CN106326391B - Multimedia resource recommendation method and device - Google Patents
Multimedia resource recommendation method and device Download PDFInfo
- Publication number
- CN106326391B CN106326391B CN201610682022.XA CN201610682022A CN106326391B CN 106326391 B CN106326391 B CN 106326391B CN 201610682022 A CN201610682022 A CN 201610682022A CN 106326391 B CN106326391 B CN 106326391B
- Authority
- CN
- China
- Prior art keywords
- recommended
- multimedia resource
- multimedia
- resource
- behavior data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a multimedia resource recommendation method and device. The multimedia resource recommendation method comprises the following steps: under the condition of receiving a request for browsing target resources initiated by a target user at a target terminal, acquiring each multimedia resource to be recommended related to the target resources; acquiring the characteristics corresponding to the multimedia resources to be recommended according to the type of the target terminal and the user behavior data of various terminals in a preset time period; and sequencing each multimedia resource to be recommended according to the corresponding characteristics of each multimedia resource to be recommended, and generating multimedia resource recommendation information according to a sequencing result. The multimedia resource recommendation method provided by the embodiment of the invention can be used for carrying out personalized resource recommendation on the user according to the characteristics of the current target terminal.
Description
Technical Field
The invention relates to the field of multimedia, in particular to a multimedia resource recommendation method and device.
Background
With The development of internet technology, OTT (Over The Top, which means providing various application services to users through The internet), IPTV (Interactive personal TV), and The like based on internet video services form a rapid growth trend. Meanwhile, intelligent terminals such as smart televisions, mobile phones and tablet computers are also popular, and everyone may own a plurality of terminal video playing devices, so that the multi-screen era comes.
In the prior art, a main method for recommending videos for a user is to analyze the watching behavior of the user at a single client, and then recommend a user personalized video according to the watching behavior of the user. By adopting the recommendation method, the watching behaviors of the user on various types of terminals cannot be covered, and the recommendation result is possibly not suitable.
Disclosure of Invention
Technical problem
In view of the above, the technical problem to be solved by the present invention is to provide a multimedia resource recommendation method, which is suitable for multimedia resource recommendation of various types of terminals.
Solution scheme
In order to solve the above technical problem, according to an embodiment of the present invention, a multimedia resource recommendation method is provided, including:
under the condition of receiving a request for browsing target resources initiated by a target user at a target terminal, acquiring each multimedia resource to be recommended related to the target resources;
acquiring the characteristics corresponding to the multimedia resources to be recommended according to the type of the target terminal and the user behavior data of various terminals in a preset time period;
and sequencing each multimedia resource to be recommended according to the corresponding characteristics of each multimedia resource to be recommended, and generating multimedia resource recommendation information according to a sequencing result.
For the above method, in a possible implementation manner, obtaining the corresponding characteristics of each multimedia resource to be recommended according to the type of the target terminal and the user behavior data of each terminal in a preset time period includes:
acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals;
carrying out feature classification and format sorting on the first user behavior data to obtain sorted first user behavior data;
and acquiring the characteristics corresponding to the multimedia resources to be recommended from the sorted first user behavior data according to the type of the target terminal, wherein the characteristics corresponding to the multimedia resources to be recommended comprise terminal characteristics and resource characteristics corresponding to the multimedia resources to be recommended.
For the above method, in a possible implementation manner, obtaining the corresponding characteristics of each multimedia resource to be recommended according to the type of the target terminal and the user behavior data of each terminal in a preset time period includes:
acquiring second user behavior data related to each multimedia resource in a preset time period from various terminals;
performing feature classification and format sorting on the second user behavior data to obtain sorted second user behavior data;
and acquiring the characteristics corresponding to the multimedia resources to be recommended from the sorted second user behavior data according to the type of the target terminal and the multimedia resources to be recommended, wherein the characteristics corresponding to the multimedia resources to be recommended comprise terminal characteristics and resource characteristics corresponding to the multimedia resources to be recommended.
For the method, in a possible implementation manner, the sorting the to-be-recommended multimedia resources according to the characteristics corresponding to the to-be-recommended multimedia resources includes:
calculating the click probability of each multimedia resource to be recommended by adopting the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiThe characteristic value corresponding to the ith characteristic is represented, N represents the number of the characteristics, f (x) represents the product of the characteristic value corresponding to each characteristic included in each multimedia resource to be recommended and a weight coefficientScore (v) represents the click probability corresponding to each multimedia resource to be recommended;
and sequencing each multimedia resource to be recommended according to the click probability corresponding to each multimedia resource to be recommended, and selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended according to a sequencing result.
For the above method, in a possible implementation manner, generating the multimedia resource recommendation information according to the sorting result includes:
deleting each alternative multimedia resource by adopting one or more of the following steps;
deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource;
deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource;
and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource.
In order to solve the above technical problem, according to another embodiment of the present invention, there is provided a multimedia resource recommendation apparatus including:
the system comprises a resource to be recommended acquisition module, a resource to be recommended acquisition module and a resource recommendation module, wherein the resource to be recommended acquisition module is used for acquiring each multimedia resource to be recommended related to a target resource under the condition of receiving a request for browsing the target resource initiated by a target user at a target terminal;
the characteristic acquisition module is connected with the resource acquisition module to be recommended and used for acquiring the characteristics corresponding to the multimedia resources to be recommended according to the type of the target terminal and the user behavior data of various terminals in a preset time period;
and the recommendation information generation module is connected with the characteristic acquisition module and used for sequencing each multimedia resource to be recommended according to the characteristic corresponding to each multimedia resource to be recommended and generating multimedia resource recommendation information according to the sequencing result.
For the apparatus, in a possible implementation manner, the feature obtaining module includes:
the first data acquisition unit is used for acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals;
the first classification and arrangement unit is connected with the first data acquisition unit and is used for carrying out feature classification and format arrangement on the first user behavior data to obtain the arranged first user behavior data;
and the first feature obtaining unit is connected with the first classification and arrangement unit and is used for obtaining features corresponding to the multimedia resources to be recommended from the arranged first user behavior data according to the type of the target terminal, wherein the features corresponding to the multimedia resources to be recommended comprise terminal features and resource features corresponding to the multimedia resources to be recommended.
For the apparatus, in a possible implementation manner, the feature obtaining module includes:
the second data acquisition unit is used for acquiring second user behavior data related to each multimedia resource in a preset time period from various terminals;
the second classification and arrangement unit is connected with the second data acquisition unit and is used for carrying out feature classification and format arrangement on the second user behavior data to obtain the second user behavior data after arrangement;
and the second feature obtaining unit is connected with the second classification and arrangement unit and is used for obtaining features corresponding to the multimedia resources to be recommended from the second user behavior data after arrangement according to the type of the target terminal and the multimedia resources to be recommended, wherein the features corresponding to the multimedia resources to be recommended comprise terminal features and resource features corresponding to the multimedia resources to be recommended.
For the apparatus, in a possible implementation manner, the recommendation information generating module includes:
a click probability calculation unit for calculating click probability of each multimedia resource to be recommended by adopting the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiThe score (v) represents the click probability corresponding to each to-be-recommended multimedia resource;
and the alternative resource acquisition unit is connected with the click probability calculation unit and used for sequencing each multimedia resource to be recommended according to the click probability corresponding to each multimedia resource to be recommended and selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended according to the sequencing result.
For the apparatus, in a possible implementation manner, the recommendation information generating module further includes:
a deleting unit, configured to delete each of the alternative multimedia resources by using one or more of the following steps;
deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource;
deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource;
and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource.
Advantageous effects
The multimedia resource recommendation method provided by the embodiment of the invention can acquire user behavior data of various terminals in a preset time period, and can cover browsing behaviors of users in various terminals, so that personalized resource recommendation can be performed on the users according to the characteristics of the current target terminal, such as screen size, network condition, watching scene and the like.
Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the invention and, together with the description, serve to explain the principles of the invention.
FIG. 1 shows a flow diagram of a multimedia resource recommendation method according to an embodiment of the invention;
FIG. 2 shows another flow diagram of a multimedia resource recommendation method according to an embodiment of the invention;
FIG. 3 shows another flow diagram of a multimedia resource recommendation method according to an embodiment of the invention;
FIG. 4 is a schematic diagram illustrating obtaining user behavior data according to an embodiment of the invention;
FIG. 5 is a block diagram illustrating an architecture of a multimedia resource recommendation apparatus according to another embodiment of the present invention;
fig. 6 is a block diagram illustrating a configuration of a multimedia resource recommendation apparatus according to another embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present invention will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, procedures, components, and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present invention.
Example 1
Fig. 1 shows a flow chart of a multimedia resource recommendation method according to an embodiment of the invention. As shown in fig. 1, the multimedia resource recommendation method may mainly include steps 101 to 103.
The terminal according to the embodiment of the present invention may include various types of terminal devices capable of browsing multimedia resources, such as a mobile phone (e.g., an Android mobile phone, an iPhone mobile phone), a computer, a tablet computer, a television, and the like, without limitation. Multimedia assets (Multimedia) may include various forms of media such as text, sound, video, and images, among others.
As an example of the embodiment of the present invention, a user a initiates a request for playing "malus spectabilis" in a video playing client of a mobile phone terminal. And under the condition that the server receives the request, acquiring each multimedia resource to be recommended related to the malus spectabilis. The user a may be the target user described in step 101, the mobile phone terminal may be the target terminal described in step 101, and the "malus spectabilis" may be the target resource described in step 101.
The multimedia resources to be recommended may include various types of multimedia resources having a correlation with the target resources currently browsed by the target user. The embodiment of the invention does not limit the specific acquisition mode of the multimedia resource to be recommended. Taking a video as an example, the multimedia resource to be recommended can belong to the same video channel as the target video, for example, the multimedia resource to be recommended and the target video belong to wu-zhu films; or may belong to a series with the target video, such as hunger game 1 and hunger game 2; but not limited to, may have the same starring actor as the target video, or may have a strong play correlation, etc.
It should be noted that, as those skilled in the art should understand, there are various ways in the prior art to obtain each multimedia resource to be recommended related to the target resource, and this is not limited thereto.
And 102, acquiring the corresponding characteristics of each multimedia resource to be recommended according to the type of the target terminal and the user behavior data of each terminal in a preset time period.
The type of the target terminal may be any one of a mobile phone (e.g., an Android mobile phone, an iPhone mobile phone), a computer, a tablet computer, a television terminal, and the like, which is not limited thereto. The user behavior data of the embodiment of the present invention may include data generated based on various behaviors that the user makes with respect to the multimedia resource. The embodiment of the present invention does not limit the specific type of the user behavior, and may include, for example, a browsing behavior of the user, a comment behavior of the user, a rating behavior of the user, a top-and-bottom-up behavior of the user, and the like.
And 103, sequencing each multimedia resource to be recommended according to the corresponding characteristics of each multimedia resource to be recommended, and generating multimedia resource recommendation information according to a sequencing result.
In the embodiment of the present invention, the feature corresponding to the multimedia resource may include various types of multimedia resource features, such as a terminal feature, a behavior feature, a resource feature, and the like, which is not limited herein. The terminal characteristics may be used to indicate the situation of the terminal for browsing multimedia resources, such as the terminal type, the terminal screen size, and the like. The behavior characteristics can be used for representing the condition of the behavior of the user on the multimedia resource, such as the watching duration, the number of comments, the score, the number of steps on the top and the like. Resource characteristics may be used in the case of attributes representing multimedia resources, such as resource channels, interest tags, etc.
Further, the feature corresponding to the multimedia resource may further include identification information (e.g., name, number, etc.) of the feature and content (e.g., feature value) corresponding to the feature identification information. The characteristic value may be a continuous value, a discrete value, or a non-numerical value. For example, the terminal screen size (terminal feature) may be a discrete value, such as 240 × 320, 320 × 480; the score (behavior feature) may be a continuous type of value, whose value range may be [0, 10 ]; the resource channels (resource features) may be non-numeric, e.g. the video resources may belong to a movie channel or a tv show channel.
Step 102 may include various implementations, for example:
in a first manner, after determining each to-be-recommended multimedia resource related to the target resource in step 101, in step 102, user behavior data related to each to-be-recommended multimedia resource in a preset time period may be acquired from each terminal. And extracting the characteristics corresponding to the multimedia resources to be recommended from the acquired user behavior data related to the multimedia resources to be recommended.
In the second mode, the user behavior data of each multimedia resource (for example, all multimedia resources in a multimedia resource library of a certain website) on various terminals in a preset time period may be counted in advance, or the user behavior data of each multimedia resource on various terminals in a preset time period may be counted once at intervals, and the corresponding features of each acquired multimedia resource may be extracted.
After determining each multimedia resource to be recommended related to the target resource in step 101, in step 102, the feature corresponding to each multimedia resource to be recommended may be screened out from the features corresponding to each multimedia resource extracted before. The step of counting the user behavior data in advance may be executed by a specific terminal, or may be executed by a server (for example, a server of a website) that can communicate with each terminal.
As to the first mode, in a possible implementation manner, as shown in fig. 2, obtaining features corresponding to each to-be-recommended multimedia resource according to the type of the target terminal and user behavior data of various terminals in a preset time period (step 102), may include:
step 201, acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals;
202, carrying out feature classification and format sorting on the first user behavior data to obtain sorted first user behavior data;
step 203, obtaining characteristics corresponding to each multimedia resource to be recommended from the sorted first user behavior data according to the type of the target terminal, where the characteristics corresponding to the multimedia resource to be recommended include terminal characteristics and resource characteristics corresponding to the multimedia resource to be recommended.
In step 201, the obtained first user behavior data may include various user behavior data related to each multimedia resource to be recommended, and the embodiment of the present invention does not limit a specific process of obtaining the first user behavior data. For example, the user behavior data related to each multimedia resource to be recommended may be directly obtained from various terminals, and then the user behavior data may be aggregated in the cache.
In addition, the specific time length of the preset time period is not limited in the embodiment of the present invention, and may be, for example, one month, half month, ten days, and the like, which is not limited in this respect. It can be understood that, by selecting a suitable preset time period, it can be ensured that the acquired user behavior data has better representativeness.
In step 202, the feature classification according to the embodiment of the present invention may include a process of classifying the user behavior data according to a certain feature, for example, the user behavior data is classified according to features such as a terminal type, a terminal screen size, a viewing duration, a number of comments, a number of steps on top, and the like, which is not limited thereto. The format sorting according to the embodiment of the present invention may include a process of sorting and counting the classified user behavior data according to a preset format, for example, sorting the classified user behavior data into forms such as a table and a list, which is not limited herein.
For example, taking a video as an example, the sorted first user behavior data may be as shown in table 1:
TABLE 1
| Resource ID | Terminal type | Terminal screen size | Duration of viewing | Number of comments | Number of steps on top |
| 1 | Mobile phone | 100*300 | 5minute | 2 | 1 |
| 1 | Computer with a display | 800*600 | 10minute | 5 | 3 |
In step 203, the characteristics corresponding to each to-be-recommended multimedia resource may be obtained from the sorted first user behavior data according to the type of the target terminal. For example, when the multimedia resource to be recommended is a video 1 and the target terminal is a mobile phone, the characteristics of the video 1 may include a terminal type (mobile phone), a terminal screen size (100 × 300), a viewing duration (5 minutes), a comment number (2), and a top-stepping number (1).
As for the second mode, in a possible implementation manner, as shown in fig. 3, obtaining features corresponding to each to-be-recommended multimedia resource according to the type of the target terminal and user behavior data of various terminals in a preset time period (step 102), which may include:
In step 301, the obtained second user behavior data may include various user behavior data related to various multimedia resources (e.g., all multimedia resources in a multimedia resource library), and the specific process of obtaining the second user behavior data is not limited in the embodiments of the present invention. For example, as shown in fig. 4, the user behavior data of various terminals may be collected in real time, and the collected user behavior data may be stored in real time on, for example, an HDFS (Hadoop Distributed File System). Further, the user behavior data obtained from various terminals may be merged and stored in, for example, a server, or each terminal or each corresponding file of each terminal may be stored, which is not limited herein.
The multimedia resource recommendation method of the embodiment of the invention can collect data of different terminals of the user, classify and store the behavior of the user in a format, provide data analysis support for other services and analyze behavior characteristics of the user on different terminals.
In step 302, the process of performing feature classification and formatting on the second user behavior data is similar to the process of performing feature classification and formatting on the first user behavior data in step 201, and is not described herein again.
For example, taking a video as an example, the second user behavior data after being sorted can be shown in table 2:
TABLE 2
| Video ID | Terminal type | Terminal screen size | Duration of viewing | Number of comments | Number of steps on top |
| 1 | Mobile phone | 100*300 | 5minute | 2 | 1 |
| 2 | Computer with a display | 800*600 | 10minute | 5 | 3 |
| 2 | Mobile phone | 100*300 | 16minute | 3 | 3 |
| 3 | Mobile phone | 100*300 | 12minute | 2 | 5 |
In step 303, the characteristics corresponding to each multimedia resource to be recommended may be obtained from the sorted second user behavior data according to the type of the target terminal and each multimedia resource to be recommended. For example, when the multimedia resource to be recommended is a video 2 and the target terminal is a computer, the characteristics of the acquired video 2 may include a terminal type (computer), a terminal screen size (800 × 600), a viewing duration (10 minutes), a comment number (5), and a top-stepping number (3).
In a possible implementation manner, the sorting (step 103) of each to-be-recommended multimedia resource according to the feature corresponding to each to-be-recommended multimedia resource may include:
step 401, calculating the click probability of each multimedia resource to be recommended by using the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiRepresenting the characteristic value corresponding to the ith characteristic, N representing the number of the characteristics, f (x) representing the characteristic value corresponding to each characteristic included in each multimedia resource to be recommended and calculating the weight coefficientThe result of summation after multiplication, score (v), represents the click probability corresponding to each multimedia resource to be recommended;
step 402, according to the click probability corresponding to each multimedia resource to be recommended, ranking each multimedia resource to be recommended, and according to the ranking result, selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended.
The multimedia resource to be recommended may include a plurality of features, and each feature has a corresponding feature value and a weight coefficient. The feature value corresponding to the feature may be obtained through, for example, feature engineering processing, and the weight coefficient corresponding to the feature may be obtained through, for example, model training. According to the characteristic value and the weight coefficient corresponding to each characteristic corresponding to each multimedia resource to be recommended, the click probability (the probability of being clicked) corresponding to each multimedia resource to be recommended can be calculated. In the recommending process, the higher the click probability corresponding to the multimedia resource to be recommended is, the higher the probability that the multimedia resource is clicked is, and the multimedia resource is preferentially recommended.
For example, the multimedia resource to be recommended has N characteristics. Wherein, the characteristic value corresponding to the 1 st characteristic is x1The weight coefficient is a1(ii) a The characteristic value corresponding to the 2 nd characteristic is x2The weight coefficient is a2(ii) a And so on, the characteristic value corresponding to the ith characteristic is xiThe weight coefficient is ai. Then, the click probability corresponding to the multimedia resource to be recommended is score (v):
it should be noted that the original value of the feature value may be a numerical value or a non-numerical value, and a quantized final value convenient for model calculation may be obtained through the processing of the feature engineering. For ease of understanding, the following are exemplified:
for scores (continuum values), it can be mapped between [0, 10 ]; for the viewing duration (discrete value), it can be mapped into 24 features, for example, if the video is viewed at 20 points, the value of the feature corresponding to 20 points is 1; for example, the terminal type (non-numerical type) can be represented by a 1-Android mobile phone, a 2-iPhone mobile phone, a 3-tablet computer, a 4-computer, and a 5-television.
It will be appreciated that the number of multimedia assets to be recommended may be much greater than the number of multimedia assets needed to generate the recommendation information. In this case, the multimedia resources to be recommended need to be screened to obtain alternative multimedia resources for generating recommendation information. Further, in step 402, for example, the multimedia resource to be recommended whose click probability exceeds a certain value may be used as the candidate multimedia resource, or the multimedia resource to be recommended ranked within a certain range may be used as the candidate multimedia resource, which is not limited herein.
In a possible implementation manner, generating the multimedia resource recommendation information according to the sorting result (step 103) may include:
step 403, deleting one or more of the following steps for each alternative multimedia resource;
deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource;
deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource;
and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource.
The resource channel of the embodiment of the invention can represent the channel to which the multimedia resource belongs. Generally, a resource channel of a multimedia resource is determined to be rarely changed. For example, a video channel may be a television show, a movie, a variety program, etc.; a novel channel may be an emotion, pass through, delay beauty, etc. The interest tag may include a keyword for representing the multimedia asset. For example, the interest tags of the video may be fun, adventure, landscape, and so on. Wherein, the resource channel and the interest label belong to the basic information of the multimedia resource.
When the user is recommended in a personalized manner, not only the interest resources of the user need to be predicted, but also the characteristics of the target terminal and the diversity of the resources may be considered. Thus, multimedia assets can be screened and controlled. The embodiment of the invention does not limit the specific screening factors, for example, the screening factors can be determined according to the browsing condition of the target user, the characteristics of the alternative multimedia resources and the like. Further, based on a set screening principle, the alternative multimedia resources are screened, and finally, each multimedia resource used for generating the recommendation information is obtained.
The multimedia resource recommendation method provided by the embodiment of the invention can acquire user behavior data of various terminals in a preset time period, and can cover browsing behaviors of users in various terminals, so that personalized resource recommendation can be performed on the users according to the characteristics of the current target terminal, such as screen size, network condition, watching scene and the like.
Example 2
Fig. 5 is a block diagram illustrating a multimedia resource recommendation apparatus according to another embodiment of the present invention. Fig. 5 may be used to execute the multimedia resource recommendation method shown in fig. 1 to 3. For convenience of explanation, only portions related to the embodiment of the present invention are shown in fig. 5.
As shown in fig. 5, the multimedia resource recommendation apparatus may mainly include: the resource to be recommended obtaining module 51 is configured to obtain each multimedia resource to be recommended related to a target resource when receiving a request for browsing the target resource, where the request is initiated by a target user at a target terminal. And the feature obtaining module 53 is connected to the resource to be recommended obtaining module 51, and is configured to obtain features corresponding to the multimedia resources to be recommended according to the type of the target terminal and user behavior data of various terminals in a preset time period. And the recommendation information generating module 55 is connected to the feature acquiring module 53, and is configured to sort each to-be-recommended multimedia resource according to the feature corresponding to each to-be-recommended multimedia resource, and generate multimedia resource recommendation information according to the sorting result. Specific principles and examples can be found in example 1 and the associated description of fig. 1.
In a possible implementation manner, the feature obtaining module may include: the first data acquisition unit is used for acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals; the first classification and arrangement unit is connected with the first data acquisition unit and is used for carrying out feature classification and format arrangement on the first user behavior data to obtain the arranged first user behavior data; and the first feature obtaining unit is connected with the first classification and arrangement unit and is used for obtaining features corresponding to the multimedia resources to be recommended from the arranged first user behavior data according to the type of the target terminal, wherein the features corresponding to the multimedia resources to be recommended comprise terminal features and resource features corresponding to the multimedia resources to be recommended. Specific principles and examples can be found in example 1 and the associated description of fig. 2.
In a possible implementation manner, the feature obtaining module may include: the second data acquisition unit is used for acquiring second user behavior data related to each multimedia resource in a preset time period from various terminals; the second classification and arrangement unit is connected with the second data acquisition unit and is used for carrying out feature classification and format arrangement on the second user behavior data to obtain the second user behavior data after arrangement; and the second feature obtaining unit is connected with the second classification and arrangement unit and is used for obtaining features corresponding to the multimedia resources to be recommended from the second user behavior data after arrangement according to the type of the target terminal and the multimedia resources to be recommended, wherein the features corresponding to the multimedia resources to be recommended comprise terminal features and resource features corresponding to the multimedia resources to be recommended. Specific principles and examples can be found in example 1 and the associated description of fig. 3.
In a possible implementation manner, the recommendation information generating module may include: a click probability calculation unit for calculating click probability of each multimedia resource to be recommended by adopting the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiThe score (v) represents the click probability corresponding to each to-be-recommended multimedia resource. And the alternative resource acquisition unit is connected with the click probability calculation unit and used for sequencing each multimedia resource to be recommended according to the click probability corresponding to each multimedia resource to be recommended and selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended according to the sequencing result. Specific principles and examples can be found in the description related to embodiment 1.
In a possible implementation manner, the recommendation information generating module further includes: a deleting unit, configured to delete each of the alternative multimedia resources by using one or more of the following steps; deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource; deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource; and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource. Specific principles and examples can be found in the description related to embodiment 1.
The multimedia resource recommendation device provided by the embodiment of the invention can acquire user behavior data of various terminals in a preset time period, and can cover browsing behaviors of users in various terminals, so that personalized resource recommendation can be performed on the users according to the characteristics of the current target terminal, such as screen size, network condition, watching scene and the like.
Example 3
Fig. 6 is a block diagram illustrating a multimedia resource recommendation apparatus according to another embodiment of the present invention. The multimedia resource recommendation device 1100 may be a host server with computing capability, a personal computer PC, or a portable computer or terminal that can be carried, etc. The specific embodiments of the present invention do not limit the specific implementation of the compute node.
The multimedia resource recommendation device 1100 includes a processor (processor)1110, a communication Interface (Communications Interface)1120, a memory 1130, and a bus 1140. The processor 1110, the communication interface 1120, and the memory 1130 communicate with each other via the bus 1140.
The communication interface 1120 is used to communicate with network devices, including, for example, virtual machine management centers, shared storage, and the like.
Processor 1110 is configured to execute programs. Processor 1110 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention.
The memory 1130 is used to store files. The memory 1130 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1130 may also be a memory array. The storage 1130 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules.
In one possible embodiment, the program may be a program code including computer operation instructions. The procedure is particularly useful for: the operations of the steps in example 1 were carried out.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may select different ways to implement the described functionality for specific applications, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
If the described functionality is implemented in the form of computer software and sold or used as a stand-alone product, it is to some extent possible to consider all or part of the technical solution of the invention (for example, the part contributing to the prior art) to be embodied in the form of a computer software product. The computer software product is generally stored in a non-volatile storage medium readable by a computer and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the methods according to the embodiments of the present invention. The storage medium includes various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A multimedia resource recommendation method is characterized by comprising the following steps:
under the condition of receiving a request for browsing target resources initiated by a target user at a target terminal, acquiring each multimedia resource to be recommended related to the target resources;
acquiring characteristics corresponding to each multimedia resource to be recommended according to the type of the target terminal and user behavior data of various terminals in a preset time period, wherein the characteristics corresponding to the multimedia resource to be recommended comprise terminal characteristics and resource characteristics corresponding to the multimedia resource to be recommended;
and sequencing each multimedia resource to be recommended according to the corresponding characteristics of each multimedia resource to be recommended, and generating multimedia resource recommendation information according to a sequencing result.
2. The method according to claim 1, wherein obtaining the corresponding characteristics of each multimedia resource to be recommended according to the type of the target terminal and the user behavior data of each terminal in a preset time period comprises:
acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals;
carrying out feature classification and format sorting on the first user behavior data to obtain sorted first user behavior data;
and acquiring the characteristics corresponding to the multimedia resources to be recommended from the sorted first user behavior data according to the type of the target terminal.
3. The method according to claim 1, wherein obtaining the corresponding characteristics of each multimedia resource to be recommended according to the type of the target terminal and the user behavior data of each terminal in a preset time period comprises:
acquiring second user behavior data related to each multimedia resource in a preset time period from various terminals;
performing feature classification and format sorting on the second user behavior data to obtain sorted second user behavior data;
and acquiring the characteristics corresponding to the multimedia resources to be recommended from the sorted second user behavior data according to the type of the target terminal and the multimedia resources to be recommended.
4. The method according to claim 2 or 3, wherein the step of ranking each to-be-recommended multimedia resource according to the feature corresponding to each to-be-recommended multimedia resource comprises:
calculating the click probability of each multimedia resource to be recommended by adopting the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiThe score (v) represents the click probability corresponding to each to-be-recommended multimedia resource;
and sequencing each multimedia resource to be recommended according to the click probability corresponding to each multimedia resource to be recommended, and selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended according to a sequencing result.
5. The method of claim 4, wherein generating the multimedia resource recommendation information according to the sorting result comprises:
deleting each alternative multimedia resource by adopting one or more of the following steps;
deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource;
deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource;
and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource.
6. A multimedia resource recommendation apparatus, comprising:
the system comprises a resource to be recommended acquisition module, a resource to be recommended acquisition module and a resource recommendation module, wherein the resource to be recommended acquisition module is used for acquiring each multimedia resource to be recommended related to a target resource under the condition of receiving a request for browsing the target resource initiated by a target user at a target terminal;
the characteristic acquisition module is connected with the resource acquisition module to be recommended and is used for acquiring the characteristics corresponding to the multimedia resources to be recommended according to the type of the target terminal and the user behavior data of various terminals in a preset time period, wherein the characteristics corresponding to the multimedia resources to be recommended comprise the terminal characteristics and the resource characteristics corresponding to the multimedia resources to be recommended;
and the recommendation information generation module is connected with the characteristic acquisition module and used for sequencing each multimedia resource to be recommended according to the characteristic corresponding to each multimedia resource to be recommended and generating multimedia resource recommendation information according to the sequencing result.
7. The apparatus of claim 6, wherein the feature obtaining module comprises:
the first data acquisition unit is used for acquiring first user behavior data related to each multimedia resource to be recommended in a preset time period from various terminals;
the first classification and arrangement unit is connected with the first data acquisition unit and is used for carrying out feature classification and format arrangement on the first user behavior data to obtain the arranged first user behavior data;
and the first characteristic acquisition unit is connected with the first classification and arrangement unit and used for acquiring the characteristics corresponding to the multimedia resources to be recommended from the arranged first user behavior data according to the type of the target terminal.
8. The apparatus of claim 6, wherein the feature obtaining module comprises:
the second data acquisition unit is used for acquiring second user behavior data related to each multimedia resource in a preset time period from various terminals;
the second classification and arrangement unit is connected with the second data acquisition unit and is used for carrying out feature classification and format arrangement on the second user behavior data to obtain the second user behavior data after arrangement;
and the second characteristic acquisition unit is connected with the second classification and arrangement unit and is used for acquiring the characteristics corresponding to the multimedia resources to be recommended from the second user behavior data after arrangement according to the type of the target terminal and the multimedia resources to be recommended.
9. The apparatus according to claim 7 or 8, wherein the recommendation information generating module comprises:
a click probability calculation unit for calculating click probability of each multimedia resource to be recommended by adopting the following formula 1 and the following formula 2,
wherein i represents the ith feature, aiRepresents the weight coefficient, x, corresponding to the ith featureiThe score (v) represents the click probability corresponding to each to-be-recommended multimedia resource;
and the alternative resource acquisition unit is connected with the click probability calculation unit and used for sequencing each multimedia resource to be recommended according to the click probability corresponding to each multimedia resource to be recommended and selecting each alternative multimedia resource meeting preset conditions from each multimedia resource to be recommended according to the sequencing result.
10. The apparatus of claim 9, wherein the recommendation information generation module further comprises:
a deleting unit, configured to delete each of the alternative multimedia resources by using one or more of the following steps;
deleting the multimedia resources which have been browsed by the target user within a preset time period from each alternative multimedia resource;
deleting multimedia resources with more than a preset number in the same resource channel from each alternative multimedia resource;
and deleting the multimedia resources with more than the preset number in the same interest tag from each alternative multimedia resource.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610682022.XA CN106326391B (en) | 2016-08-17 | 2016-08-17 | Multimedia resource recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610682022.XA CN106326391B (en) | 2016-08-17 | 2016-08-17 | Multimedia resource recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106326391A CN106326391A (en) | 2017-01-11 |
| CN106326391B true CN106326391B (en) | 2020-02-14 |
Family
ID=57743637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610682022.XA Active CN106326391B (en) | 2016-08-17 | 2016-08-17 | Multimedia resource recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326391B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951137A (en) * | 2017-03-02 | 2017-07-14 | 合网络技术（北京）有限公司 | The sorting technique and device of multimedia resource |
| CN107704516A (en) * | 2017-09-01 | 2018-02-16 | 北京雷客天地科技有限公司 | A kind of method and system of requesting song |
| CN108335137B (en) * | 2018-01-31 | 2021-07-30 | 北京三快在线科技有限公司 | Sorting method and device, electronic equipment and computer readable medium |
| CN108416446B (en) * | 2018-03-15 | 2021-07-06 | 北京奇艺世纪科技有限公司 | Video satisfaction determining method and device |
| CN110209845B (en) * | 2018-07-26 | 2024-01-30 | 腾讯数码（天津）有限公司 | Recommendation method, device and storage medium of multimedia content |
| CN109218801B (en) * | 2018-08-15 | 2021-12-03 | 咪咕视讯科技有限公司 | Information processing method, device and storage medium |
| CN109241425B (en) * | 2018-08-31 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Resource recommendation method, device, equipment and storage medium |
| CN109639786B (en) * | 2018-12-04 | 2021-06-18 | 北京达佳互联信息技术有限公司 | Multimedia resource distribution method, device, server and storage medium |
| CN112241486A (en) * | 2019-07-17 | 2021-01-19 | 北京达佳互联信息技术有限公司 | Multimedia information acquisition method and device |
| CN111291264B (en) * | 2020-01-23 | 2023-06-23 | 腾讯科技（深圳）有限公司 | Access object prediction method and device based on machine learning and computer equipment |
| CN111556366A (en) * | 2020-04-02 | 2020-08-18 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, terminal, server and system |
| CN112364244B (en) * | 2020-11-16 | 2024-10-11 | 广州酷狗计算机科技有限公司 | Multimedia data recommendation method, device, server and storage medium |
| CN113536125A (en) * | 2021-07-20 | 2021-10-22 | 西安力传智能技术有限公司 | Media information processing method, device, equipment and storage medium |
| CN113849685A (en) * | 2021-09-10 | 2021-12-28 | 浙江岩华文化科技有限公司 | Video recommendation method, device, electronic device and storage medium |
| CN116628235B (en) * | 2023-07-19 | 2023-11-03 | 支付宝(杭州)信息技术有限公司 | Data recommendation method, device, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368788A (en) * | 2011-12-09 | 2012-03-07 | 中国电信股份有限公司 | Information pushing method and apparatus thereof |
| CN104035982A (en) * | 2014-05-28 | 2014-09-10 | 小米科技有限责任公司 | Multimedia resource recommendation method and device |
| CN104598505A (en) * | 2014-06-03 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device |
| CN105808743A (en) * | 2016-03-11 | 2016-07-27 | 中国联合网络通信集团有限公司 | Terminal recommendation method and terminal recommendation system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729408A (en) * | 2013-12-09 | 2014-04-16 | 乐视网信息技术（北京）股份有限公司 | Method for transmitting multimedia file and electronic device |
| CN105718545A (en) * | 2016-01-18 | 2016-06-29 | 合一网络技术(北京)有限公司 | Recommendation method and device of multimedia resources |
-
2016
- 2016-08-17 CN CN201610682022.XA patent/CN106326391B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102368788A (en) * | 2011-12-09 | 2012-03-07 | 中国电信股份有限公司 | Information pushing method and apparatus thereof |
| CN104035982A (en) * | 2014-05-28 | 2014-09-10 | 小米科技有限责任公司 | Multimedia resource recommendation method and device |
| CN104598505A (en) * | 2014-06-03 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Multimedia resource recommendation method and device |
| CN105808743A (en) * | 2016-03-11 | 2016-07-27 | 中国联合网络通信集团有限公司 | Terminal recommendation method and terminal recommendation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106326391A (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
| CN112052387B (en) | Content recommendation method, device and computer readable storage medium | |
| CN110321422B (en) | Method for training model on line, pushing method, device and equipment | |
| CN111368141B (en) | Video tag expansion method, device, computer equipment and storage medium | |
| CN109033149B (en) | Information recommendation method and device, server and storage medium | |
| CN105653700B (en) | Video retrieval method and system | |
| CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
| CN106339507B (en) | Streaming Media information push method and device | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| CN109753601B (en) | Method and device for determining click rate of recommended information and electronic equipment | |
| CN110309795A (en) | Video detecting method, device, electronic equipment and storage medium | |
| CN114491093B (en) | Multimedia resource recommendation and object representation network generation method and device | |
| CN110337012B (en) | Intelligent recommendation method and device based on Internet television platform | |
| CN105653572A (en) | Resource processing method and apparatus | |
| CN106604051A (en) | Live channel recommending method and device | |
| CN112100221A (en) | Information recommendation method and device, recommendation server and storage medium | |
| CN112907334A (en) | Object recommendation method and device | |
| CN113873330B (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN108664654A (en) | A kind of main broadcaster's recommendation method and device based on user's similarity | |
| US20200192930A1 (en) | Method and device for assessing quality of multimedia resource | |
| CN111259195A (en) | Video recommendation method and device, electronic equipment and readable storage medium | |
| TW201933231A (en) | Method and apparatus for mining relationship between articles and recommending article, computation device and storage medium | |
| CN115965439A (en) | Data recall method, data recall device, electronic equipment and storage medium | |
| CN109063080B (en) | Video recommendation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200529 Address after: 310051 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Patentee after: Alibaba (China) Co.,Ltd. Address before: 518030, Sannuo building, 19L02, 3012 Binhai Avenue, Shenzhen, Guangdong, Nanshan District Patentee before: HEYI INTELLIGENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |