CN108108491B - Multimedia data recommendation method and device - Google Patents
Multimedia data recommendation method and device Download PDFInfo
- Publication number
- CN108108491B CN108108491B CN201810034582.3A CN201810034582A CN108108491B CN 108108491 B CN108108491 B CN 108108491B CN 201810034582 A CN201810034582 A CN 201810034582A CN 108108491 B CN108108491 B CN 108108491B
- Authority
- CN
- China
- Prior art keywords
- user
- multimedia data
- matrix
- similarity
- users
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a method and a device for recommending multimedia data, and relates to a recommendation deviceThe technical field of computers solves the problem that a terminal in the prior art cannot accurately recommend a user and a video. The method comprises the following steps: according to the attribute information of the multimedia data, generating a matrix R and generating a corresponding matrix S for each user, wherein the elements of the matrix RRepresenting whether user i views multimedia data j, elements of matrix SRepresenting whether the multimedia data v viewed by the user belongs to the multimedia data type u; calculating the similarity between the first user and other users according to the matrix R, the matrix S corresponding to the first user and the matrices S corresponding to other users; and determining the multimedia data recommended to the first user according to the similarity between the first user and each of the other users, the number of preset similar users, the matrix S and the number of the multimedia data needing to be recommended to the first user. The method and the device are applied to recommendation of multimedia data.
Description
The present application is a divisional application of chinese patent application 201510438746.5 entitled "a method and apparatus for recommending multimedia data" filed on 23.07.2015.
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for recommending multimedia data.
Background
Nowadays, in the era of the rapid development of the internet, people have higher and higher requirements on audio and video, and the video associated recommendation service can recommend videos for users, effectively help the users to find the requirements, and promote the users to request the audio and video services. In the prior art, a Collaborative Filtering recommendation (CF) algorithm is generally used to recommend videos for users.
In the prior art, when a terminal (taking an intelligent television as an example) recommends videos for users according to a traditional CF algorithm, a clustering algorithm is generally used to cluster television videos stored in a database of a terminal background server and users watching the videos according to the categories to which the videos belong, and then the videos are recommended for the users according to the categories to which the clustered users belong and the categories to which the videos belong. However, since the terminal only considers the viewing behavior of the users when calculating the similarity between the users in the prior art, and does not consider other aspects, for example, when calculating the similarity between the users, the similarity between the two users can be determined according to the similarity between the tv video sources respectively viewed by the two users. However, since a large number of television video sources are usually stored in the database of the terminal background server, and the number of videos watched by each user is small, the similarity of videos watched between two users is low, so that the degree of discrimination of the calculated user similarity is not high, and further videos in which the user is interested cannot be correctly recommended for the user.
Disclosure of Invention
The embodiment of the invention provides a method and a device for recommending multimedia data, and solves the problem that a terminal in the prior art cannot accurately recommend a user and a video.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
in a first aspect, a method for recommending multimedia data is provided, including:
acquiring attribute information of multimedia data, wherein the attribute information comprises an identifier of a user, a multimedia data type to which the multimedia data belongs and an identifier of the multimedia data watched by the user;
generating a matrix R and a matrix S corresponding to each user according to the attribute information of the multimedia data, wherein the rows and the columns of the matrix R respectively represent the identification of the user and the identification of the multimedia data, and the element R of the matrix RijRepresenting whether a user i watches multimedia data j, wherein the rows and columns of the matrix S are respectively the multimedia data type and the identification of the multimedia data watched by the user, and the element S of the matrix SvuRepresenting whether the multimedia data v viewed by the user belongs to a multimedia data type u;
obtaining a first similarity between a first user and a second user according to a multimedia data set of the first user and a multimedia data set of the second user obtained from the matrix R, and a second similarity between the first user and the second user according to a matrix S1 corresponding to the first user and a matrix S2 corresponding to the second user, wherein the second user is any user except the first user, and the multimedia data set of the users comprises all multimedia data viewed by the users;
sequencing the similarity between the first user and each of other users, and determining the similar users of the first user according to the number of preset similar users;
determining multimedia data recommended to the first user according to the identification of the similar user of the first user, the matrix S, the similarity between the first user and the similar user of the first user and the number of multimedia data required to be recommended to the first user;
wherein i ∈ 1,2, … …, n; j, v ∈ 1,2, … …, m; u is equal to 1,2, … …, k; the n is the number of users, the m is the number of multimedia data, and the k is the number of multimedia data types.
In a second aspect, an apparatus for recommending multimedia data is provided, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring attribute information of multimedia data, and the attribute information comprises an identifier of a user, a multimedia data type to which the multimedia data belongs and an identifier of the multimedia data watched by the user;
a generating module, configured to generate a matrix R and a matrix S corresponding to each user according to the attribute information of the multimedia data acquired by the acquiring module, where rows and columns of the matrix R respectively represent identifiers of the users and identifiers of the multimedia data, and an element R of the matrix RijRepresenting whether a user i watches multimedia data j, wherein the rows and columns of the matrix S are respectively the multimedia data type and the multimedia watched by the userIdentification of data, element S of said matrix SvuRepresenting whether the multimedia data v viewed by the user belongs to a multimedia data type u;
a calculating module, configured to obtain a similarity between a first user and a second user according to a first similarity between the first user and the second user, which is calculated according to a multimedia data set of the first user and a multimedia data set of the second user obtained from the matrix R generated by the generating module, and a second similarity between the first user and the second user, which is calculated according to a matrix S1 corresponding to the first user and a matrix S2 corresponding to the second user generated by the generating module, where the second user is any user except the first user, and a multimedia data set of a user includes all multimedia data viewed by the user;
the first determining module is used for sequencing the similarity between the first user and each of the other users calculated by the calculating module and determining the similar users of the first user according to the number of preset similar users;
a second determining module, configured to determine, according to the identifier of the similar user of the first user determined by the first determining module, the matrix S generated by the generating module, the similarity between the first user and the similar user of the first user calculated by the calculating module, and the number of multimedia data that needs to be recommended to the first user, multimedia data recommended to the first user;
wherein i ∈ 1,2, … …, n; j, v ∈ 1,2, … …, m; u is equal to 1,2, … …, k; the n is the number of users, the m is the number of multimedia data, and the k is the number of multimedia data types.
According to the method and the device for recommending multimedia data, provided by the embodiment of the invention, a matrix R is generated according to the attribute information of the multimedia data, a corresponding matrix S is generated by each user, the row and the column of the matrix R respectively represent the identification of the user and the identification of the multimedia data, and the element R of the matrix RijRepresenting whether user i views multimedia data j, the momentThe rows and columns of matrix S are respectively the multimedia data type and the identification of the multimedia data viewed by the user, the element S of the matrix SvuAnd calculating the similarity between the first user and other users according to the matrix R, the matrix S1 corresponding to the first user and the matrixes S2 corresponding to other users, and then determining the multimedia data recommended to the first user according to the similarity between the first user and other users, the preset number of similar users and the number of multimedia data required to be recommended to the first user. In this way, through the relevance between the users and the multimedia data represented in the matrix R and the degree of proportion between the multimedia data types watched by each user represented in the matrix S1 corresponding to the first user and the matrix S2 corresponding to the other users, the preference degree of the multimedia data types of the multimedia data watched by the users is more finely distinguished, so that the accuracy of the terminal in recommending the users and the multimedia data is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a method for recommending multimedia data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an apparatus for recommending multimedia data according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of another multimedia data recommendation apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a method for recommending multimedia data, as shown in fig. 1, the method specifically includes the following steps:
101. a recommendation device for multimedia data acquires attribute information of the multimedia data.
The multimedia data in the present invention is, for example, multimedia file data such as video, music, text document, etc. The attribute information of the multimedia data comprises the identification of the user, the identification of the multimedia data watched by the user and the type of the multimedia data to which the multimedia data belongs. For example, if the multimedia data is a movie, the multimedia data types include science fiction, animation, drama, war, antique, comedy, and the like. The type of the multimedia data type in this embodiment may be preset by a technician, and a multimedia data type to which each multimedia data belongs is determined, it should be noted that each multimedia data may belong to one multimedia data type or to multiple multimedia data types at the same time, for example, a certain movie belongs to both an ancient fashion type and a comedy type. Wherein, the attribute information further includes parameter information of the multimedia data including file attribute information, for example, when the multimedia data is a video, the parameter information of the multimedia data includes: video actor names, director names, video types, etc.
The identifier of the user may be a login account of the user or other identifiers that can uniquely represent the user, and in this embodiment, the identifiers of different users are represented in the form of U1, U2, and U3 … … Un; the multimedia data identifier may be a name of the multimedia data or other identifiers that can uniquely represent the multimedia data, and in this embodiment, B1, B2, B3, … …, and Bm are used to represent different multimedia data identifiers; the recording of the user viewing the multimedia data represents a relationship between the user and the viewed multimedia data.
Preferably, in step 101, an update period may be set, and the length of the update period may be set according to an update condition of the multimedia data database, for example, it may be set to be one month, one week or one day, which is not limited by the present invention, and the attribute information of the multimedia data in each update period is obtained and updated in each update period. The following steps of this embodiment are described with reference to the current cycle as an example.
102. The recommendation device of the multimedia data generates a matrix R and a corresponding matrix S for each user according to the attribute information of the multimedia data.
Wherein, the rows and columns of the matrix R represent the user identification and the multimedia data identification respectively, and the element R of the matrix RijIndicating whether the user i views the multimedia data j; the rows and columns of the matrix S are respectively the multimedia data type and the identifier of the multimedia data viewed by the corresponding user, and the element S of the matrix SvuIndicating whether the multimedia data v viewed by the user belongs to the multimedia data type u.
I e is equal to 1,2, … …, n; j, v ∈ 1,2, … …, m; u is equal to 1,2, … …, k; n is the number of users, m is the sum of non-repetitive multimedia data viewed by n users in the recording, and K is the number of multimedia data types, that is, the multimedia data types in this embodiment include K types.
For example, if multimedia data is taken as a video, it is assumed that the sets of users and videos are U ═ U, respectively1,U2,...,UnB ═ B1,B2,...,BmAnd if the user identification is taken as a matrix row and the multimedia data identification is taken as a matrix column, defining a relation matrix between the user and the video as a matrixRijRepresenting user uiWhether video B has been watchedjThe information of (1). If R is on the smart televisionijRepresenting user uiViewed video BjThen R isijNot 1, otherwise Rij0. The meaning of the matrix R is illustrated in table 1, it should be noted that the real matrix R has dimensions of millions, and the following table 1 is merely an illustration of the meaning of the matrix R, and is only an example.
TABLE 1
Illustratively, if the predetermined multimedia data type K is 4, assume that the user U is1The set of videos viewed is B ═ B1,B2,B4,B6}, user U2The set of videos viewed is B ═ B1,B2,B6,B7The meaning of the user matrix S can be illustrated by table 2 and table 3, specifically, table 2 is used to indicate the users U1Table 2 for user U, S12The matrix S2 of (a) is to be noted that, in practical applications, a user may watch tens or hundreds of videos, and only 4 videos are taken as an example for illustration, which is only an example.
TABLE 2
TABLE 3
103. The multimedia data recommending device obtains the similarity between the first user and the second user according to the first similarity between the first user and the second user calculated according to the multimedia data set of the first user and the multimedia data set of the second user obtained from the matrix R and the second similarity between the first user and the second user calculated according to the matrix S1 corresponding to the first user and the matrix S2 corresponding to the second user.
The second user is any other user except the first user, and the multimedia data set of the user comprises all the multimedia data watched by the user. Specifically, the multimedia data recommendation device calculates the similarity between the first user and each of the other users. Preferably, when the recommendation device for multimedia data calculates the similarity between the first user and the second user, the calculated first similarity between the first user and the second user and the calculated second similarity between the first user and the second user are multiplied or added to obtain the similarity between the first user and the second user. It should be noted that the form of multiplication or addition described above is only a preferred form, and in practical application, the similarity may be calculated by other calculation forms, which is not limited herein.
Specifically, the calculation process of the first similarity between the first user and the second user, which is calculated by the multimedia data recommendation device of the multimedia data from the multimedia data set of the first user and the multimedia data set of the second user, obtained from the matrix R in step 103 is as follows:
a1, the multimedia data recommending device obtains the multimedia data set corresponding to each user from the matrix R.
a2, recommending multimedia data according to the first similarity calculation formula, the multimedia data set I of the first user1And a set of multimedia data I of a second user2And calculating a first similarity between the first user and the second user.
Wherein, the second user is any one of the other users except the first user, and the first similarity calculation formula is as follows:
specifically, the calculation process of the second similarity between the first user and the second user, which is calculated by the multimedia data recommendation device in step 103 according to the matrix S1 corresponding to the first user and the matrix S2 corresponding to the second user, is as follows:
b1, the multimedia data recommender calculates a second similarity between the first user and the second user according to a second similarity calculation formula, the matrix S1 corresponding to the first user, and the matrix S2 corresponding to the second user.
The second user is any one of other users except the first user; the second similarity calculation formulaThe x, y ∈ 1,2, … …, k, paIs a vector formed by the accumulated values of all the elements in the column of each multimedia data type in the matrix S1, pbRefers to a vector formed by the accumulated values of all the elements in the column of each multimedia data type in the matrix S2.
Specifically, based on the content described in step 103, the similarity calculation formula between the first user and the second user is:
for example, when calculating the similarity between the first user and the second user, the multimedia data recommendation device needs to obtain the multimedia data preference vector of the matrix S1 according to the matrix S1 corresponding to the first user, and obtain the multimedia data preference vector of the matrix S2 according to the matrix S2 corresponding to the second user, where the multimedia data preference vector of the matrix S1 is in the form of pa(P1,P1,……,Pk) Similarly, the multimedia data preference vector form of the matrix S2 is pb(P1,P1,……,Pk)。
Illustratively, if the matrix S of the user U1 is shown in Table 2, the matrix S2 of the user U2 is shown in Table 3, and the multimedia data set I of the user U1 is shown1(B1,B2,B4,B6) The multimedia data set I of the user U22(B1,B2,B6,B7) The multimedia data preference vector form of the matrix S1 of the user U1 is p (4,3,1,2), and the multimedia data preference vector form of the matrix S2 of the user U2 is p (3,4,2, 1).
Based on the first similarity calculation formula, the first similarity R1 between the user U1 and the user U2 is:
further, based on the second similarity calculation formula, it can be found that the second similarity R2 between the user U1 and the user U2 is:
finally, according to the formula R1 × R2, the similarity R between the user U1 and the user U2 is: r60% 93.3% 56%.
104. The recommendation device of the multimedia data sequences the similarity between the first user and each of the other users, and determines the similar users of the first user according to the preset number of the similar users.
Illustratively, the recommendation device for multimedia data sequences the similarity between the first user and each of the other users, and inserts the sequence into a preset linked list in a descending order, wherein the maximum number of elements contained in the preset linked list is the same as the number of preset similar users.
105. The multimedia data recommending device determines the multimedia data recommended to the first user according to the identification of the similar user of the first user, the matrix S, the similarity between the first user and the similar user of the first user and the number of the multimedia data needing to be recommended to the first user.
Optionally, step 104 specifically includes the following steps:
105a, the multimedia data recommending device generates a matrix Y according to the matrix R, the identifications of the similar users and the identifications of the multimedia data which are not watched by the first user.
Wherein, the rows and columns of the matrix Y respectively represent the identities of the similar users and the identities of the multimedia data that the similar users have viewed and the first user has not viewed.
105b, the multimedia data recommending device calculates the association value of the first user to each multimedia data in the matrix Y according to the similarity between the first user and the similar users and the matrix Y.
Illustratively, the multimedia data recommending device may be implemented by the following processes when calculating the association value of the first user to any multimedia data in the matrix Y: the recommendation device of the multimedia data selects any multimedia data from the multimedia data in the matrix Y, and then accumulates the similarity between the first user and each similar user who watches any multimedia data to obtain the correlation value between the first user and any multimedia data.
105c, the multimedia data recommending device ranks the correlation values between the first user and each multimedia data in the matrix Y, and determines the multimedia data recommended to the first user according to the number of the multimedia data recommended to the first user.
Illustratively, the multimedia data recommendation device sorts the correlation values between the first user and each multimedia data in the matrix Y, and inserts the sorted correlation values into a preset linked list in a descending order, where the maximum number of elements included in the preset linked list is the same as the number of multimedia data to be recommended for the first user.
According to the method for recommending multimedia data provided by the embodiment of the invention, a matrix R is generated according to the attribute information of the multimedia data, a corresponding matrix S is generated by each user, the rows and the columns of the matrix R respectively represent the identifiers of the users and the identifiers of the multimedia data, and the element R of the matrix RijRepresenting whether a user i watches multimedia data j, the rows and columns of the matrix S are respectively the multimedia data type and the identification of the multimedia data watched by the user, and the element S of the matrix SvuWhether the multimedia data v watched by the user belongs to the multimedia data type u or not is indicated, the similarity between the first user and other users is calculated according to the matrix R, the matrix S1 corresponding to the first user and the matrixes S2 corresponding to the other users, and then the pushing to the first user is determined according to the similarity between the first user and the other users, the preset number of similar users and the number of multimedia data needing to be recommended to the first userRecommended multimedia data. In this way, through the relevance between the users and the multimedia data represented in the matrix R and the degree of proportion between the multimedia data types watched by each user represented in the matrix S1 corresponding to the first user and the matrix S2 corresponding to the other users, the preference degree of the multimedia data types of the multimedia data watched by the users is more finely distinguished, so that the accuracy of the terminal in recommending the users and the multimedia data is improved.
An embodiment of the present invention provides a multimedia data recommendation apparatus, which is configured to implement the recommendation method described above, and as shown in fig. 2, the apparatus includes an obtaining module 21, a generating module 22, a calculating module 23, a first determining module 24, and a second determining module 25, where:
the obtaining module 21 is configured to obtain attribute information of the multimedia data, where the attribute information includes an identifier of a user, a multimedia data type to which the multimedia data belongs, and an identifier of the multimedia data viewed by the user.
A generating module 22, configured to generate a matrix R and a matrix S corresponding to each user according to the attribute information of the multimedia data acquired by the acquiring module 21, where rows and columns of the matrix R respectively represent identifiers of the users and identifiers of the multimedia data, and an element R of the matrix RijRepresenting whether a user i watches multimedia data j, the rows and columns of the matrix S are respectively the multimedia data type and the identification of the multimedia data watched by the user, and the element S of the matrix SvuIndicating whether the multimedia data v viewed by the user belongs to the multimedia data type u.
A calculating module 23, configured to obtain a similarity between a first user and a second user according to a first similarity between the first user and the second user, which is calculated according to the multimedia data set of the first user and the multimedia data set of the second user obtained from the matrix R generated by the generating module 22, and a second similarity between the first user and the second user, which is calculated according to the matrix S1 corresponding to the first user and the matrix S2 corresponding to the second user generated by the generating module 22, where the second user is any user except the first user, and the multimedia data set of the user includes all multimedia data viewed by the user.
The first determining module 24 is configured to sort the similarity between the first user and each of the other users calculated by the calculating module 23, and determine the similar users of the first user according to a preset number of similar users.
The second determining module 25 is configured to determine, according to the identifier of the similar user of the first user determined by the first determining module 24, the matrix S generated by the generating module 22, the similarity between the first user and the similar user of the first user calculated by the calculating module 23, and the number of multimedia data that needs to be recommended for the first user, multimedia data recommended to the first user.
Wherein i ∈ 1,2, … …, n; j, v ∈ 1,2, … …, m; u is equal to 1,2, … …, k; n is the number of users, m is the number of multimedia data, and k is the number of multimedia data types.
Optionally, the calculating module 23 is specifically configured to: the first similarity between the first user and the second user, which is calculated from the multimedia data set of the first user and the multimedia data set of the second user obtained from the matrix R generated by the generating module 22, and the second similarity between the first user and the second user, which is calculated according to the matrix S1 corresponding to the first user and the matrix S2 corresponding to the second user generated by the generating module 22, are multiplied to obtain the similarity between the first user and the second user.
Optionally, the calculating module 23 specifically includes, when the first similarity between the first user and the second user is calculated according to the multimedia data set of the first user and the multimedia data set of the second user acquired from the matrix R generated by the generating module 22:
acquiring a multimedia data set corresponding to each user from the matrix R generated by the generating module 22;
according to a first similarity calculation formula and a multimedia data set I of a first user1And a set of multimedia data I of a second user2Calculating a first similarity between a first user and a second user, wherein the second user is any one of other users except the first user;
optionally, when the second similarity between the first user and the second user is calculated according to the matrix S1 corresponding to the first user and the matrix S2 corresponding to the second user, which are generated by the generating module 22, the calculating module 23 specifically includes:
calculating a second similarity between the first user and a second user according to a second similarity calculation formula, the matrix S1 corresponding to the first user generated by the generation module 22, and the matrix S2 corresponding to the second user, where the second user is any one of the users except the first user;
wherein the second similarity calculation formulapaIs a vector formed by the accumulated values of all the elements in the column of each multimedia data type in the matrix S1, pbRefers to a vector formed by the accumulated values of all the elements in the column of each multimedia data type in the matrix S2.
Optionally, the second determining module 25 is specifically configured to:
generating a matrix Y according to the matrix R generated by the generating module 22, the identifiers of the similar users determined by the first determining module 24, and the identifiers of the multimedia data that is not viewed by the first user, wherein rows and columns of the matrix Y respectively represent the identifiers of the similar users and the identifiers of the multimedia data that is viewed by the similar users and is not viewed by the first user;
calculating the correlation value of the first user to each multimedia data in the matrix Y according to the similarity between the first user and the similar users calculated by the calculating module 23 and the matrix Y;
and sequencing the correlation values between the first user and each multimedia data in the matrix Y, and determining the multimedia data recommended to the first user according to the number of the multimedia data recommended to the first user.
Further optionally, when the second determining module 25 calculates the correlation value of the first user to each multimedia data in the matrix Y according to the similarity between the first user and the similar user calculated by the calculating module 23 and the matrix Y, the method specifically includes:
selecting any multimedia data from the multimedia data in the matrix Y;
and accumulating the similarity between the first user and each similar user who watches any multimedia data to obtain the correlation value between the first user and any multimedia data.
Optionally, the first determining module 24 is specifically configured to:
and the similarity between the first user and each of the other users calculated by the calculation module 23 is sorted, and the sorted similarity is inserted into a preset linked list in a descending order, wherein the number of the maximum elements contained in the preset linked list is the same as the number of the preset similar users.
Optionally, as shown in fig. 3, the apparatus further includes a setting module 26, configured to set an update period;
the obtaining module 21 is specifically configured to: and acquiring the attribute information of the multimedia data in each updating period according to the set updating period in each updating period.
According to the multimedia data recommendation device provided by the embodiment of the invention, a matrix R is generated according to the attribute information of the multimedia data, a corresponding matrix S is generated by each user, the rows and the columns of the matrix R respectively represent the user identification and the multimedia data identification, and the element R of the matrix RijRepresenting whether a user i watches multimedia data j, the rows and columns of the matrix S are respectively the multimedia data type and the identification of the multimedia data watched by the user, and the element S of the matrix SvuAnd calculating the similarity between the first user and other users according to the matrix R, the matrix S1 corresponding to the first user and the matrixes S2 corresponding to other users, and determining the multimedia data recommended to the first user according to the similarity between the first user and other users, the preset number of similar users and the number of multimedia data required to be recommended to the first user. Thus by use embodied in the matrix RThe relevance between the users and the multimedia data, the proportion degree of the multimedia data types among the multimedia data watched by each user, which is reflected in the matrix S1 corresponding to the first user and the matrix S2 corresponding to the other users, distinguish the preference degree of the multimedia data types of the multimedia data watched by the users more finely, so that the accuracy of the terminal in recommending the multimedia data and the users is improved.
It will be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the above described functions. For the specific working processes of the system, the apparatus and the unit described above, reference may be made to the corresponding processes in the foregoing method embodiments, and details are not described here again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. And another point. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 in the embodiments of the present application.
Claims (4)
1. A method for recommending multimedia data, comprising:
acquiring attribute information of multimedia data, wherein the attribute information comprises an identifier of a user, a multimedia data type to which the multimedia data belongs and an identifier of the multimedia data watched by the user;
generating a matrix R and a matrix S corresponding to each user according to the attribute information of the multimedia data, wherein the rows and the columns of the matrix R respectively represent the identification of the user and the identification of the multimedia data, and the element R of the matrix RijRepresenting whether a user i watches multimedia data j, wherein the rows and columns of the matrix S are respectively the multimedia data type and the identification of the multimedia data watched by the user, and the element S of the matrix SvuRepresenting whether the multimedia data v viewed by the user belongs to a multimedia data type u;
adding a first similarity between a first user and a second user, which is calculated according to a multimedia data set of the first user and a multimedia data set of the second user, which are obtained from the matrix R, and a second similarity between the first user and the second user, which is calculated according to a matrix S1 corresponding to the first user and a matrix S2 corresponding to the second user, to obtain a similarity between the first user and the second user, wherein the second user is any user except the first user, and the multimedia data set of the user comprises all multimedia data viewed by the user;
sequencing the similarity between the first user and each of other users, and determining the similar users of the first user according to the number of preset similar users;
determining multimedia data recommended to the first user according to the identification of the similar users of the first user, the matrix S corresponding to each user, the similarity between the first user and the similar users of the first user and the number of multimedia data needing to be recommended to the first user;
wherein i ∈ 1,2, … …, n; j, v ∈ 1,2, … …, m; u is equal to 1,2, … …, k; the n is the number of users, the m is the number of multimedia data, and the k is the number of multimedia data types.
2. The method according to claim 1, wherein the calculating the first similarity between the first user and the second user according to the multimedia data set of the first user and the multimedia data set of the second user obtained from the matrix R specifically comprises:
acquiring a multimedia data set corresponding to each user from the matrix R;
according to a first similarity calculation formula, the multimedia data set I of the first user1And a set of multimedia data I of a second user2Calculating a first similarity between the first user and the second user, wherein the second user is any one of other users except the first user;
3. the method according to claim 1, wherein the determining, according to the identifier of the similar user of the first user, the matrix S corresponding to each user, the similarity between the first user and the similar user of the first user, and the number of multimedia data that needs to be recommended for the first user, the multimedia data recommended to the first user specifically includes:
generating a matrix Y according to a matrix R generated by the attribute information of the multimedia data, the identifications of the similar users and the identifications of the multimedia data which are not watched by the first user, wherein the rows and columns of the matrix Y respectively represent the identifications of the similar users and the identifications of the multimedia data which are watched by the similar users and are not watched by the first user;
calculating the correlation value of the first user to each multimedia data in the matrix Y according to the similarity between the first user and the similar users and the matrix Y;
and sequencing the correlation values between the first user and each multimedia data in the matrix Y, and determining the multimedia data recommended to the first user according to the number of the multimedia data recommended to the first user.
4. The method according to claim 3, wherein the calculating, according to the similarity between the first user and the similar user and a matrix Y, the association value of the first user to each multimedia data in the matrix Y specifically comprises:
selecting any multimedia data from the multimedia data in the matrix Y;
and accumulating the similarity between the first user and each similar user who watches any multimedia data to obtain the correlation value between the first user and any multimedia data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810034582.3A CN108108491B (en) | 2015-07-23 | 2015-07-23 | Multimedia data recommendation method and device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510438746.5A CN105095442B (en) | 2015-07-23 | 2015-07-23 | A kind of recommendation method and device of multi-medium data |
CN201810034582.3A CN108108491B (en) | 2015-07-23 | 2015-07-23 | Multimedia data recommendation method and device |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510438746.5A Division CN105095442B (en) | 2015-07-23 | 2015-07-23 | A kind of recommendation method and device of multi-medium data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108108491A CN108108491A (en) | 2018-06-01 |
CN108108491B true CN108108491B (en) | 2021-07-30 |
Family
ID=54575879
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810034582.3A Active CN108108491B (en) | 2015-07-23 | 2015-07-23 | Multimedia data recommendation method and device |
CN201510438746.5A Active CN105095442B (en) | 2015-07-23 | 2015-07-23 | A kind of recommendation method and device of multi-medium data |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510438746.5A Active CN105095442B (en) | 2015-07-23 | 2015-07-23 | A kind of recommendation method and device of multi-medium data |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN108108491B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512252B (en) * | 2015-12-01 | 2019-03-05 | 海信集团有限公司 | The method and device of correlation between a kind of acquisition multi-medium data |
CN105574198B (en) * | 2015-12-28 | 2019-12-06 | 海信集团有限公司 | column recommendation method and device |
CN105404700B (en) * | 2015-12-30 | 2019-04-16 | 山东大学 | A kind of video column recommendation system and recommended method based on collaborative filtering |
CN105589916B (en) * | 2016-01-11 | 2020-05-08 | 西华大学 | Method for extracting explicit and implicit interest knowledge |
CN105868317B (en) * | 2016-03-25 | 2017-04-12 | 华中师范大学 | Digital education resource recommendation method and system |
CN105956061B (en) * | 2016-04-26 | 2020-01-03 | 海信集团有限公司 | Method and device for determining similarity between users |
CN106294800A (en) * | 2016-08-16 | 2017-01-04 | 武汉斗鱼网络科技有限公司 | Method and system recommended by direct broadcasting room based on weighting k neighbour scoring |
CN106534984B (en) * | 2016-12-23 | 2020-07-14 | 深圳Tcl数字技术有限公司 | Television program pushing method and device |
CN106604068B (en) * | 2016-12-30 | 2019-11-05 | 中广热点云科技有限公司 | A kind of method and its system of more new media program |
CN109063080B (en) * | 2018-07-25 | 2022-01-21 | 北京小度互娱科技有限公司 | Video recommendation method and device |
CN111711838B (en) * | 2020-06-23 | 2023-03-31 | 广州酷狗计算机科技有限公司 | Video switching method, device, terminal, server and storage medium |
CN112559856B (en) * | 2020-12-04 | 2023-06-02 | 中国联合网络通信集团有限公司 | Application ordering method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103327111A (en) * | 2013-07-01 | 2013-09-25 | 百度在线网络技术(北京)有限公司 | multimedia file recommendation method, system thereof and server |
CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103327045B (en) * | 2012-03-21 | 2017-03-22 | 腾讯科技(深圳)有限公司 | User recommendation method and system in social network |
CN104035934B (en) * | 2013-03-06 | 2019-01-15 | 腾讯科技(深圳)有限公司 | A kind of method and device that multimedia messages are recommended |
CN104123315B (en) * | 2013-04-28 | 2018-01-30 | 北京音之邦文化科技有限公司 | The recommendation method and recommendation server of multimedia file |
-
2015
- 2015-07-23 CN CN201810034582.3A patent/CN108108491B/en active Active
- 2015-07-23 CN CN201510438746.5A patent/CN105095442B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103327111A (en) * | 2013-07-01 | 2013-09-25 | 百度在线网络技术(北京)有限公司 | multimedia file recommendation method, system thereof and server |
CN103942712A (en) * | 2014-05-09 | 2014-07-23 | 北京联时空网络通信设备有限公司 | Product similarity based e-commerce recommendation system and method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN105095442B (en) | 2018-04-24 |
CN105095442A (en) | 2015-11-25 |
CN108108491A (en) | 2018-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108108491B (en) | Multimedia data recommendation method and device | |
CN106331778B (en) | Video recommendation method and device | |
CN105956149B (en) | method and device for recommending default search terms | |
US9553922B1 (en) | Media event based social networking interfaces | |
CN105677715B (en) | A kind of video recommendation method and device based on multi-user | |
CN106326391B (en) | Multimedia resource recommendation method and device | |
US20130297611A1 (en) | Method and apparatus for providing temporal context for recommending content for consumption by a user device | |
CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
CN105163142B (en) | A kind of user preference determines method, video recommendation method and system | |
CN108197336B (en) | Video searching method and device | |
CN103686382A (en) | Program recommendation method | |
CN107608990B (en) | Live broadcast personalized recommendation method | |
CN105224576A (en) | A kind of video display intelligent recommendation method | |
CN103686231A (en) | Method and system for integrated management, failure replacement and continuous playing of film | |
CN104615741B (en) | Cold-start project recommendation method and device based on cloud computing | |
CN106131703A (en) | A kind of method of video recommendations and terminal | |
JP2008542870A (en) | Method and apparatus for estimating the overall interest of a group of users for content | |
CN105718510B (en) | A kind of multi-medium data recommended method and device | |
Xu et al. | Catch-up TV recommendations: show old favourites and find new ones | |
JP2011095814A (en) | Device for recommending items suitable for user preferences | |
CN102426577A (en) | Information processing apparatus, information processing system, information processing method, and program | |
CN110598047A (en) | Movie and television information recommendation method and device, electronic equipment and storage medium | |
CN109063080B (en) | Video recommendation method and device | |
CN106534984B (en) | Television program pushing method and device | |
CN109640128B (en) | Television user watching behavior feature extraction method and system |
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 |