein, ti
Indicate that user watches the duration of the program under actual program label every time, i and n indicate the number that user watches under certain label,
I is more than or equal to 1, n and is greater than i, piIndicate that user watches the advance notice playing duration of the program under actual program label every time.
Wherein, normalized active user is in the program index parameter of each program label relative to whole
The relative value of user obtains corresponding normalized value, comprising: it is corresponding complete to obtain the program watched under each program label
The corresponding program index parameter of each user under the number of portion user and each program label;Determine active user each
Relative value of the program index parameter of the program label relative to whole users;It is normalized based on max min
Calculation method and the corresponding program index parameter of each user obtain active user described in each program label
Program index parameter watches relative value of the number of days relative to whole users, using obtained each relative value as respective corresponding program
The normalized value of program index parameter under label.
Wherein, if the program index parameter includes: rating duration, watches completion rate, number of programs and watch number of days;Then
The corresponding normalized value of each program index parameter under the corresponding each program label of the weighted calculation active user, obtains
To active user to the interest-degree of the corresponding program of each program label, comprising: obtain the corresponding each institute of active user
Each rating duration under program label is stated, described completion rate, the number of programs watched and described watches that number of days is corresponding
Normalized value;For each program label, it is based on H=aT '+bP '+cR '+dD ', obtains active user to each section
The interest-degree H of the corresponding program of target label, wherein T ' is the corresponding normalized value of rating duration described under actual program label,
P ' is the corresponding normalized value of number of programs described under actual program label, and R ' watches completion rate pair to be described under actual program label
The normalized value answered, D ' watch the corresponding normalized value of number of days to be described under actual program label, and a, b, c, d are pre-assigned
Weighted value, and a+b+c+d=1.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of evaluation method of user interest degree characterized by comprising
Interest tags library is established, the interest tags library includes each program ginseng under program label and the program label
Number, the program label includes program generic;
Program index parameter of the user on each program label is calculated based on the program label;
Program index parameter of the presently described user of normalized under each program label is relative to whole users'
Relative value obtains the corresponding normalized value of each program index parameter;
Each program index parameter under the corresponding each program label of the presently described user of weighted calculation is corresponding
Normalized value obtains presently described user to the interest-degree of the corresponding program of each program label.
2. the method according to claim 1, wherein the program parameter includes at least: programm name and program
The duration of itself;
The program generic includes at least: the classification according to division of teaching contents and/or the classification according to the division of program subject matter, institute
Stating according to the classification of division of teaching contents includes: plot, comedy or reality TV show, and the classification divided according to program subject matter includes: electricity
Depending on acute, film or variety.
3. the method according to claim 1, wherein the program index parameter includes: rating duration, has watched
At rate, number of programs and watch number of days.
4. the method according to claim 1, wherein if the program index parameter includes rating duration, base
Program index parameter of the user on each program label is calculated in the program label, comprising:
Determine each program label;
Obtain the duration for the program that the user watches under each program label
Wherein, tiIndicate that the user watches the duration of the program under actual program label every time, i and n indicate the user at certain
The number watched under label, i are more than or equal to 1, n and are greater than i.
5. the method described in any one of according to claim 1, which is characterized in that if the program index parameter includes: to receive
It sees completion rate, is then calculated based on the program label for the program index parameter on each program label, comprising:
Determine each program label;
Obtain the number that the user watches each program under the program label, each time watch duration and each program
Original duration, obtain watching completion rate
Wherein, tiIndicate that the user watches the duration of the program under actual program label every time, i and n indicate that the user exists
The number watched under certain label, i are more than or equal to 1, n and are greater than i, piIndicate that user watches the program under actual program label every time
Predict playing duration.
6. method described in any one of -5 according to claim 1, which is characterized in that normalized active user is each
Relative value of the program index parameter of the program label relative to whole users, obtains corresponding normalized value, comprising:
It obtains each under the number for watching the corresponding whole users of program under each program label and each program label
The corresponding program index parameter of a user;
Determine presently described user each program label the program index parameter relative to the opposite of whole users
Value;
Based on the normalized calculation method of max min and the corresponding program index parameter of each user, obtain current
The user watches relative value of the number of days relative to whole users in the program index parameter of each program label, will
Normalized value of the obtained each relative value as the program index parameter under respective corresponding program label.
7. method described in any one of -5 according to claim 1, which is characterized in that if the program index parameter includes:
Rating duration watches completion rate, number of programs and watches number of days;The then corresponding each institute of the presently described user of the weighted calculation
The corresponding normalized value of each program index parameter under program label is stated, obtains presently described user to each program label
The interest-degree of corresponding program, comprising:
Obtain each rating duration under the corresponding each program label of presently described user, it is described watch completion rate,
The number of programs and described watch the corresponding normalized value of number of days;
For each program label, it is based on H=aT '+bP '+cR '+dD ', obtains presently described user to each section
The interest-degree H of the corresponding program of target label, wherein T ' is the corresponding normalized value of rating duration described under actual program label,
P ' is the corresponding normalized value of number of programs described under actual program label, and R ' watches completion rate pair to be described under actual program label
The normalized value answered, D ' watch the corresponding normalized value of number of days to be described under actual program label, and a, b, c, d are pre-assigned
Weighted value, and a+b+c+d=1.
8. a kind of evaluation system of user interest degree characterized by comprising
Pretreatment unit, for establishing interest tags library, the interest tags library includes program label and the program label
Under each program parameter, the program label includes program generic;
Indicator calculating unit, for calculating program index parameter of the user on each program label based on the program label;
Normalized unit, for program index ginseng of the presently described user of normalized under each program label
Relative value of the number relative to whole users, obtains the corresponding normalized value of each program index parameter;
Interest-degree computing unit, for each described under the corresponding each program label of the presently described user of weighted calculation
The corresponding normalized value of program index parameter obtains presently described user to the interest of the corresponding program of each program label
Degree.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment execute evaluation side such as user interest degree of any of claims 1-7
Method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein executed such as when described program is run
The evaluation method of user interest degree of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710888524.2A CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710888524.2A CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109561350A true CN109561350A (en) | 2019-04-02 |
CN109561350B CN109561350B (en) | 2021-06-29 |
Family
ID=65863917
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710888524.2A Active CN109561350B (en) | 2017-09-27 | 2017-09-27 | User interest degree evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109561350B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111858564A (en) * | 2019-04-28 | 2020-10-30 | 腾讯科技(深圳)有限公司 | Data processing method, service processing method, device, terminal and storage medium |
CN113590926A (en) * | 2020-04-30 | 2021-11-02 | 北京爱笔科技有限公司 | User interest identification method, device, equipment and computer readable medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008129879A1 (en) * | 2007-04-18 | 2008-10-30 | Panasonic Corporation | Digital broadcast receiver and digital broadcast reception method |
US20090328105A1 (en) * | 2008-06-27 | 2009-12-31 | Guideworks, Llc | Systems and methods for ranking assets relative to a group of viewers |
CN102263992A (en) * | 2011-08-08 | 2011-11-30 | 上海文广互动电视有限公司 | Program recommendation degree estimation method based on user viewing record |
CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技(天津)有限公司 | Method and system for recommending video resource |
CN104935970A (en) * | 2015-07-09 | 2015-09-23 | 三星电子(中国)研发中心 | Method for recommending television content and television client |
CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
CN106802956A (en) * | 2017-01-19 | 2017-06-06 | 山东大学 | A kind of film based on weighting Heterogeneous Information network recommends method |
CN107113466A (en) * | 2014-06-12 | 2017-08-29 | 慧与发展有限责任合伙企业 | To user's recommended project |
-
2017
- 2017-09-27 CN CN201710888524.2A patent/CN109561350B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008129879A1 (en) * | 2007-04-18 | 2008-10-30 | Panasonic Corporation | Digital broadcast receiver and digital broadcast reception method |
US20090328105A1 (en) * | 2008-06-27 | 2009-12-31 | Guideworks, Llc | Systems and methods for ranking assets relative to a group of viewers |
CN102263992A (en) * | 2011-08-08 | 2011-11-30 | 上海文广互动电视有限公司 | Program recommendation degree estimation method based on user viewing record |
CN103686236A (en) * | 2013-11-19 | 2014-03-26 | 乐视致新电子科技(天津)有限公司 | Method and system for recommending video resource |
CN107113466A (en) * | 2014-06-12 | 2017-08-29 | 慧与发展有限责任合伙企业 | To user's recommended project |
CN104935970A (en) * | 2015-07-09 | 2015-09-23 | 三星电子(中国)研发中心 | Method for recommending television content and television client |
CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
CN106802956A (en) * | 2017-01-19 | 2017-06-06 | 山东大学 | A kind of film based on weighting Heterogeneous Information network recommends method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111858564A (en) * | 2019-04-28 | 2020-10-30 | 腾讯科技(深圳)有限公司 | Data processing method, service processing method, device, terminal and storage medium |
CN113590926A (en) * | 2020-04-30 | 2021-11-02 | 北京爱笔科技有限公司 | User interest identification method, device, equipment and computer readable medium |
Also Published As
Publication number | Publication date |
---|---|
CN109561350B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105898420B (en) | A kind of video recommendation method, device and electronic equipment | |
CN110012302A (en) | A kind of network direct broadcasting monitoring method and device, data processing method | |
CN109472296A (en) | A kind of model training method and device promoting decision tree based on gradient | |
CN108537568A (en) | A kind of information recommendation method and device | |
CN109582403A (en) | Interlocked display method and device between chart inner assembly | |
CN104506894A (en) | Method and device for evaluating multi-media resources | |
US9753988B1 (en) | Computer processes for predicting media item popularity | |
CN109903065A (en) | A kind of method and apparatus of the candidate score value of determining candidate point | |
CN107967173A (en) | A kind of methods, devices and systems of scheduling of resource | |
CN110502665A (en) | Method for processing video frequency and device | |
CN109583921A (en) | Advertising budget acquisition methods, device, storage medium and processor | |
CN109242288A (en) | Performance data matching process and system | |
CN110458615A (en) | Pass through the method and device of internet information assessment customer satisfaction | |
CN110046278A (en) | Video classification methods, device, terminal device and storage medium | |
CN109598171A (en) | A kind of data processing method based on two dimensional code, apparatus and system | |
CN109561350A (en) | The evaluation method and system of user interest degree | |
CN110334013A (en) | Test method, device and the electronic equipment of decision engine | |
CN108322819A (en) | Predict the method and device of user behavior | |
CN109710410A (en) | A kind of internet information resource distribution method and device | |
Cerit et al. | Quality function deployment and its application on a smartphone design | |
CN109614548B (en) | Information display method and device based on service user number change rate and storage medium | |
CN108881968A (en) | A kind of network video advertisement put-on method and system | |
CN109740060A (en) | A kind of frequency control method and device of pushed information | |
Balint et al. | On supporting contract-aware IoT dataspace services | |
CN106204125A (en) | A kind of pricing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: Beijing Guoshuang Technology Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: Beijing Guoshuang Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |