CN108260007B - Program recommendation method and program recommendation system - Google Patents
Program recommendation method and program recommendation system Download PDFInfo
- Publication number
- CN108260007B CN108260007B CN201810057293.5A CN201810057293A CN108260007B CN 108260007 B CN108260007 B CN 108260007B CN 201810057293 A CN201810057293 A CN 201810057293A CN 108260007 B CN108260007 B CN 108260007B
- Authority
- CN
- China
- Prior art keywords
- program
- user
- cost
- matrix
- data
- 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.)
- Active
Links
Images
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
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Abstract
The invention provides a program recommendation method and a program recommendation system, wherein the method comprises the following steps: collecting program data and user data; calculating a preference matrix of the user to the program according to the user data; calculating a program cost matrix according to the program data; calculating a program recommendation level according to a preference matrix of a user to the program and a program cost matrix; and sequencing the programs according to the program recommendation grades, and making the programs into a program recommendation list for storage. The invention has the advantages of objectivity, justice and high program recommendation efficiency.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a program recommendation method and a program recommendation system.
Background
In the current information age, computer technology has advanced dramatically. All media are leading to the era in terms of cultural science and technology. The audio and video program resources are rich and the management is complex. In actual work, the computer technology provides a good working mode for purchasing and selling personnel through classified management, quick look-up, accurate selection, free arrangement and recommendation and the like of audio and video resources, and the accurate matching speed and the working quality are greatly improved. The combined analysis of the audio and video production cost, the playing and the income is a powerful basis for comprehensively evaluating related departments and providing management and decision. How a video copyright party promotes the content of the video copyright party, and the income is maximized; how to obtain high-quality copyright content is a current difficult problem in video websites, value-added services and the like. At present, the programming work related to both parties is very endless, the resource management is disordered, and valuable or interesting contents cannot be found.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a program recommendation method and a program recommendation system that overcome or at least partially solve the above problems.
In one aspect of the present invention, a program recommendation method is provided, including the steps of:
collecting program data and user data;
calculating a preference matrix of the user to the program according to the user data;
calculating a program cost matrix according to the program data;
calculating a program recommendation level according to a preference matrix of a user to the program and a program cost matrix;
and sequencing the programs according to the program recommendation grades, and making the programs into a program recommendation list for storage.
Further, the collected user data is the program preferred by the user, the playing times of the program preferred by the user, the type of the program preferred by the user, the director of the program preferred by the user, the playing amount of the program preferred by the user, and the cost price of the program preferred by the user according to the program data and the formula
Calculating a preference matrix M ═ t of the user to the programm,ym,um,im,pmjIn which imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjThe cost price of the program is preferred for the user.
Further, the collected program data includes program name, program type, program director, program playing amount, program cost rate, cost price, program sale times, total program number, and total program cost, and the program data is substituted into formula pm(TF-IDF) ═ cost (number of program sales/total number of programs) abs (log (total of program costs + 1/cost · number of program sales))), and (t) ═ t ═ program cost matrix Q is calculatedm,ym,um,im,pmWhere Q is the program cost matrix, tmIs the program name, ymIs the program type, um is the program director, imFor the amount of program play, pmIs the program cost rate.
Further, substituting the preference matrix of the user to the program and the program cost matrix into a formula
And calculating the program recommendation level, wherein M is a preference matrix of the user to the program, Q is a program cost matrix, Ma is a preference value of the user M to Qa, Qa is the program Q containing the program attribute a, and a is an a-dimensional matrix.
Further, the collected user data includes a program name, a program type, a program director, a program play amount, a program cost rate, a cost price, a program sale frequency, a total program number, and a total program cost amount.
A second aspect of the present invention provides a program recommendation system implementing any one of the above program recommendation methods, including:
the data acquisition module is used for acquiring program data and user data and respectively sending the program data and the user data to the user preference calculation module, the program cost calculation module and the program recommendation module;
the user preference calculation module is used for calculating a preference matrix of the user to the program according to the user data and sending the preference matrix to the program recommendation level calculation module;
the program cost calculation module is used for calculating a program cost matrix according to the program data and sending the program cost matrix to the program recommendation level calculation module;
the program recommendation level calculation module is used for calculating a program recommendation level according to the preference matrix of the user to the program and the program cost matrix and sending the program recommendation level to the program recommendation list making module;
and the program recommendation list making module is used for sequencing the programs according to the program recommendation grades and making the programs into a program recommendation list for storage.
Further, the user data collected by the data collecting module is the program preferred by the user, the playing times of the program preferred by the user, the type of the program preferred by the user, the director of the program preferred by the user, the playing amount of the program preferred by the user, and the cost price of the program preferred by the user according to the program data and the formula
Calculating a preference matrix M ═ t of the user to the programm,ym,um,im,pmjIn which imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjThe cost price of the program is preferred for the user.
Further, the program data collected by the data collecting module includes program name, program type, program director, program playing amount, program cost rate, cost price, program selling times, total program number and total program cost, and the program data is substituted into the formula pm(TF-IDF) ═ cost (number of program sales/total number of programs) abs (log (total of program costs + 1/cost · number of program sales))), and (t) ═ t ═ program cost matrix Q is calculatedm,ym,um,im,pmWhere Q is the program cost matrix, tmIs the program name, ymIs the program type, um is the program director, imFor the amount of program play, pmIs the program cost rate.
Further, the program recommendation level calculation module substitutes the preference matrix of the user to the program and the program cost matrix into a formula
Calculating a program recommendation level, wherein M is a userAnd for a preference matrix of the program, Q is a program cost matrix, Ma is the preference value of the user M to Qa, Qa is the program Q containing the program attribute a, and a is an a-dimensional matrix.
Furthermore, the data acquisition module is respectively and electrically connected with the user preference calculation module, the program cost calculation module and the program recommendation list making module, and the program recommendation level calculation module is respectively and electrically connected with the user preference calculation module, the program cost calculation module and the program recommendation list making module.
Compared with the prior art, the program recommendation method provided by the invention has the following progress: the user and program data collected by the data collecting module are comprehensive and objective, the preference degree matrix and the program cost matrix of the user to the program are calculated according to the user and program data collected by the data collecting module, the program recommendation level is calculated according to the preference matrix and the program cost matrix of the user to the program, the programs are sorted according to the program recommendation level and are made into a program recommendation list for storage, program resources which are more interesting to the user can be objectively and fairly recommended to the user, and the user experience is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a diagram illustrating steps of a program recommendation method according to an embodiment of the present invention;
fig. 2 is a device connection block diagram of the program recommendation system in the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The embodiment of the invention provides a program recommendation method and a program recommendation system.
Fig. 1 schematically shows a step diagram of a program recommendation method according to an embodiment of the present invention. Referring to fig. 1, a program recommendation method according to an embodiment of the present invention includes the following steps:
collecting program data and user data;
calculating a preference matrix of the user to the program according to the user data;
calculating a program cost matrix according to the program data;
calculating a program recommendation level according to a preference matrix of a user to the program and a program cost matrix;
and sequencing the programs according to the program recommendation grades, and making the programs into a program recommendation list for storage.
According to the program recommending method in the embodiment, the preference matrix and the program cost matrix of the user for the program are calculated according to the collected user data and the collected program data, the collected user data and the collected program data are comprehensive and objective, the program recommending level is calculated according to the preference matrix and the program cost matrix of the user for the program, the programs are sorted according to the program recommending level and are made into the program recommending list for storage, the program resources which are more interested by the user can be recommended for the user objectively and fairly, the time of the user is saved, and the user experience is improved.
In this embodiment, the collected user data includes a program preferred by the user, the playing times of the program preferred by the user, the type of the program preferred by the user, the director of the program preferred by the user, the playing amount of the program preferred by the user, and the cost price of the program preferred by the user, according to the program data and the formula
Calculating a preference matrix M ═ t of the user to the programm,ym,um,im,pmjIn which imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjThe cost price of the program is preferred for the user.
In one embodiment, first, all user sets are recorded as a row matrix: c ═ C1,c2,c3,.......,cnIn which c is1For users 1, c2For users 2, c3For user 3, … cnIs user n. Then modeling is carried out on the program data played by the user, and a program data analysis matrix is constructed:
wherein, CiRepresenting a set of preferences of user i for various attributes of the program, t11Is the date, t, of program 112For the user playing program 1, t13Is the name … …, t of program 11nIs the type of program 1, t21Is the date, t, of program 222For the user of program 2, t23Is the name of program 2Weighing … …, t2nIs the type of program 2, tn1Is the date, t, of the program nn2For a user of program n, tn3Is the name … …, t of program nnnIs the genre of program n. In practical applications, the matrix is a set of user preferences for program attributes, is expandable and scalable so as to be an n-dimension, is multi-dimensional and can contain many user preference attributes, and in other embodiments, t is an exemplary examplennOther attributes of other user preferred programs may also be represented. The setting is made by a person skilled in the art as the case may be.
In the above manner, the user and the program played by the user have been modeled. The following formula was run once a day and repeated. The calculation method is as follows: first step calculation of user CiAverage of all videos played
The amount of play is calculated by the formula
Wherein r ismN is the number of plays of the mth user-preferred program, and is taken from m up to r. Through the calculation, a matrix M ═ t of interest and preference of the user is constructedm,ym,um,im,pmjIn the formula, all are M-dimensional vectors, M is a preference matrix of the user to the program, and tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjThe cost price of the program is preferred for the user.
In this embodiment, the collected program data includes program name, program type, program director, program playing amount, program cost rate, cost price, program selling times, total program number, and total program cost, and the program data is substituted into the formula pm(TF-IDF) ═ cost (number of program sales/total number of programs) abs (log (total of program costs + 1/cost · number of program sales))), and (t) ═ t ═ program cost matrix Q is calculatedm,ym,um,im,pmWherein Q is a program cost matrix，tmIs the program name, ymIs the program type, um is the program director, imFor the amount of program play, pmIs the program cost rate.
In one embodiment, the program set is recorded as P ═ { P ═ P1,p2,p3,.......,pnWhere P is a set of programs, P1Is a program 1, p2Is a program 2, p3Is program 3, … …, pnIs program n. Then, constructing a program cost matrix, constructing a 1 x n-dimensional matrix, wherein n represents the number of the attribute values of the video program, including the number of program types, the number of the lead actors appearing in the program list, the film cost, the number of the directors and the like, and obtaining the video program matrix:
for example, the row matrix information of the jth movie: { display volume ratio, movie name, type, purchase cost unit price, sales frequency, director, lead actor,. n }, in this way, the program is modeled. In practical application, the matrix is a set of preferences of a user for program attributes, is extensible and scalable, and therefore is an n-dimension, is multi-dimensional, and can contain a plurality of program attributes.
Calculating the cost rate by using a TF-IDF right method: p is a radical ofm(TF-IDF) ═ cost (number of program sales/total number of programs) abs (log (total of program costs + 1/cost) number of sales), and a program cost matrix Q ═ t · is constructed by calculationm,ym,um,im,pmWhere Q is the program cost matrix, tmIs the program name, ymAs a program type umFor the program director, imFor the amount of program play, pmIs the program cost rate.
In this embodiment, the user preference matrix and the program cost matrix are substituted into the formula
Calculate program recommendations, etcAnd the level, wherein M is a preference matrix of the user to the program, Q is a program cost matrix, Ma is a preference value of the user M to Qa, Qa is the program Q containing the program attribute a, and a is an a-dimensional matrix.
In one embodiment, a cosine similarity formula is used to calculate the distance between a given user preference matrix "M" and program cost matrix "Q" for a program, wherein a greater cosine similarity indicates that the more similar the user preference matrix "M" and program cost matrix "Q" for the program, the higher the program recommendation level, and the further the program is in the front when making a program recommendation list. The specific calculation method of the cosine similarity is as follows:
where Ma is a preference value of the user M for Qa, Qa is a program Q including a program attribute a, and a is an a-dimensional matrix.
And calculating the preference degree and cosine similarity of the user to the program parameters, determining the program recommendation level according to the cosine similarity, and making a program recommendation list by using the program recommendation level for storage, so as to be convenient for recommending program resources for the user subsequently.
In one embodiment, cosine similarity calculation is used: deriving a user preference matrix for the program as
The program cost matrix is
Using cosine similarity to obtain:
the closer the cosine value is to 1, the closer the included angle is to 0 degree, that is, the more similar the two vectors are, the higher the recommendation level of the program is, the more worthy of recommendation to the user is, and the program should be set before the program recommendation list is made.
In this embodiment, the collected user data includes a program name, a program type, a program director, a program play amount, a program cost rate, a cost price, a program sale frequency, a total program number, and a total program cost amount.
Fig. 2 schematically shows a device connection block diagram of a program recommendation system according to an embodiment of the present invention. Referring to fig. 2, the program recommendation system according to the embodiment of the present invention includes:
the data acquisition module is used for acquiring program data and user data and respectively sending the program data and the user data to the user preference calculation module, the program cost calculation module and the program recommendation module;
the user preference calculation module is used for calculating a preference matrix of the user to the program according to the user data and sending the preference matrix to the program recommendation level calculation module;
the program cost calculation module is used for calculating a program cost matrix according to the program data and sending the program cost matrix to the program recommendation level calculation module;
the program recommendation level calculation module is used for calculating a program recommendation level according to the preference matrix of the user to the program and the program cost matrix and sending the program recommendation level to the program recommendation list making module;
and the program recommendation list making module is used for sequencing the programs according to the program recommendation grades and making the programs into a program recommendation list for storage.
The program recommendation level calculation module is electrically connected with the user preference calculation module, the program cost calculation module and the program recommendation list making module respectively.
The program recommending system of the embodiment of the invention obtains the program recommending level by calculating the preference matrix of the user to the program parameters and the program cost matrix, recommends the program resources to the user according to the size of the program recommending level, and has the advantages of objectivity, fairness and time saving.
In this embodiment, the user data collected by the data collecting module is a program preferred by the user, the playing times of the program preferred by the user, the type of the program preferred by the user, the director of the program preferred by the user, the playing amount of the program preferred by the user, and the cost price of the program preferred by the user according to the program data and the formula
Calculating a preference matrix M ═ t of the user to the programm,ym,um,im,pmjIn which imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjThe cost price of the program is preferred for the user.
In this embodiment, the program data collected by the data collecting module includes program name, program type, program director, program playing amount, program cost rate, cost price, program selling times, total program number, and total program cost, and the program data is substituted into the formula pm(TF-IDF) ═ cost (number of program sales/total number of programs) abs (log (total of program costs + 1/cost · number of program sales))), and (t) ═ t ═ program cost matrix Q is calculatedm,ym,um,im,pmWhere Q is the program cost matrix, tmIs the program name, ymIs the program type, um is the program director, imFor the amount of program play, pmIs the program cost rate.
In this embodiment, the program recommendation level calculation module substitutes the user preference matrix and the program cost matrix into the formula
Calculating program recommendation levels, wherein M is a preference matrix of users to programs, Q is a program cost matrix, and Ma is a use matrixThe preference value of the user M to the program attribute a, Qa is the program Q containing the program attribute a, and a is the attribute of the program.
In this embodiment, the data acquisition module may obtain program data by downloading a program data packet from the internet, analyzing the program data, entering program information through the platform, editing and entering attributes of the program such as program name, genre, cost price, profile, and the like into the database for storage, or obtaining program data from other manners; the data acquisition module can acquire user data through registration information of a user or through records clicked by the user, and can also collect user data of programs such as video websites. This embodiment is only an example, and does not limit the protection scope of the present invention.
According to the program recommending method provided by the invention, the user and program data collected by the data collecting module are comprehensive and objective, the preference matrix of the user to the program and the program cost matrix are calculated according to the user and program data collected by the data collecting module, the program recommending level is calculated according to the preference matrix of the user to the program and the program cost matrix, the programs are sorted according to the program recommending level and are made into the program recommending list for storage, program resources which are more interesting to the user can be objectively and fairly recommended for the user, and the user experience is favorably improved.
For simplicity of explanation, the method embodiments are described as a series of acts or combinations, but those skilled in the art will appreciate that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the embodiments of the invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (3)
1. A program recommendation method, comprising the steps of:
collecting program data and user data, wherein the collected user data are programs preferred by a user, playing times of the programs preferred by the user, types of the programs preferred by the user, directors of the programs preferred by the user, playing quantity of the programs preferred by the user and cost price of the programs preferred by the user; the collected program data comprises program names, program types, program directors, program playing amounts, program cost rates, cost prices, program sales times, total program numbers and program cost totals;
according to user data and formula
Calculating the preference matrix M ═ t of the user to the programm,ym,um,im,pmjIn which imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjFavoring cost price of the program for the user;
calculating a program cost matrix according to the program data, and substituting the program data into a formula p'm(TF-IDF) — cost price (number of program sales/total number of programs × (log (total number of program costs + 1/cost price × number of program sales))), and calculate program cost matrix Q ═ t'm,y'm,u'm,i'm,p'mQ is a program cost matrix, t'mIs program name, y'mIs the program type, u'mIs the director of the program i'mAs to the amount of play-out of the program,p'mis the program cost rate;
calculating program recommendation level according to user preference matrix and program cost matrix of program, substituting user preference matrix and program cost matrix into formula
Calculating a program recommendation level, wherein Ma is a preference value of the user M to Qa, Qa is a program Q containing a program attribute a, and a is an a-dimensional matrix;
and sequencing the programs according to the program recommendation grades, and making the programs into a program recommendation list for storage.
2. A program recommendation system, comprising:
the data acquisition module is used for acquiring program data and user data and respectively sending the program data and the user data to the user preference calculation module, the program cost calculation module and the program recommendation list making module; the user data is a program preferred by a user, the playing times of the program preferred by the user, the type of the program preferred by the user, the director of the program preferred by the user, the playing amount of the program preferred by the user and the cost price of the program preferred by the user; the program data is program name, program type, program director, program playing amount, program cost rate, cost price, program selling times, total program number and total program cost;
a user preference calculation module for calculating the user preference according to the user data and the formula
Calculating the preference matrix M ═ t of the user to the programm,ym,um,im,pmjAnd sending the data to a program recommendation level calculation module, wherein imAverage amount of play for all programs, r, for the usermThe number of playing times of the program preferred by the mth user, n is the number of times of taking from M and up to r, M is the preference matrix of the user to the program, tmFor programs preferred by the user, ymPreference of the type of program for the user, umFor the director of the user's preferred programs, pmjFavoring cost price of the program for the user;
the program cost calculation module is used for calculating a program cost matrix according to the program data and sending the program cost matrix to the program recommendation level calculation module; substituting program data into formula p'm(TF-IDF) — cost price (number of program sales/total number of programs × (log (total number of program costs + 1/cost price × number of program sales))), and calculate program cost matrix Q ═ t'm,y'm,u'm,i'm,p'mQ is a program cost matrix, t'mIs program name, y'mIs the program type, u'mIs the director of the program i'mIs the amount of program play, p'mIs the program cost rate;
the program recommendation level calculation module is used for calculating a program recommendation level according to the preference matrix of the user to the program and the program cost matrix and sending the program recommendation level to the program recommendation list making module; substituting the preference matrix of the user to the program and the program cost matrix into a formula
Calculating a program recommendation level, wherein Ma is a preference value of the user M to Qa, Qa is a program Q containing a program attribute a, and a is an a-dimensional matrix;
and the program recommendation list making module is used for sequencing the programs according to the program recommendation grades and making the programs into a program recommendation list for storage.
3. The program recommendation system of claim 2, wherein the data collection module is electrically connected to the user preference calculation module, the program cost calculation module, and the program recommendation list creation module, respectively, and the program recommendation level calculation module is electrically connected to the user preference calculation module, the program cost calculation module, and the program recommendation list creation module, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057293.5A CN108260007B (en) | 2018-01-22 | 2018-01-22 | Program recommendation method and program recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810057293.5A CN108260007B (en) | 2018-01-22 | 2018-01-22 | Program recommendation method and program recommendation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108260007A CN108260007A (en) | 2018-07-06 |
| CN108260007B true CN108260007B (en) | 2020-06-16 |
Family
ID=62741662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810057293.5A Active CN108260007B (en) | 2018-01-22 | 2018-01-22 | Program recommendation method and program recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108260007B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527815A (en) * | 2008-03-06 | 2009-09-09 | 株式会社东芝 | Program recommending apparatus and method |
| CN103179461A (en) * | 2013-03-27 | 2013-06-26 | 四川长虹电器股份有限公司 | Method for recommending smart television content |
| CN103942243A (en) * | 2013-01-21 | 2014-07-23 | 三星电子株式会社 | Display apparatus and method for providing customer-built information using the same |
| CN106028156A (en) * | 2016-06-24 | 2016-10-12 | 合肥工业大学 | Television viewer interest modeling method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7970905B2 (en) * | 2008-07-03 | 2011-06-28 | International Business Machines Corporation | Method, system and computer program product for server selection, application placement and consolidation planning of information technology systems |
| US20130173202A1 (en) * | 2011-12-30 | 2013-07-04 | Aktiebolaget Skf | Systems and Methods for Dynamic Prognostication of Machine Conditions for Rotational Motive Equipment |
-
2018
- 2018-01-22 CN CN201810057293.5A patent/CN108260007B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101527815A (en) * | 2008-03-06 | 2009-09-09 | 株式会社东芝 | Program recommending apparatus and method |
| CN103942243A (en) * | 2013-01-21 | 2014-07-23 | 三星电子株式会社 | Display apparatus and method for providing customer-built information using the same |
| CN103179461A (en) * | 2013-03-27 | 2013-06-26 | 四川长虹电器股份有限公司 | Method for recommending smart television content |
| CN106028156A (en) * | 2016-06-24 | 2016-10-12 | 合肥工业大学 | Television viewer interest modeling method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108260007A (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7154334B2 (en) | Using machine learning to recommend livestream content | |
| US10152517B2 (en) | System and method for identifying similar media objects | |
| WO2017096877A1 (en) | Recommendation method and device | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| US7849092B2 (en) | System and method for identifying similar media objects | |
| Deldjoo et al. | Audio-visual encoding of multimedia content for enhancing movie recommendations | |
| CN106503025B (en) | Application recommendation method and system | |
| US20090055376A1 (en) | System and method for identifying similar media objects | |
| US20090132519A1 (en) | Cliprank: ranking media content using their relationships with end users | |
| CN109511015B (en) | Multimedia resource recommendation method, device, storage medium and equipment | |
| US20070219994A1 (en) | Methods and systems for displaying media utilizing user-generated data | |
| US20080077568A1 (en) | Talent identification system and method | |
| CN106294830A (en) | The recommendation method and device of multimedia resource | |
| CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
| US9141671B2 (en) | System and method for presenting filter options to a user based on ongoing monitoring of filter selections | |
| CN106131703A (en) | A kind of method of video recommendations and terminal | |
| CN110737859A (en) | UP main matching method and device | |
| CN112364202A (en) | Video recommendation method and device and electronic equipment | |
| CN104615741B (en) | Cold-start project recommendation method and device based on cloud computing | |
| CN105843876B (en) | Quality evaluation method and device for multimedia resources | |
| CN105183925A (en) | Content association recommending method and content association recommending device | |
| Yamasaki et al. | Social popularity score: Predicting numbers of views, comments, and favorites of social photos using only annotations | |
| US20150120634A1 (en) | Information processing device, information processing method, and program | |
| CN105426550A (en) | Collaborative filtering tag recommendation method and system based on user quality model | |
| Liu et al. | QA document recommendations for communities of question–answering websites |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |