CN112507163A - Duration prediction model training method, recommendation method, device, equipment and medium - Google Patents
Duration prediction model training method, recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN112507163A CN112507163A CN202011405977.3A CN202011405977A CN112507163A CN 112507163 A CN112507163 A CN 112507163A CN 202011405977 A CN202011405977 A CN 202011405977A CN 112507163 A CN112507163 A CN 112507163A
- Authority
- CN
- China
- Prior art keywords
- multimedia data
- multimedia
- data
- historical
- prediction model
- 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
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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a duration prediction model training method, a recommendation method, a device, equipment and a medium, wherein the method comprises the following steps: constructing a duration prediction model; obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and tag-associated multimedia sample data based on the historical multimedia sample data; extracting a preset amount of multimedia data samples from a multimedia data sample library to generate a plurality of multimedia data sample combinations; the following training process is performed separately for each multimedia data sample combination: inputting the multimedia data sample combination into a duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model; calculating the consistency rate of the predicted playing time and the verification value; and if the consistency rate is greater than the preset threshold value, finishing the training of the duration prediction model. The method and the device are used for solving the problems that the user feels tired in appearance and watching duration is reduced due to single recommended video content in the prior art.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a duration prediction model training method, a duration prediction model recommendation apparatus, a duration prediction model training device, and a duration prediction model recommendation medium.
Background
The home page recommendation bit of the existing video application program is the largest entrance for bearing the personalized recommendation flow of the user, and the video application program recommends videos which are interesting to the user through the home page recommendation bit and is used for prolonging the watching time of the user.
The video displayed by the existing recommendation position is a video which is possibly interested by a user is scored through a scoring model (pointwise model), and video recommendation is carried out according to the score. However, in this process, most videos that the user may be interested in are videos that the user has historically viewed, and the videos that the user has historically viewed are scored higher, thus resulting in most videos that the user has historically viewed being displayed at the recommendation position.
Under the recommendation condition, most recommended videos are videos which are historically watched by the user, and the recommendation inner cylinder is single, so that the user feels tired in appearance, and the watching duration of the user is not prolonged by the videos recommended by the recommendation positions.
Disclosure of Invention
The application provides a duration prediction model training method, a recommendation device, equipment and a medium, which are used for solving the problems of fatigue in the appearance of a user and reduction in the viewing duration caused by single recommended video content in the prior art.
In a first aspect, the present application provides a method for training a duration prediction model, including:
constructing a duration prediction model;
obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and label correlation multimedia sample data based on the historical multimedia sample data;
extracting a preset amount of multimedia data samples from the multimedia data sample library to generate a plurality of multimedia data sample combinations;
performing the following training process for each multimedia data sample combination respectively: inputting the multimedia data sample combination into the duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model;
calculating the consistency rate of the predicted playing time and the verification value;
and if the consistency rate is greater than a preset threshold value, finishing training of the duration prediction model.
Optionally, in the multimedia data sample combination, the number of the historical multimedia sample data is sequentially increased.
In a second aspect, the present application provides a recommendation method, applied to a server, the method including:
obtaining a multimedia database of a target account, the multimedia database comprising: historical multimedia data associated with the target account and tag-associated multimedia data based on the historical multimedia data;
extracting preset amount of multimedia data from the multimedia database to generate a plurality of multimedia data combinations;
respectively inputting a plurality of multimedia data combinations into a duration prediction model to obtain the predicted playing duration of each multimedia data combination;
determining a target multimedia data content combination according to the predicted playing time;
and generating recommendation information of the target multimedia data content combination, and sending the recommendation information to client equipment corresponding to the target account so as to enable the client equipment to display the recommendation information.
Optionally, extracting a preset amount of multimedia data from the multimedia database, and generating a plurality of multimedia data combinations, includes:
constructing a first data pool and a second data pool, wherein the first data pool is used for storing the historical multimedia data, and the second data pool is used for storing the tag-associated multimedia data;
extracting a first sub-number of the historical multimedia data from the first data pool, and extracting a second sub-number of the tag-associated multimedia data from the second data pool to generate a plurality of multimedia data combinations;
wherein a sum of the first sub-quantity and the second sub-quantity is equal to the preset quantity.
Optionally, in the multimedia data combination, the ratios of the first sub-amount of the extracted historical multimedia data are sequentially increased.
Optionally, after the first data pool and the second data pool are constructed, the method further includes:
inputting the multimedia database into a scoring model, and respectively outputting scores corresponding to the historical multimedia data and the label associated multimedia data through the scoring model;
determining the playing probability of each historical multimedia data and each label-associated multimedia data according to the score;
extracting a first amount of the historical multimedia data from the multimedia database and storing the historical multimedia data in the first data pool according to the playing probability, and extracting a second amount of the tag-associated multimedia data from the multimedia database and storing the tag-associated multimedia data in the second data pool;
wherein an upper limit of the first quantity is greater than or equal to the preset quantity, and an upper limit of the second quantity of the tag-associated multimedia data is greater than or equal to the preset quantity.
Optionally, before inputting the multimedia database into the scoring model, the method further includes:
filtering the historical multimedia data with the playing proportion smaller than a first preset ratio from the multimedia database to obtain first filtered multimedia data; the play ratio is as follows: a ratio of a played time length to an unplayed time length of one piece of the historical multimedia data;
and filtering the historical multimedia data which have a continuous relation and have a playing ratio larger than a second preset ratio in the first filtered multimedia data within a second preset time period to obtain second filtered multimedia data, and taking the second filtered multimedia data as the multimedia database.
Optionally, determining a target multimedia data content combination according to the predicted playing duration includes:
acquiring the multimedia data combination with the longest predicted playing time;
and determining the target multimedia data content combination according to the multimedia data combination with the longest predicted playing time.
In a third aspect, the present application provides a training apparatus for a duration prediction model, including:
the construction module is used for constructing a duration prediction model;
an obtaining module, configured to obtain a multimedia data sample library, where the multimedia data sample library includes: historical multimedia sample data and label correlation multimedia sample data based on the historical multimedia sample data;
the generating module is used for extracting a preset amount of multimedia data samples from the multimedia data sample library and generating a plurality of multimedia data sample combinations;
a training module, configured to perform the following training processes for each multimedia data sample combination respectively: inputting the multimedia data sample combination into the duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model;
the calculation module is used for calculating the consistency rate of the predicted playing time and the verification value;
and the adjusting module is used for finishing the training of the duration prediction model if the consistency rate is greater than a preset threshold value.
In a fourth aspect, the present application provides a recommendation apparatus, comprising:
an obtaining module, configured to obtain a multimedia database of a target account, where the multimedia database includes: historical multimedia data associated with the target account and tag-associated multimedia data based on the historical multimedia data;
the generating module is used for extracting preset amount of multimedia data from the multimedia database and generating a plurality of multimedia data combinations;
the prediction module is used for respectively inputting a plurality of multimedia data combinations into a duration prediction model to obtain the predicted playing duration of each multimedia data combination;
the determining module is used for determining a target multimedia data content combination according to the predicted playing time;
and the recommending module is used for generating recommending information of the target multimedia data content combination and sending the recommending information to the client equipment corresponding to the target account so as to enable the client equipment to display the recommending information.
In a fifth aspect, the present application provides an electronic device, comprising: the system comprises a processor, a communication component, a memory and a communication bus, wherein the processor, the communication component and the memory are communicated with each other through the communication bus; the memory for storing a computer program; the processor is configured to execute a program stored in the memory, to implement the method for training a duration prediction model according to the first aspect, and/or to implement the recommendation method according to the second aspect.
In a sixth aspect, the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the training method of the duration prediction model according to the first aspect, and/or the recommendation method according to the second aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: according to the method provided by the embodiment of the application, a duration prediction model is constructed; obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and tag-associated multimedia sample data based on the historical multimedia sample data can be obtained through a multimedia data sample library, and the duration prediction model can meet the pursuit appeal of the user and the interest discovery of the user.
Further, extracting a preset amount of multimedia data samples from a multimedia data sample library to generate a plurality of multimedia data sample combinations; inputting each multimedia data sample combination into a duration prediction model, and outputting the predicted playing duration of each multimedia data sample combination through the duration prediction model; and calculating the consistency rate of the predicted playing time length and the verification value, and finishing the training of the time length prediction model when the consistency rate is greater than a preset threshold value.
According to the method and the device, the combined data of the historical multimedia sample data and the label associated multimedia sample data is input through the training duration prediction model, and the predicted playing duration of the multimedia data is output. In addition, the multimedia data recommendation content is various, the problems that the user feels tired in appearance and the playing time is shortened due to single recommendation content are solved, and further the retention rate of the user 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 training method of a duration prediction model in an embodiment of the present application;
FIG. 2 is a schematic diagram of a process for implementing a machine translation technique according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a recommendation method in an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a process of filtering a multimedia database according to an embodiment of the present application;
FIG. 5 is a process diagram illustrating an embodiment of a process for combining multiple multimedia data according to the present application;
FIG. 6 is a schematic flow chart illustrating a method for obtaining historical multimedia data and tag-associated multimedia data according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a specific implementation process of a recommendation method in an embodiment of the present application;
FIG. 8 is a schematic structural diagram of a training apparatus for a duration prediction model in an embodiment of the present application;
FIG. 9 is a schematic structural diagram of a recommendation device in an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device in an embodiment of the present application.
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.
A first embodiment of the present application provides a method for training a duration prediction model, which may be applied to a client device, such as a mobile phone, a computer, a tablet, a television, or the like, may also be applied to an application installed on the client device, and may also be applied to a server.
The specific implementation of the method is shown in fig. 1:
Specifically, the multimedia data sample library comprises: and S, associating the historical multimedia sample data with the C label, wherein S is an integer larger than 1, and C is an integer larger than 1.
And 105, calculating the consistency rate of the predicted playing time and the verification value.
And the verification value is the actual playing time length of the multimedia data sample combination.
And step 106, if the consistency rate is larger than a preset threshold value, finishing the training of the duration prediction model.
Specifically, if the consistency rate is less than or equal to the preset threshold, after adjusting parameters in the duration prediction model, the training process is repeatedly executed until the consistency rate is greater than the preset threshold, and the duration prediction model training is completed.
According to the method and the device, the duration prediction model is continuously updated, so that the output result of the duration prediction model is more and more accurate, and the retention rate of the user is further improved.
Specifically, the duration prediction model may be a list recommendation model (listwise model).
Specifically, each time a user enters a recommended video list through an application program recommendation bit, the data is recorded and stored in a multimedia data sample library at the same time, and the data format is [ request identifier, video list ], wherein the video list comprises: the identification of each video and the position combination relation of each video.
When the user exits the recommendation position of the application program, the related behaviors of the user are recorded and stored into a multimedia data sample library, and the data format is [ request identification, user unique identification and playing time ]. And combining the two data through the request identifier to form a multimedia data sample combination, and training a listwise model according to the multimedia data sample combination.
Specifically, the video data can be obtained by training an encoder (encoder) part in a machine translation model (Transformer model), and the Transformer model can be used for learning the interaction relation of different videos in a group of video lists, so as to calculate the playing time of the group of video lists:
fig. 2 is a standard Transformer model, which includes a vector layer 201, a processing layer 202 and an output layer 203, wherein the processing layer 202 includes a multi-head attention layer, a first residual and normalization, a full-connected layer and a second residual and normalization. The candidate multimedia data sample list is input to the vector layer 201, and is processed by the processing layer 202 for G times to obtain the playing time length of each candidate video, and the playing time length is output through the output layer 203, wherein G is an integer greater than or equal to 1.
In one embodiment, the number of historical multimedia sample data in the multimedia data sample combination is sequentially increased.
According to the method provided by the embodiment of the application, a duration prediction model is constructed; obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and tag-associated multimedia sample data based on the historical multimedia sample data can be obtained through a multimedia data sample library, and the duration prediction model can meet the pursuit appeal of the user and the interest discovery of the user.
Further, extracting a preset amount of multimedia data samples from a multimedia data sample library to generate a plurality of multimedia data sample combinations; inputting each multimedia data sample combination into a duration prediction model, and outputting the predicted playing duration of each multimedia data sample combination through the duration prediction model; and calculating the consistency rate of the predicted playing time length and the verification value, and finishing the training of the time length prediction model when the consistency rate is greater than a preset threshold value.
According to the method and the device, the combined data of the historical multimedia sample data and the label associated multimedia sample data is input through the training duration prediction model, and the predicted playing duration of the multimedia data is output. In addition, the multimedia data recommendation content is various, the problems that the user feels tired in appearance and the playing time is shortened due to single recommendation content are solved, and further the retention rate of the user is improved.
The second embodiment of the present application provides a recommendation method, which may be applied to a client device, such as a mobile phone, a computer, a tablet, a television, and the like, or may be applied to an application installed on the client device, such as a video application, a news application, and the like, or may be applied to a server.
The method is applied to a server as an example, and it is needless to say that the method is only an example and is not intended to limit the scope of the present application, and the method is not described here. Moreover, other examples in the present application are not intended to limit the scope of the present application, and thus are not described in detail.
Specifically, an instruction for acquiring a video list is sent to a server through a recommendation interface by an application installed on a client device, wherein the instruction for acquiring the video list comprises: a request identification, a unique identification of the target account, etc., for example, the unique identification includes: the user logs in an account of the application program, physical parameters of a client device on which the application program is installed, and the like.
The server obtains the multimedia data combination with the longest playing time according to the unique identification of the target account, and returns the target multimedia data content combination corresponding to the multimedia data combination with the longest playing time to the application program, and the application program receives and displays the target multimedia data content combination table returned by the server.
The specific implementation of the method is shown in fig. 3:
Wherein the multimedia database comprises: historical multimedia data associated with the target account, and tag-associated multimedia data based on the historical multimedia data, the tag-associated multimedia data being multimedia data of interest to the user obtained from the historical multimedia data.
Specifically, an application program installed on the client device sends an instruction for acquiring a video list to the server through the recommendation interface, and the server firstly acquires the multimedia database of the user from the user watching behavior library according to the unique identifier.
Wherein, the user watching action library comprises: the watching behavior of the user, the types of the portrait and the video of the user and the like, wherein the types of the video comprise a fun video, a face video, a street video, a pernicious video, an animation video, a delicacy video, a favorite video and the like. The historical multimedia data includes: the video content watched by the user in the preset time period comprises: the name of the video, the viewing time point, the viewing duration.
For example, the user watches a tv show a during the week, and starts watching at 8 pm every day for 2 hours.
In a specific embodiment, as shown in fig. 4, the specific implementation manner of filtering the multimedia database to obtain the final multimedia database is as follows:
Specifically, when the historical multimedia data is a video album, and the first preset ratio is 20%, for example, a tv series having a total of 50 episodes is watched by the user, the play percentage of the tv series is 16%, and 16% is less than 20%, so that the tv series is filtered. When the historical multimedia data is a single video, such as a movie, the first preset ratio is 10%, the movie is 120 minutes in total, the user watches the movie for 30 minutes, the playing proportion of the movie is 25%, and 10% is less than 25%, so that the movie is not filtered.
In addition, regarding the first filtered multimedia data, the user can select from near to far according to the chronological order of time.
Of course, the user may set the first preset ratio according to the actual needs of the user, and this example is not used to limit the protection scope.
The method and the device filter the videos smaller than the first preset ratio, and can better meet the interest requirements of users.
Specifically, the second preset time period is taken as one week for explanation.
The multimedia data having the consecutive relationship is a continuously loaded video such as a television series, a continuously loaded cartoon, a continuously loaded variety program, etc., which includes a video that has been updated and a video that has not been updated.
When the user watches the tv series whose video is updated, the second preset ratio is 90%, the tv series has 50 episodes in total, the user watches 48 episodes, the playing ratio of the tv series is 96%, and 96% is greater than 90%, so the tv series is filtered out. When the user watches the television series with the video not updated, the second preset ratio is 90%, the television series is updated by 8 episodes, the user watches 5 episodes, the playing ratio of the television series is 62.5%, and 62.5% is less than 90%, so that the television series is not filtered. For example, 80 first multimedia data are selected.
Certainly, the user may set the second preset ratio, the second preset time period, and the number of the first multimedia data according to the actual needs of the user, which is not used for limiting the protection range. However, it needs to be prompted that the second preset time period is the current time period.
In a specific embodiment, the specific implementation of extracting a preset amount of multimedia data from the multimedia database and generating a plurality of multimedia data combinations is shown in fig. 5:
The first data pool is used for storing historical multimedia data, and the second data pool is used for storing tag-associated multimedia data.
In a specific embodiment, after a first data pool and a second data pool are constructed, historical multimedia data are stored in the first data pool, and tag-associated multimedia data are stored in the second data pool, which is specifically implemented as shown in fig. 6:
Specifically, the scoring model is obtained through training scores corresponding to historical multimedia sample data, tag-associated multimedia sample data, and the historical multimedia sample data and the tag-associated multimedia sample data respectively.
Specifically, taking 80 pieces of historical multimedia data and 300 pieces of tag-associated multimedia data as an example, scoring is performed, and then the process needs to be performed 380 times to obtain 380 scores, wherein the scoring model may be a poitwise model.
Specifically, the score and the playing probability are in a direct relationship.
Step 603, according to the playing probability, extracting a first amount of historical multimedia data from the multimedia database and storing the historical multimedia data in a first data pool, and extracting a second amount of tag-associated multimedia data from the multimedia database and storing the tag-associated multimedia data in a second data pool.
Wherein the upper limit of the first amount is greater than or equal to a preset amount, and the upper limit of the second amount of the tag-associated multimedia data is greater than or equal to a preset amount.
Specifically, a first amount of historical multimedia data is extracted from a multimedia database, and a second amount of tag-associated multimedia data is obtained by utilizing a collaborative filtering algorithm according to the historical multimedia data. The method comprises the steps of finding which multimedia data are liked by a user through historical multimedia data of the user based on a collaborative filtering algorithm of the user, measuring and scoring the liked multimedia data of the user, then determining the preference degree of the user to each multimedia data according to a scoring result, and recommending the multimedia data to the user according to the preference degree.
The extracted first amount of historical multimedia data is videos in which the user is pursuing hot within a first preset time period, or may be a union of videos, that is, a certain series of tv shows instead of a few th episode of a certain series of tv shows, a certain variety program instead of a few th period of a certain variety program, and so on. The extracted second amount of tag-associated multimedia data is a video that has not been viewed by the user but is of interest, such as a television series, an art show, a movie, a game video album, an animation, and so forth.
Specifically, obtaining a second number of tag-associated multimedia data by using a collaborative filtering algorithm according to the historical multimedia data specifically includes: the obtaining is performed according to attributes of the video, for example, the attributes of the video include: the theme to which the video belongs, such as movies, dramas, documentaries, art, animations, games, etc., the list of actors in the video, the list of directors in the video, the content style of the video, such as police drama, love drama, antique, etc., the content age of the video, e.g., ancient, modern, future, etc. According to the historical multimedia data of the user, videos with similar video attributes are found from the video main pool, such as television plays of the same star protagonist and police dramas, or movies of crossing subjects, and the like, and for example, 300 tags are selected to be associated with the multimedia data.
However, the number of the tag-associated multimedia data is only an example, and is not intended to limit the scope of protection.
According to the method and the device, videos which are in hot pursuit of users in the current time period and have continuous relations are filtered, and the problem that the interest appeal of the users is ignored in video recommendation due to the fact that the multimedia data in the final multimedia data combination is dominant in hot pursuit of the users is solved.
Wherein the sum of the first sub-quantity and the second sub-quantity is equal to a preset quantity.
In one embodiment, the first sub-number of extracted historical multimedia data is sequentially incremented in the multimedia data assembly.
Specifically, the recommended number of bits of the application is 15 for example, so the preset number needs to be equal to 15 at this time, and this is only an example and is not intended to limit the scope of the present application.
In a specific embodiment, according to the playing probability of the first sub-number of pieces of historical multimedia data, the first multimedia data is sorted from high to low according to the playing probability, M pieces of historical multimedia data are selected, and the M pieces of historical multimedia data are combined to obtain at least one first combination result. And similarly, according to the playing probability of the second sub-number of the tag-associated multimedia data, sorting the tag-associated multimedia data from high to low in the playing probability, selecting N tag-associated multimedia data, and combining the N tag-associated multimedia data to obtain at least one second combination result. And generating a plurality of multimedia volume data combinations according to the first combination result and the second combination result.
Wherein, the value of M is 0-15, and the corresponding value of N is 15-0.
Specifically, 15 multimedia data combinations are generated according to the first combination result and the second combination result, wherein the drama chasing content belongs to the historical multimedia data, and the interest content belongs to the tag-associated multimedia data.
Specifically, a first amount of historical multimedia data is scored through a scoring model, the playing probability corresponding to the score of each historical multimedia data output by the scoring model is determined, the playing probabilities are sequenced from large to small, and the first 15 historical multimedia data are obtained. Similarly, the first 15 tag-associated multimedia data are obtained.
Combining the historical multimedia data ranked at 1 and the tag associated multimedia data ranked at 14 to form a first multimedia data combination; and associating the historical multimedia data at the top 2 with the tag at the top 13 to form a second multimedia data combination, and so on, associating the historical multimedia data at the top 14 with the tag at the top 1 to form a fourteenth multimedia data combination, and associating the historical multimedia data at the top 15 with the tag at the top 15 to form a fifteenth multimedia data combination.
The method comprises the following specific steps:
1 episode content +14 interest contents;
2 pieces of episode content +13 pieces of interest content;
3 pieces of episode content +12 pieces of interest content;
...
m pieces of episode content + (15-M) pieces of interest content;
...
14 pieces of episode content +1 piece of interest content;
15 pieces of episode content.
Here, the expression form of the 15 multimedia volume data combinations is when the series content is greater than or equal to 15. When the series content is less than 15, there may be a case of less than 15 multimedia volume data combinations, because the case of the series content being greater than 15 does not exist, the series content is taken as 5 for an example for description, which specifically follows:
1 episode content +14 interest contents;
2 pieces of episode content +13 pieces of interest content;
3 pieces of episode content +12 pieces of interest content;
4 pieces of episode content +11 pieces of interest content;
5 episode content +10 interest content.
And step 304, determining the target multimedia data content combination according to the predicted playing time length.
Specifically, the description will be given taking a combination of 15 pieces of multimedia data as an example.
In a specific embodiment, 15 multimedia data combinations are input into a duration prediction model, are analyzed through the duration prediction model, and the predicted playing duration of each multimedia data combination is output; and acquiring the multimedia data combination with the longest predicted playing time, and determining the target multimedia volume data content combination according to the multimedia data combination with the longest predicted playing time.
The method and the device recommend the multimedia data combination with the longest predicted playing time for improving the playing time of the video and improving the retention rate of the user. In addition, the problem that the watching duration of a group of video list users is integrally evaluated, the situation that the watching content of the series is dominant due to the fact that the effect of evaluating a single video is evaluated, the recommended content is single, and the user feels tired is solved, in addition, the problem that the interesting content is ignored in the conventional recommendation is solved, and the method and the device can better meet the interest appeal of the user.
In the following, a detailed description is made of the recommendation method of the present application through fig. 7, as follows:
in step 701, an application installed on a client device sends an instruction to obtain a video list.
In step 703, the user's episode content is recalled.
And step 704, recalling the interest content of the user.
And step 705, scoring the recalled chase content and the interest content through a pointwise model, and outputting scores.
And step 706, combining the episode content and the interest content according to the scores to generate a plurality of multimedia data combinations.
And 707, predicting the playing time of each multimedia data combination through a listwise model, and selecting the multimedia data combination with the longest predicted playing time to recommend.
The recommendation method provided by the embodiment of the application obtains a multimedia database of the target account, wherein the multimedia database comprises: historical multimedia data associated with the target account and tag-associated multimedia data based on the historical multimedia data can meet the pursuit appeal of the user and the interest discovery of the user.
Further, extracting preset amount of multimedia data from a multimedia database, generating a plurality of multimedia data combinations, respectively inputting the plurality of multimedia data combinations to a duration prediction model, obtaining the predicted playing duration of each multimedia data combination, determining a target multimedia data content combination according to the predicted playing duration, generating recommendation information of the target multimedia data content combination, and sending the recommendation information to client equipment corresponding to a target account so that the client equipment can display the recommendation information.
According to the method and the device, the combined data of the historical multimedia data and the label associated multimedia data is input by using the duration prediction model, and the predicted playing duration of the multimedia data combination is output. In addition, the multimedia data recommendation content is various, the problems that the user feels tired in appearance and the playing time is shortened due to single recommendation content are solved, and further the retention rate of the user is improved.
A third embodiment of the present application provides a training apparatus for a duration prediction model, as shown in fig. 8, for specific implementation of the apparatus, reference may be made to the descriptions of the first embodiment and the second embodiment, and repeated details are not repeated, including:
and a building module 801, configured to build a duration prediction model.
An obtaining module 802, configured to obtain a multimedia data sample library, where the multimedia data sample library includes: historical multimedia sample data and tags based on the historical multimedia sample data.
The generating module 803 is configured to extract a preset number of multimedia data samples from the multimedia data sample library, and generate a plurality of multimedia data sample combinations.
A training module 804, configured to perform the following training processes for each multimedia data sample combination respectively: and inputting the multimedia data sample combination into the duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model.
The calculating module 805 is configured to calculate a coincidence rate between the predicted playing time length and the verification value.
And an adjusting module 806, configured to complete training of the duration prediction model if the consistency rate is greater than a preset threshold.
A fourth embodiment of the present application further provides a recommendation apparatus, as shown in fig. 9, for specific implementation of the apparatus, reference may be made to the descriptions of the first embodiment and the second embodiment, and repeated descriptions are omitted, including:
an obtaining module 901, configured to obtain a multimedia database of the target account, where the multimedia database includes: historical multimedia data associated with the target account, and tag-associated multimedia data based on the historical multimedia data.
A generating module 902, configured to extract a preset amount of multimedia data from a multimedia database, and generate a plurality of multimedia data combinations.
And the predicting module 903 is configured to input the multiple multimedia data combinations to the duration prediction model, respectively, and obtain a predicted playing duration of each multimedia data combination.
And a determining module 904, configured to determine a target multimedia data content combination according to the predicted playing time.
The recommending module 905 is configured to generate recommendation information of a target multimedia data content combination, and send the recommendation information to a client device corresponding to a target account, so that the client device displays the recommendation information.
Based on the same concept, a fifth embodiment of the present application further provides an electronic device, as shown in fig. 10, the electronic device mainly includes: a processor 1001, a communication component 1002, a memory 1003 and a communication bus 1004, wherein the processor 1001, the communication component 1002 and the memory 1003 communicate with each other via the communication bus 1004. The memory 1003 stores a program executable by the processor 1001, and the processor 1001 executes the program stored in the memory 1003, so as to implement the following steps: constructing a duration prediction model; obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and tag-associated multimedia sample data based on the historical multimedia sample data; extracting a preset amount of multimedia data samples from a multimedia data sample library to generate a plurality of multimedia data sample combinations; the following training process is performed separately for each multimedia data sample combination: inputting the multimedia data sample combination into a duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model; calculating the consistency rate of the predicted playing time and the verification value; if the consistency rate is larger than a preset threshold value, finishing the training of the duration prediction model, and/or acquiring a multimedia database of the target account; extracting preset amount of multimedia data from a multimedia database to generate a plurality of multimedia data combinations; respectively inputting a plurality of multimedia data combinations into a duration prediction model to obtain the predicted playing duration of each multimedia data combination; determining a target multimedia data content combination according to the predicted playing time; and generating recommendation information of the target multimedia data content combination, and sending the recommendation information to the client equipment corresponding to the target account so as to enable the client equipment to display the recommendation information.
The communication bus 1004 mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 1004 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
The communication component 1002 is used for communication between the electronic device and other devices described above.
The Memory 1003 may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the memory may be at least one storage device located remotely from the aforementioned processor 1001.
The Processor 1001 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc., and may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.
In a sixth embodiment of the present application, there is further provided a computer-readable storage medium having stored therein a computer program, which, when run on a computer, causes the computer to execute the training method of the duration prediction model described in the above embodiments, and/or the recommendation method.
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 application 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 on 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 wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, 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 includes one or more of the available media. The available media may be magnetic media (e.g., floppy disks, hard disks, tapes, etc.), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives), among others.
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 (12)
1. A training method of a duration prediction model is characterized by comprising the following steps:
constructing a duration prediction model;
obtaining a multimedia data sample library, the multimedia data sample library comprising: historical multimedia sample data and label correlation multimedia sample data based on the historical multimedia sample data;
extracting a preset amount of multimedia data samples from the multimedia data sample library to generate a plurality of multimedia data sample combinations;
performing the following training process for each multimedia data sample combination respectively: inputting the multimedia data sample combination into the duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model;
calculating the consistency rate of the predicted playing time and the verification value;
and if the consistency rate is greater than a preset threshold value, finishing training of the duration prediction model.
2. The method for training a duration prediction model according to claim 1, wherein the number of the historical multimedia sample data in the multimedia data sample combination is sequentially increased.
3. A recommendation method, applied to a server, the method comprising:
obtaining a multimedia database of a target account, the multimedia database comprising: historical multimedia data associated with the target account and tag-associated multimedia data based on the historical multimedia data;
extracting preset amount of multimedia data from the multimedia database to generate a plurality of multimedia data combinations;
respectively inputting a plurality of multimedia data combinations into a duration prediction model to obtain the predicted playing duration of each multimedia data combination;
determining a target multimedia data content combination according to the predicted playing time;
and generating recommendation information of the target multimedia data content combination, and sending the recommendation information to client equipment corresponding to the target account so as to enable the client equipment to display the recommendation information.
4. The recommendation method according to claim 3, wherein extracting a preset amount of multimedia data from the multimedia database to generate a plurality of multimedia data combinations comprises:
constructing a first data pool and a second data pool, wherein the first data pool is used for storing the historical multimedia data, and the second data pool is used for storing the tag-associated multimedia data;
extracting a first sub-number of the historical multimedia data from the first data pool, and extracting a second sub-number of the tag-associated multimedia data from the second data pool to generate a plurality of multimedia data combinations;
wherein a sum of the first sub-quantity and the second sub-quantity is equal to the preset quantity.
5. The recommendation method according to claim 4, wherein the ratios of the first sub-amounts of the extracted historical multimedia data in the multimedia data combination are sequentially increased.
6. The recommendation method of claim 5, wherein after constructing the first data pool and the second data pool, further comprising:
inputting the multimedia database into a scoring model, and respectively outputting scores corresponding to the historical multimedia data and the label associated multimedia data through the scoring model;
determining the playing probability of each historical multimedia data and each label-associated multimedia data according to the score;
extracting a first amount of the historical multimedia data from the multimedia database and storing the historical multimedia data in the first data pool according to the playing probability, and extracting a second amount of the tag-associated multimedia data from the multimedia database and storing the tag-associated multimedia data in the second data pool;
wherein an upper limit of the first quantity is greater than or equal to the preset quantity, and an upper limit of the second quantity of the tag-associated multimedia data is greater than or equal to the preset quantity.
7. The recommendation method of claim 6, wherein before entering the multimedia database into a scoring model, further comprising:
filtering the historical multimedia data with the playing proportion smaller than a first preset ratio from the multimedia database to obtain first filtered multimedia data; the play ratio is as follows: a ratio of a played time length to an unplayed time length of one piece of the historical multimedia data;
and filtering the historical multimedia data which have a continuous relation and have a playing ratio larger than a second preset ratio in the first filtered multimedia data within a second preset time period to obtain second filtered multimedia data, and taking the second filtered multimedia data as the multimedia database.
8. The recommendation method according to any of claims 3-7, wherein determining a target multimedia data content combination based on said predicted play duration comprises:
acquiring the multimedia data combination with the longest predicted playing time;
and determining the target multimedia data content combination according to the multimedia data combination with the longest predicted playing time.
9. A training device for a duration prediction model, comprising:
the construction module is used for constructing a duration prediction model;
an obtaining module, configured to obtain a multimedia data sample library, where the multimedia data sample library includes: historical multimedia sample data and label correlation multimedia sample data based on the historical multimedia sample data;
the generating module is used for extracting a preset amount of multimedia data samples from the multimedia data sample library and generating a plurality of multimedia data sample combinations;
a training module, configured to perform the following training processes for each multimedia data sample combination respectively: inputting the multimedia data sample combination into the duration prediction model, and outputting the predicted playing duration of the multimedia data sample combination through the duration prediction model;
the calculation module is used for calculating the consistency rate of the predicted playing time and the verification value;
and the adjusting module is used for finishing the training of the duration prediction model if the consistency rate is greater than a preset threshold value.
10. A recommendation device, comprising:
an obtaining module, configured to obtain a multimedia database of a target account, where the multimedia database includes: historical multimedia data associated with the target account and tag-associated multimedia data based on the historical multimedia data;
the generating module is used for extracting preset amount of multimedia data from the multimedia database and generating a plurality of multimedia data combinations;
the prediction module is used for respectively inputting a plurality of multimedia data combinations into a duration prediction model to obtain the predicted playing duration of each multimedia data combination;
the determining module is used for determining a target multimedia data content combination according to the predicted playing time;
and the recommending module is used for generating recommending information of the target multimedia data content combination and sending the recommending information to the client equipment corresponding to the target account so as to enable the client equipment to display the recommending information.
11. An electronic device, comprising: the system comprises a processor, a communication component, a memory and a communication bus, wherein the processor, the communication component and the memory are communicated with each other through the communication bus;
the memory for storing a computer program;
the processor is configured to execute the program stored in the memory, implement the training method of the duration prediction model according to any one of claims 1 to 2, and/or implement the recommendation method according to any one of claims 3 to 8.
12. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the method for training a duration prediction model according to any one of claims 1 to 2 and/or carries out the method for recommendation according to any one of claims 3 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011405977.3A CN112507163B (en) | 2020-12-02 | 2020-12-02 | Duration prediction model training method, recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011405977.3A CN112507163B (en) | 2020-12-02 | 2020-12-02 | Duration prediction model training method, recommendation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112507163A true CN112507163A (en) | 2021-03-16 |
| CN112507163B CN112507163B (en) | 2023-07-21 |
Family
ID=74968548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011405977.3A Active CN112507163B (en) | 2020-12-02 | 2020-12-02 | Duration prediction model training method, recommendation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112507163B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111217A (en) * | 2021-04-22 | 2021-07-13 | 北京达佳互联信息技术有限公司 | Training method of playing duration prediction model, video recommendation method and device |
| CN113132803A (en) * | 2021-04-23 | 2021-07-16 | Oppo广东移动通信有限公司 | Video watching time length prediction method, device, storage medium and terminal |
| CN113656681A (en) * | 2021-07-08 | 2021-11-16 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| WO2023082864A1 (en) * | 2021-11-09 | 2023-05-19 | 腾讯科技（深圳）有限公司 | Training method and apparatus for content recommendation model, device, and storage medium |
| CN116828265A (en) * | 2023-08-28 | 2023-09-29 | 湖南快乐阳光互动娱乐传媒有限公司 | Video control method, system, electronic equipment and readable storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010072099A1 (en) * | 2008-12-22 | 2010-07-01 | 华为技术有限公司 | Method and apparatus for prediction of time delay of video service |
| CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
| WO2017185951A1 (en) * | 2016-04-28 | 2017-11-02 | 华为技术有限公司 | Video transmission method, base station, and system |
| WO2018090793A1 (en) * | 2016-11-18 | 2018-05-24 | 腾讯科技（深圳）有限公司 | Multimedia recommendation method and device |
| CN108304441A (en) * | 2017-11-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Network resource recommended method, device, electronic equipment, server and storage medium |
| US20180262798A1 (en) * | 2017-03-13 | 2018-09-13 | Wipro Limited | Methods and systems for rendering multimedia content on a user device |
| US20180324476A1 (en) * | 2017-05-04 | 2018-11-08 | Facebook, Inc. | Guaranteed delivery of video content items based on received constraints |
| CN110149540A (en) * | 2018-04-27 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Recommendation process method, apparatus, terminal and the readable medium of multimedia resource |
| CN110209843A (en) * | 2019-05-31 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Multimedia resource playback method, device, equipment and storage medium |
| CN110933492A (en) * | 2019-12-10 | 2020-03-27 | 北京爱奇艺科技有限公司 | Method and device for predicting playing time |
| CN111353068A (en) * | 2020-02-28 | 2020-06-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Video recommendation method and device |
| WO2020135193A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳Tcl新技术有限公司 | Deep neural network-based video recommendation method and system, and storage medium |
| US20200320646A1 (en) * | 2018-04-26 | 2020-10-08 | Tencent Technology (Shenzhen) Company Limited | Interest recommendation method, computer device, and storage medium |
-
2020
- 2020-12-02 CN CN202011405977.3A patent/CN112507163B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010072099A1 (en) * | 2008-12-22 | 2010-07-01 | 华为技术有限公司 | Method and apparatus for prediction of time delay of video service |
| WO2017185951A1 (en) * | 2016-04-28 | 2017-11-02 | 华为技术有限公司 | Video transmission method, base station, and system |
| WO2018090793A1 (en) * | 2016-11-18 | 2018-05-24 | 腾讯科技（深圳）有限公司 | Multimedia recommendation method and device |
| CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
| US20180262798A1 (en) * | 2017-03-13 | 2018-09-13 | Wipro Limited | Methods and systems for rendering multimedia content on a user device |
| US20180324476A1 (en) * | 2017-05-04 | 2018-11-08 | Facebook, Inc. | Guaranteed delivery of video content items based on received constraints |
| CN108304441A (en) * | 2017-11-14 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Network resource recommended method, device, electronic equipment, server and storage medium |
| US20200320646A1 (en) * | 2018-04-26 | 2020-10-08 | Tencent Technology (Shenzhen) Company Limited | Interest recommendation method, computer device, and storage medium |
| CN110149540A (en) * | 2018-04-27 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Recommendation process method, apparatus, terminal and the readable medium of multimedia resource |
| WO2020135193A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳Tcl新技术有限公司 | Deep neural network-based video recommendation method and system, and storage medium |
| CN110209843A (en) * | 2019-05-31 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Multimedia resource playback method, device, equipment and storage medium |
| CN110933492A (en) * | 2019-12-10 | 2020-03-27 | 北京爱奇艺科技有限公司 | Method and device for predicting playing time |
| CN111353068A (en) * | 2020-02-28 | 2020-06-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Video recommendation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 许良武;: "基于向量化标签的视频推荐算法研究与实现", 无线互联科技, no. 12 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113111217A (en) * | 2021-04-22 | 2021-07-13 | 北京达佳互联信息技术有限公司 | Training method of playing duration prediction model, video recommendation method and device |
| CN113111217B (en) * | 2021-04-22 | 2024-02-27 | 北京达佳互联信息技术有限公司 | Training method of play duration prediction model, video recommendation method and device |
| CN113132803A (en) * | 2021-04-23 | 2021-07-16 | Oppo广东移动通信有限公司 | Video watching time length prediction method, device, storage medium and terminal |
| CN113132803B (en) * | 2021-04-23 | 2022-09-16 | Oppo广东移动通信有限公司 | Video watching time length prediction method, device, storage medium and terminal |
| CN113656681A (en) * | 2021-07-08 | 2021-11-16 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| CN113656681B (en) * | 2021-07-08 | 2023-08-11 | 北京奇艺世纪科技有限公司 | Object evaluation method, device, equipment and storage medium |
| WO2023082864A1 (en) * | 2021-11-09 | 2023-05-19 | 腾讯科技（深圳）有限公司 | Training method and apparatus for content recommendation model, device, and storage medium |
| CN116828265A (en) * | 2023-08-28 | 2023-09-29 | 湖南快乐阳光互动娱乐传媒有限公司 | Video control method, system, electronic equipment and readable storage medium |
| CN116828265B (en) * | 2023-08-28 | 2023-11-28 | 湖南快乐阳光互动娱乐传媒有限公司 | Video control method, system, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112507163B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101944469B1 (en) | Estimating and displaying social interest in time-based media | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| CN106331778B (en) | Video recommendation method and device | |
| CN112507163A (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| US11017024B2 (en) | Media content rankings for discovery of novel content | |
| US9253511B2 (en) | Systems and methods for performing multi-modal video datastream segmentation | |
| US20180152767A1 (en) | Providing related objects during playback of video data | |
| TW201340690A (en) | Video recommendation system and method thereof | |
| EP1851967A2 (en) | Automatic generation of trailers containing product placements | |
| CN107454442B (en) | Method and device for recommending video | |
| CN106599165B (en) | content recommendation method and server based on playing behavior | |
| CN104685899A (en) | Dynamic media segment pricing | |
| CN107592572B (en) | Video recommendation method, device and equipment | |
| CN109063080B (en) | Video recommendation method and device | |
| CN108769831A (en) | The generation method and device of video advance notice | |
| US20150227970A1 (en) | System and method for providing movie file embedded with advertisement movie | |
| Daneshi et al. | Eigennews: Generating and delivering personalized news video | |
| CN113761364B (en) | Multimedia data pushing method and device | |
| CN117033610A (en) | Method, device, client, server and storage medium for acquiring topics | |
| Moustakas et al. | Online voting behaviour, public content preferences, and content complexity of movies and digital entertainment since the late 19th century | |
| KR20160029627A (en) | Method and service server for providing detail information for content | |
| CN114356979A (en) | Query method and related equipment thereof | |
| CN117271806A (en) | Content recommendation method, device, equipment, storage medium and product | |
| CN116264625A (en) | Video scenario visualization method, device, equipment and storage medium | |
| CN114025176A (en) | Anchor recommendation method and device, 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 |