CN111291217A - Content recommendation method and device, electronic equipment and computer readable medium - Google Patents
Content recommendation method and device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN111291217A CN111291217A CN202010144164.7A CN202010144164A CN111291217A CN 111291217 A CN111291217 A CN 111291217A CN 202010144164 A CN202010144164 A CN 202010144164A CN 111291217 A CN111291217 A CN 111291217A
- Authority
- CN
- China
- Prior art keywords
- matrix
- interest
- user
- content
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 239000011159 matrix material Substances 0.000 claims abstract description 189
- 238000004891 communication Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 10
- 239000013598 vector Substances 0.000 description 9
- 230000009471 action Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
Abstract
A content recommendation method, device, electronic equipment and computer readable medium, the application obtains the historical click record of the media content which is interested by the user; calculating the interest breadth degree of the user on the media content based on the historical click records; calculating a customized recommended content matrix according to the wide interest degree of the user and a preset standard recommended content matrix, wherein the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of standard recommended content; and selecting recommended contents from the plurality of standard recommended contents based on the recommendation priority to achieve the purpose of calculating personalized interest extensive degrees aiming at different interest extensive degrees of the media contents of the user, calculating the priority of the standard recommended contents by combining the interest extensive degrees with a preset standard recommended content matrix, and finally selecting the recommended contents meeting the user interest extensive degrees from the plurality of standard recommended contents based on the priority, thereby realizing flexible personalized recommendation and improving the user experience.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a content recommendation method and apparatus, an electronic device, and a computer-readable medium.
Background
With the advent of the big data era, people are full of different types of recommended contents in daily life, and platforms of different industries such as application software, video platforms, shopping platforms and the like are dedicated to recommending contents to users so as to mine new points of interest of the users. For example: in the video platform, a video recommendation system can recommend videos of the same type according to historical browsing of users, and then recommend videos of related types in order to meet the diversity requirements of the users.
However, the interest ranges of different users are different, for example, some users have wide interests, like various types of related videos pushed by the recommendation system, and some users have single interests, and only like the same type of videos pushed by the recommendation system, but the current recommendation system does not consider that the interest ranges of different users are different, and uniformly recommends videos selected in advance, so that recommended content is rigid, and user experience is poor.
Disclosure of Invention
The embodiment of the invention aims to provide a content recommendation method, a content recommendation device, electronic equipment and a computer readable medium, so as to solve the technical problems that recommended content is rigid and user experience is poor due to the fact that different interest ranges of different users are not considered in the current recommendation system and videos selected in advance are recommended in a unified mode. The specific technical scheme is as follows:
in a first aspect of this application, there is provided a content recommendation method, including:
if a content recommendation request of a user is received, acquiring a historical click record of the user;
calculating the interest breadth degree of the user in the media content based on the historical click records;
calculating a customized recommended content matrix according to the interest breadth degree of the user and a preset standard recommended content matrix, wherein the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of the standard recommended content;
and selecting recommended content from a plurality of standard recommended contents based on the recommendation priority.
Optionally, the step of calculating the degree of interest of the user in the media content based on the historical click records comprises:
determining the number of types of media contents which are interested by the user and the attention degree corresponding to each type according to the historical click records;
and calculating the interest popularity degree according to the number of the categories and the attention degree corresponding to each category.
Optionally, the formula for calculating the interest popularity according to the number of categories and the attention degree corresponding to each category is as follows:
wherein, WuRepresenting said degree of interest, M representing said number of categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
Optionally, the step of calculating a customized recommended content matrix according to the wide interest degree of the user and a preset standard recommended content matrix includes:
reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
calculating the product of the interest popularity degree and the similarity matrix to obtain a customized similarity matrix;
and generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix.
In a second aspect of the present application, there is also provided a content recommendation apparatus, including:
the acquisition module is used for acquiring the historical click record of the user if the content recommendation request of the user is received;
the first calculation module is used for calculating the interest breadth degree of the user on the media content based on the historical click record;
the second calculation module is used for calculating a customized recommended content matrix according to the wide interest degree of the user and a preset standard recommended content matrix, the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for representing the recommendation priority of the standard recommended content;
and the selecting module is used for selecting recommended contents from the standard recommended contents based on the recommendation priority.
Optionally, the first computing module comprises:
the determining unit is used for determining the number of the media contents which are interested by the user and the attention degree corresponding to each type according to the historical click record;
a first calculating unit for calculating the interest popularity degree according to the number of categories and the attention degree corresponding to each category.
Optionally, the formula for calculating the interest popularity according to the number of categories and the attention degree corresponding to each category is as follows:
wherein, WuRepresenting said degree of interest, M representing said number of categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
Optionally, the second computing module comprises:
the decomposition unit is used for reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
the second calculation unit is used for calculating the product of the interest popularity degree and the similarity matrix to obtain a customized similarity matrix;
and the generating unit is used for generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix.
In a third aspect of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor adapted to perform the method steps of any of the above first aspects when executing a program stored in the memory.
In a fourth aspect implemented by the present application, there is also provided a computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the method of any of the above first aspects.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:
the method provided by the embodiment of the application comprises the steps of obtaining a historical click record of a user if a content recommendation request of the user is received; calculating the interest breadth degree of the user in the media content based on the historical click records; calculating a customized recommended content matrix according to the interest breadth degree of the user and a preset standard recommended content matrix, wherein the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of the standard recommended content; and selecting recommended content from a plurality of standard recommended contents based on the recommendation priority.
According to the method and the device, firstly, historical click records of a user are obtained, then the interest breadth degree is calculated based on the historical click records, the personalized interest breadth degree is calculated according to different interest breadth degrees of the user on media contents, then the interest breadth degree is combined with a preset standard recommended content matrix to calculate the priority of standard recommended contents, and finally the recommended contents meeting the user interest breadth degree are selected from a plurality of standard recommended contents based on the priority, so that flexible personalized recommendation is achieved, and user experience is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
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, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a content recommendation method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of step S102 in fig. 1 according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a standard recommended content matrix establishment process provided in an embodiment of the present application;
fig. 4 is a schematic flowchart of step S103 in fig. 1 according to an embodiment of the present disclosure;
fig. 5 is a schematic flowchart of step S104 in fig. 1 according to an embodiment of the present disclosure;
fig. 6 is a block diagram of a content recommendation apparatus according to an embodiment of the present invention;
fig. 7 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.
At present, people are full of different types of recommended contents in daily life, platforms of different industries such as application software, video platforms and shopping platforms are dedicated to recommending contents to users at a time to mine new interest points of the users, most multimedia platforms recommend some preset media contents to the users, however, the interest ranges of different users are different, for example, some users have wide interests, like various types of related videos (such as life types, military types, science and technology types and the like) pushed by a recommendation system, some users have single interests, and only like the same type of videos pushed by the recommendation system, so that the current recommendation system uniformly wants the users to recommend videos selected in advance, the recommended contents are rigid, the recommended contents do not meet the requirements of the users, and poor user experience is caused. Based on this, an embodiment of the present application provides a content recommendation method, as shown in fig. 1, where the content recommendation method includes:
step S101, if a content recommendation request of a user is received, acquiring a historical click record of the user;
in the embodiment of the present application, the content recommendation request may be a request for obtaining recommended content, and in practical applications, whether the recommended content meets the interest of the user or not is directly determined as the quality of the recommended content, so the embodiment of the present application first obtains the historical click record of the user to determine the direction of interest of the user.
The manner of obtaining the historical click record of the user may be determined according to actual situations, for example: in the practical application of the video website platform, after a user clicks a video, the video classification label of the clicked video of the user is recorded in the background and is stored in the background, so that the media content which the user is interested in is analyzed. The above embodiments are merely examples, and the embodiments of the present application are not limited thereto.
Step S102, calculating the interest extensive degree of the user to the media content based on the historical click record;
in the embodiments of the present application, the media content refers to a medium for transmitting information, which refers to a means, channel, carrier, intermediary or technical means for people to transmit information and obtain information, and may also be regarded as any technical means for realizing information transmission from an information source to a recipient, for example: audio, video, and other forms of conveying information. The wide degree of interest indicates the tendency of the user to the media content, for example, some users have a high wide degree of interest and represent the media content of different topics (military topics, life topics, scientific topics, fun topics, comprehensive topics, etc.) that the user likes, while some users have a low wide degree of interest and represent the media content that the user likes is relatively single.
In this step, the method for calculating the interest popularity through the history click record may be determined according to actual situations, for example, the history click record includes the user history browsing videos and classification tags corresponding to the videos, and the probability that the user browses videos of each category may be calculated through a probability statistics method, so as to determine whether the videos browsed by the user are of the same category or of various categories, and further determine the interest popularity of the user in the media content.
Step S103, a customized recommended content matrix is calculated according to the interest wide degree of the user and a preset standard recommended content matrix, the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of the standard recommended content;
in the embodiment of the application, the standard recommended content may be preset manually, and the application is used for representing the recommendation priority of each standard recommended content by establishing a standard recommended content matrix, wherein the recommendation priority may be preset manually.
In practical applications, for example: a certain video platform selects 10 competitive videos as recommended contents for a user, and establishes a standard recommended content matrix for representing the recommended content recommended priority, wherein a plurality of elements exist in the matrix for representing certain standard recommended contents, and each element in the matrix is used for representing the recommended priority of the standard recommended contents, so that whether the recommended contents meet the recommended conditions or not can be determined by calculating the recommended priorities of the plurality of elements for representing certain standard recommended contents.
In the step, the way of calculating the customized recommended content matrix according to the wide degree of interest and the preset standard recommended content matrix can be determined according to the actual situation, the wide degree of interest is introduced into the standard recommended content matrix according to the preset algorithm, the customized recommended content matrix can be obtained, the personalized interest breadth degree is calculated according to the different interest breadth degrees of the users to the media content, the interest breadth degree is combined with the preset standard recommended content matrix to calculate the priority of the standard recommended content, the standard content recommended matrix containing the priorities of a plurality of standard recommended contents is obtained, and finally the priority of the standard recommended content is referred, the recommended content meeting the wide degree of the user interest can be selected from the plurality of standard recommended contents, so that flexible personalized recommendation is realized, and the user experience is improved.
And step S104, selecting recommended content from the standard recommended content based on the recommendation priority.
In the embodiment of the application, recommended contents are screened from a plurality of standard recommended contents and are pushed to a user, the wide interest degree of the user on media contents is calculated through historical information such as historical browsing records of the user, then the wide interest degree is combined with a standard content recommendation matrix representing a plurality of standard recommended contents to obtain a customized recommended content matrix representing recommended content recommendation priority, therefore, the priority of each standard recommended content is calculated according to the wide interest degree of the user, finally, the recommended contents meeting the wide interest degree of the user can be selected from the standard recommended contents based on the recommendation priority, the problem that the contents pushed by a traditional recommendation system are single and rigid is solved, the recommended contents are more suitable for the preference of the user, and the user experience is improved.
In another embodiment of the present application, a specific implementation manner of calculating the interest level of the user based on the historical click record is provided, as shown in fig. 2, in step S102, the calculating the interest level of the user in the media content based on the historical click record includes:
step S201, determining the number of types of media contents which are interested by a user and the attention degree corresponding to each type according to the historical click record;
in this embodiment of the present application, the number of types of media content may be the number of classification tags corresponding to the media content browsed by a user, in practical applications, each media content may correspond to one primary classification tag, where the primary classification tag is used to indicate a largest partition of the media content, such as a military subject, an academic subject, a funny subject, and the like, each time the user browses one media content, a background records that the more browsing times of a certain subject a, the more attention paid to the subject, the less attention paid to a certain subject B, and the less attention paid to the subject, and a history click record may be used to indicate a history browsing record of the user, so that the number of types of media content interested by the user and the attention paid to each type are extracted from the history click record.
Step S202, calculating the interest extensive degree according to the number of the categories and the attention degree corresponding to each category.
In the embodiment of the present application, by counting the number of categories of media content in which a user is interested and the attention degree corresponding to each category, the interest breadth degree of the user can be calculated, for example: according to the historical click record, it may be determined that the user has 25% attention to the type a content, 15% attention to the type B content, 35% attention to the type C content, and 25% attention to the type D content, and the interest popularity that may be calculated according to a preset statistical formula, further, in another embodiment of the present invention, in step S202, the formula for calculating the interest popularity according to the number of categories and the attention corresponding to each type is as follows:
wherein, WuRepresents the aboveThe degree of interest, M representing the number of said categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
In the embodiment of the application, the number of the categories and the attention degree corresponding to each type are brought into the formula established based on the information entropy concept, the interest wide degree can be calculated, and the interest wide degree calculation formula established based on the information entropy concept only focuses on the possibility of the user for browsing the media content, namely the interest wide degree, because the information has uncertainty, namely the probability of the user for browsing the media content of each type has uncertainty, the obtained W isuRanging between 0 and 1.
According to the method and the device, the interest range of the user for the interested media content is determined by calculating the interest range of the user, and the media content which is fit with the interest can be recommended to the user according to different interests of the user.
In another embodiment provided by the present application, regarding the establishment manner of the standard physical examination content matrix in the media content recommendation system, optionally, as shown in fig. 3, the establishment process of the standard physical examination content matrix includes:
step S301, obtaining a plurality of standard recommended contents and a feature vector corresponding to each standard recommended content;
in this step, the feature vector corresponding to the standard recommended content is used to represent a vector of content attributes of the standard recommended content, and in practical applications, the standard recommended content may be recommended videos preset by a video website, where each video corresponds to a feature vector used to represent a subject type of the video, for example: and designing the fun elements and the synthesis elements by the video, wherein the feature vectors of the video are biased to the fun elements and the synthesis elements in the subject type space.
Step S302, aiming at each standard recommended content, calculating a relevance score for expressing the relevance degree between the standard recommended content and the historical click record according to the standard recommended content and the historical click record to obtain a plurality of relevance scores;
in this step, the standard recommended content is preset, and the historical click record is obtained according to the media content that the user is interested in browsing, so a relevance score can be calculated through the standard recommended content and the historical click record, and the relevance score can be used for the relevance degree to be the type relevance degree between the standard recommended content and the historical click record.
Step S303, sequencing a plurality of relevance scores according to the sequence of the relevance scores from big to small to obtain a standard recommended content sequence;
in this step, after calculating the relevance score between each standard recommended content and the historical click record, a plurality of the standard recommended contents are sorted according to the descending order of the relevance scores, for example: and if the relevance score of the video A is 90 scores, the relevance score of the video B is 68 scores, and the relevance score of the video C is 88 scores, the three standard recommended contents are sequenced according to the descending order of the relevance scores to obtain {90, 88 and 68}, wherein each relevance score corresponds to a video number.
Step S304, generating a correlation matrix according to the standard recommended content sequence;
in this step, since the correlation matrix is generated from the standard recommended content sequence, the correlation matrix may represent the degree of correlation between the standard recommended content and the historical clicks of the media content of interest to the user.
In this step, a specific operation manner of generating the correlation matrix according to the standard recommended content sequence may be determined according to an actual situation, and this is not specifically limited in this embodiment of the present application.
Step S305, calculating the product of the feature vectors of any two standard recommended contents to obtain a plurality of similarity scores for representing the similarity degree of the two standard recommended contents;
in this step, the feature vector corresponding to each standard recommended content is used to represent the vector of the content attribute of the standard recommended content, so the product of the feature vectors of any two standard recommended contents is calculated, and the obtained similarity score is used to represent the degree of similarity between the two standard recommended contents, where any two selected standard recommended contents may be different or the same.
Step S306, generating a similarity matrix according to the similarity scores;
in this step, since the similarity matrix is generated from a plurality of the similarity scores, the similarity matrix may represent the degree of similarity between any two standard recommended contents. The specific operation manner for generating the similarity matrix according to the plurality of similarity scores may be determined according to actual situations, and this is not specifically limited in the embodiment of the present application.
Step S307, generating the standard recommended content matrix according to the correlation matrix and the similarity matrix;
in this step, the standard recommended content may be set manually in advance, a correlation matrix for representing the degree of correlation between the standard recommended content and the historical click record of the media content of interest to the user may be calculated according to the historical click record of interest to the user and the standard recommended content, that is, the degree of interest to the standard recommended content by the user may be expressed, then the degree of correlation between any two standard recommended contents may be represented by calculating a similarity matrix for representing any two standard recommended contents, and finally the standard recommended content matrix is generated according to the correlation matrix and the similarity matrix, so that the purpose of calculating a recommendation priority for each standard recommended content is achieved, and the standard recommended content meeting the interest of the user may be selected.
Based on the established standard content recommendation matrix, the customized recommended content matrix fitting the interest of the user can be calculated by combining the interest breadth degree of the user, in another embodiment provided by the present application, a specific implementation manner for calculating the customized recommended content matrix according to the interest breadth degree of the user and a preset standard recommended content matrix is provided, as shown in fig. 4, step S103, the step of calculating the customized recommended content matrix according to the interest breadth degree of the user and the preset standard recommended content matrix includes:
step S401, reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
in the embodiment of the present application, in order to introduce the pre-calculated interest breadth degree of the user into the standard recommended content matrix, the standard recommended content matrix needs to be subjected to matrix inverse decomposition to obtain the correlation matrix and the similarity matrix, and the specific manner in which the standard recommended content matrix consists of the correlation matrix and the similarity matrix may refer to the contents of the above embodiment.
Step S402, calculating the product of the interest extensive degree and the similarity matrix to obtain a customized similarity matrix;
in the embodiment of the application, the product of the interest popularity degree and the similarity matrix is calculated, the interest popularity degree of the user is taken as the weight and introduced into the similarity matrix to obtain the customized similarity matrix, and the purpose of recommending the priority corresponding to the content according to the interest popularity degree of the user is achieved, wherein when the interest popularity degree W is used as the interest popularity degree W, the priority corresponding to the standard recommendation content is adjusteduWhen the interest degree is close to 1, the types of the media contents which indicate the interest of the user are wider, that is, the user wants to see more recommended contents of different types, so the interest degree W is wideruWhen the similarity matrix is close to 1, the similarity matrix is also close to be unchanged with the original matrix, and the media content recommended to the user is basically consistent with the original preset matrix; when the interest is extensive WuWhen the value is close to 0, the interest of the user is more concentrated, the preference on the similarity is weaker, namely the customized similarity matrix hardly works, and the type of the final recommended content is more concentrated.
Step S403, generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix;
in the embodiment of the present application, a specific implementation manner of generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix may be determined according to an actual situation, for example: optionally, in this embodiment of the present application, a specific implementation manner for generating a customized recommended content matrix according to a customized similarity matrix and a correlation matrix is provided, and step S402 is performed by generating a formula of the customized recommended content matrix according to the customized similarity matrix and the correlation matrix as follows:
θ∈[0,1]
wherein S represents the customized similarity matrix,
representing the correlation matrix, theta representing a preset adjustment parameter between correlation and similarity, RCRepresents the relevance score, WuRepresents the degree of said interest, LN×NRepresenting elements in the customized recommended content matrix.
The set value of theta can be a preset value, and is used for adjusting the relationship between the relevance and the similarity of the standard recommended content, the smaller theta is, the more the recommended result is biased towards the similarity, the more the media content recommended to the user is, the larger theta is, the more the recommended result is biased towards the relevance, the type of the media content recommended to the user is single, the specific theta set value can be determined according to the actual situation, and the embodiment of the application is not specifically limited to this.
In the embodiment of the present application, a customized recommended content matrix is established by using a DPP (deterministic Point Process) diversity control algorithm, and the purpose of calculating the standard recommended content priority in combination with the interest popularity of the user is achieved by introducing the interest popularity of the user into the customized similarity matrix S in the embodiment of the present application.
In practical application, when the type of the media content of interest of the user is wide, the calculated wide interest degree WuThen, the value is close to 1, at this time, the L matrix is similar to the original L matrix, and no change occurs, that is, the media content recommended to the user at this time is basically consistent with the original preset value; when the type of the media content of interest of the user is single, the calculated interest breadth degree WuWhen the value is close to 0, the interest of the user is more concentrated, the preference on the similarity is weaker, namely the customized similarity matrix hardly works, and the type of the final recommended content is more concentrated.
In the embodiment provided by the present application, optionally, as shown in fig. 5, the step S104 of selecting a recommended content from the plurality of standard recommended contents based on the recommendation priority includes:
step S501, randomly acquiring K from the customized recommended content matrix2Constructing a sub-matrix by the elements to obtain a plurality of sub-matrices, wherein K is the number of preset recommended contents;
in this embodiment of the application, N is a preset recommended content number, for example, if a video website wants to recommend 3 video contents to a user, N is 3, 9 elements are randomly obtained from a customized recommended content matrix, and preferably, 9 elements with high relevance are selected from the customized recommended content matrix, that is, the elements with the same row number and column number are selected to represent the recommendation score of a certain video, for example: selecting elements of the first row and the first column to construct a submatrix A, and then recommending contents represented by the submatrix A and the Rc1The corresponding standard recommended content is the same.
In one practical application, setting N to be 3, randomly acquiring 9 elements from the customized recommended content matrix, and selecting the rows 1, 3 and 5 and the elements positioned in the columns 1, 3 and 5Element (ii) to obtain L11、L13、L15、L31、L33、L35、L51、L53、L55And constructing a submatrix by using the elements to obtain the representation Rc1Corresponding standard recommended content, Rc2Corresponding standard recommended content and Rc3A sub-matrix of recommendation scores for corresponding standard recommended content.
Step S502, aiming at each sub-matrix, calculating a determinant value of the sub-matrix according to the recommended priority corresponding to each element in the sub-matrix;
in the embodiment of the application, a recommendation score is calculated for the randomly extracted standard recommended content by calculating the determinant value of the submatrix, so as to determine the recommended optimal scheme.
Step S503, determining the submatrix with the maximum determinant value as a recommended content matrix;
in the embodiment of the application, if the customized recommendation matrix is an M-order matrix, N recommendation contents are selected from the M-order matrix, and the customized recommendation matrix exists
In such a case, the embodiment of the present application uses the formula:
calculating to obtain a submatrix with the maximum determinant value, and taking the submatrix as a recommended content matrix, wherein Y is a subset with the length of N (the number of videos is finally deduced, such as 10) and belongs to the set C; l isYIs a sub-matrix formed by rows and columns corresponding to Y in the L matrix (for example, Y ═ {1,2}, then LY ═ L11, L12; L21, L22)])；det(LY) Represents LYThe determinant value of (a).
Step S504, determining the recommended content according to the standard recommended content corresponding to the K elements of the recommended content matrix.
In the embodiment of the present application, for example, the elements in rows 1, 3 and 5 and in columns 1, 3 and 5 are selected to obtain L11、L13、L15、L31、L33、L35、L51、L53、L55And constructing a sub-matrix by using the elements, wherein the standard recommended content sequence is obtained by sequencing a plurality of relevance scores according to the sequence of the relevance scores from large to small, so that L11、L13、L15、、L31、L51For characterizing the 1 st video in the set C, and so on, L13、L31、L33、L35、L53For representing the 3 rd video in the set C, L15、L35、L51、L53、L55Representing the 5 th video in set C.
The embodiment of the application is based on a DPP algorithm solving principle, the customized standard matrix is solved, the determinant of the submatrix is calculated based on each element used for representing the video recommendation priority in the matrix, the optimal solution is solved from the customized recommendation matrix constructed based on the wide degree of user interest, namely, the recommendation content fitting the user interest is obtained, and the effect of improving the user experience is achieved.
In another embodiment provided by the present application, there is also provided a content recommendation apparatus, as shown in fig. 6, including:
the acquisition module 01 is used for acquiring historical click records of media contents which are interested by a user;
a first calculating module 02, configured to calculate a degree of interest of the user in the media content based on the historical click record;
the second calculating module 03 is configured to calculate a customized recommended content matrix according to the wide interest degree of the user and a preset standard recommended content matrix, where the same position element in the standard recommended content matrix and the customized recommended content matrix corresponds to the same standard recommended content, and a value of each element in the customized recommended content matrix is used to represent a recommendation priority of the standard recommended content;
and the selecting module 04 is configured to select recommended content from the plurality of standard recommended content based on the recommendation priority.
In another embodiment provided herein, the first computing module includes:
the determining unit is used for determining the number of the media contents which are interested by the user and the attention degree corresponding to each type according to the historical click record;
a first calculating unit for calculating the interest popularity degree according to the number of categories and the attention degree corresponding to each category.
Optionally, the formula for calculating the interest popularity according to the number of categories and the attention degree corresponding to each category is as follows:
wherein, WuRepresenting said degree of interest, M representing said number of categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
In another embodiment provided herein, the second computing module includes:
the decomposition unit is used for reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
the second calculation unit is used for calculating the product of the interest popularity degree and the similarity matrix to obtain a customized similarity matrix;
and the generating unit is used for generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix.
The embodiment of the present invention further provides an electronic device, as shown in fig. 7, which includes a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 complete mutual communication through the communication bus 1140,
a memory 1130 for storing computer programs;
the processor 1110, when executing the program stored in the memory 1130, implements the following steps:
acquiring historical click records of media contents which are interested by a user; calculating the interest breadth degree of the user in the media content based on the historical click records; calculating a customized recommended content matrix according to the interest breadth degree of the user and a preset standard recommended content matrix, wherein the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of the standard recommended content; and selecting recommended content from a plurality of standard recommended contents based on the recommendation priority.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete gate or transistor logic device, or discrete hardware components.
In still another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to perform the content recommendation method described in any of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the content recommendation method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for recommending content, the method comprising:
if a content recommendation request of a user is received, acquiring a historical click record of the user;
calculating the interest breadth degree of the user in the media content based on the historical click records;
calculating a customized recommended content matrix according to the interest breadth degree of the user and a preset standard recommended content matrix, wherein the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for expressing the recommendation priority of the standard recommended content;
and selecting recommended content from a plurality of standard recommended contents based on the recommendation priority.
2. The content recommendation method according to claim 1, wherein the step of calculating the user's interest level of the media content based on the historical click records comprises:
determining the number of types of media contents which are interested by the user and the attention degree corresponding to each type according to the historical click records;
and calculating the interest popularity degree according to the number of the categories and the attention degree corresponding to each category.
3. The content recommendation method according to claim 2, wherein the formula for calculating the degree of interest based on the number of categories and the degree of interest corresponding to each category is as follows:
wherein, WuRepresenting said degree of interest, M representing said number of categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
4. The content recommendation method according to claim 1, wherein the step of calculating a customized recommended content matrix according to the user's interest breadth and a preset standard recommended content matrix comprises:
reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
calculating the product of the interest popularity degree and the similarity matrix to obtain a customized similarity matrix;
and generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix.
5. A content recommendation apparatus characterized by comprising:
the acquisition module is used for acquiring the historical click record of the user if the content recommendation request of the user is received;
the first calculation module is used for calculating the interest breadth degree of the user on the media content based on the historical click record;
the second calculation module is used for calculating a customized recommended content matrix according to the wide interest degree of the user and a preset standard recommended content matrix, the same position elements in the standard recommended content matrix and the customized recommended content matrix correspond to the same standard recommended content, and the value of each element in the customized recommended content matrix is used for representing the recommendation priority of the standard recommended content;
and the selecting module is used for selecting recommended contents from the standard recommended contents based on the recommendation priority.
6. The content recommendation device according to claim 5, wherein the first calculation module comprises:
the determining unit is used for determining the number of the media contents which are interested by the user and the attention degree corresponding to each type according to the historical click record;
a first calculating unit for calculating the interest popularity degree according to the number of categories and the attention degree corresponding to each category.
7. The content recommendation apparatus according to claim 6, wherein the formula for calculating the degree of interest based on the number of categories and the degree of interest corresponding to each category is as follows:
wherein, WuRepresenting said degree of interest, M representing said number of categories, NuiIndicates the degree of attention, N, of type iuAnd representing the sum of the attention degrees corresponding to each type.
8. The content recommendation device according to claim 5, wherein the second calculation module comprises:
the decomposition unit is used for reversely decomposing the standard recommended content matrix to obtain a correlation matrix and a similarity matrix;
the second calculation unit is used for calculating the product of the interest popularity degree and the similarity matrix to obtain a customized similarity matrix;
and the generating unit is used for generating the customized recommended content matrix according to the customized similarity matrix and the correlation matrix.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 4 when executing a program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144164.7A CN111291217B (en) | 2020-03-04 | 2020-03-04 | Content recommendation method, device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010144164.7A CN111291217B (en) | 2020-03-04 | 2020-03-04 | Content recommendation method, device, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291217A true CN111291217A (en) | 2020-06-16 |
| CN111291217B CN111291217B (en) | 2024-02-02 |
Family
ID=71024723
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010144164.7A Active CN111291217B (en) | 2020-03-04 | 2020-03-04 | Content recommendation method, device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291217B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112351345A (en) * | 2020-11-04 | 2021-02-09 | 深圳Tcl新技术有限公司 | Control method and device of recommended content, smart television and storage medium |
| CN112395496A (en) * | 2020-10-22 | 2021-02-23 | 上海众源网络有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102866997A (en) * | 2011-07-05 | 2013-01-09 | 腾讯科技（深圳）有限公司 | Method and device for processing user data |
| US20160371274A1 (en) * | 2015-06-18 | 2016-12-22 | Nbcuniversal Media Llc | Recommendation system using a transformed similarity matrix |
| CN109697629A (en) * | 2018-11-15 | 2019-04-30 | 平安科技（深圳）有限公司 | Product data method for pushing and device, storage medium, computer equipment |
-
2020
- 2020-03-04 CN CN202010144164.7A patent/CN111291217B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102866997A (en) * | 2011-07-05 | 2013-01-09 | 腾讯科技（深圳）有限公司 | Method and device for processing user data |
| US20160371274A1 (en) * | 2015-06-18 | 2016-12-22 | Nbcuniversal Media Llc | Recommendation system using a transformed similarity matrix |
| CN109697629A (en) * | 2018-11-15 | 2019-04-30 | 平安科技（深圳）有限公司 | Product data method for pushing and device, storage medium, computer equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112395496A (en) * | 2020-10-22 | 2021-02-23 | 上海众源网络有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN112351345A (en) * | 2020-11-04 | 2021-02-09 | 深圳Tcl新技术有限公司 | Control method and device of recommended content, smart television and storage medium |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291217B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002488B (en) | Recommendation model training method and device based on meta-path context | |
| CN110929052B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN110457581B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| JP5735087B2 (en) | Providing personalized resources on demand to consumer device applications over a broadband network | |
| CN111291217B (en) | Content recommendation method, device, electronic equipment and computer readable medium | |
| CN106708817B (en) | Information searching method and device | |
| CN111767429B (en) | Video recommendation method and device and electronic equipment | |
| CN111010592B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| US20230017667A1 (en) | Data recommendation method and apparatus, computer device, and storage medium | |
| CN109903086B (en) | Similar crowd expansion method and device and electronic equipment | |
| CN107592572B (en) | Video recommendation method, device and equipment | |
| CN112507163B (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| US11423096B2 (en) | Method and apparatus for outputting information | |
| CN102165441A (en) | Method, system, and apparatus for ranking media sharing channels | |
| CN112328906A (en) | Content item recommendation method, device, equipment and storage medium | |
| CN109753601A (en) | Recommendation information clicking rate determines method, apparatus and electronic equipment | |
| CN106162351A (en) | A kind of video recommendation method and device | |
| US20170366862A1 (en) | Content recommendation user interface | |
| CN109242544A (en) | Processing method, device, computer equipment and the storage medium of product information push | |
| US20140289334A1 (en) | System and method for recommending multimedia information | |
| CN115455280A (en) | Recommendation list determining method and server | |
| CN110110206B (en) | Method, device, computing equipment and storage medium for mining and recommending relationships among articles | |
| CN112989118A (en) | Video recall method and device | |
| CN112836126A (en) | Recommendation method and device based on knowledge graph, electronic equipment and storage medium |
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 |