CN106649848A - Video recommendation method and video recommendation device - Google Patents
Video recommendation method and video recommendation device Download PDFInfo
- Publication number
- CN106649848A CN106649848A CN201611256126.0A CN201611256126A CN106649848A CN 106649848 A CN106649848 A CN 106649848A CN 201611256126 A CN201611256126 A CN 201611256126A CN 106649848 A CN106649848 A CN 106649848A
- Authority
- CN
- China
- Prior art keywords
- video
- recommended
- label
- user
- corresponding label
- 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
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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
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)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to a video recommendation method and a video recommendation device. The method comprises the following steps: determining a tag corresponding to a video currently watched by a user; determining a plurality of to-be-recommended videos according to the tag corresponding to the video currently watched; sequencing the plurality of to-be-recommended videos according to the tag corresponding to the video currently watched, the tags corresponding to the plurality of to-be-recommended videos and the tags corresponding to the user to obtain a sequencing result; and recommending the plurality of to-be-recommended videos according to the sequencing result. According to the method and the device provided by the invention, the tag corresponding to the user is considered when recommending videos related to the videos currently washed by the user, so that the video recommending effect can be improved.
Description
Technical field
It relates to video technique field, more particularly to a kind of video recommendation method and device.
Background technology
When user watches video by video website, video website would generally recommend currently viewing with user to user
The related video of video.For example, when user with non-screen mode toggle watch video when, can the right side of video playback window and/
Or downside shows the information of the related video of the video currently viewing to user.The quality of video recommendations effect is mainly according to click
Passing judgment on, generally, clicking rate is higher, then video recommendations effect is better for the height of rate.It is current generally according to user in correlation technique
The title and/or label of the video of viewing carries out video recommendations, and the relevant information for being considered is less, cause video recommendations effect compared with
Difference.
The content of the invention
Technical problem
In view of this, the disclosure technical problem to be solved is, the poor problem of the video recommendations effect in correlation technique.
Solution
In order to solve above-mentioned technical problem, according to an embodiment of the disclosure, there is provided a kind of video recommendation method, bag
Include：
Determine the corresponding label of the currently viewing video of user；
Multiple videos to be recommended are determined according to the corresponding label of the currently viewing video；
According to the corresponding label of the currently viewing video, multiple video corresponding labels to be recommended and the use
Multiple videos to be recommended are ranked up by the corresponding label in family, obtain ranking results；
Multiple videos to be recommended are recommended according to the ranking results.
For said method, in a kind of possible implementation, according to the corresponding label of the currently viewing video,
Multiple videos to be recommended are arranged by multiple video corresponding labels to be recommended and the corresponding label of the user
Sequence, obtains ranking results, including：
For video to be recommended each described, respectively according to the corresponding label of the currently viewing video, described wait to push away
Video corresponding label and the corresponding label of the user are recommended, the ranking value of the video to be recommended is determined；
Multiple videos to be recommended are ranked up according to the ranking value, obtain ranking results.
For said method, in a kind of possible implementation, for video to be recommended each described, respectively according to institute
The corresponding label of currently viewing video, the video corresponding label to be recommended and the corresponding label of the user are stated, it is determined that
The ranking value of the video to be recommended, including：
For video to be recommended each described, according to the corresponding label of the currently viewing video and described treat respectively
The corresponding label of video is recommended to determine the predicted value of the video to be recommended；
The predicted value of the video to be recommended is adjusted according to the user corresponding label, obtains described to be recommended
The ranking value of video.
For said method, in a kind of possible implementation, wait to push away to described according to the corresponding label of the user
The predicted value for recommending video is adjusted, including：
Calculate the similarity of the corresponding label of user label corresponding with the video to be recommended；
The predicted value of the video to be recommended is adjusted according to the similarity, obtains the row of the video to be recommended
Sequence value.
For said method, in a kind of possible implementation, according to the similarity to the video to be recommended
Predicted value is adjusted, and obtains the ranking value of the video to be recommended, including：
Determine the corresponding weight of the predicted value and the corresponding weight of the similarity；
According to the predicted value, the corresponding weight of the predicted value, the similarity and the corresponding power of the similarity
The ranking value of the video to be recommended is determined again.
For said method, in a kind of possible implementation, the label includes multilayer.
For said method, in a kind of possible implementation, calculate the corresponding label of the user and wait to push away with described
The similarity of the corresponding label of video is recommended, including：
Calculate similarity of the corresponding label of the user label corresponding with the video to be recommended in identical layer.
For said method, in a kind of possible implementation, treat with described the corresponding label of the user is calculated
After recommending the similarity of the corresponding label of video, methods described also includes：
In the case where the similarity is more than the first preset value and less than 1, the use is increased to the video to be recommended
The corresponding label in family, wherein, first preset value is more than or equal to 0 and less than 1.
In order to solve above-mentioned technical problem, according to another embodiment of the present disclosure, there is provided a kind of video recommendations device, bag
Include：
First label determining module, for determining the corresponding label of the currently viewing video of user；
Video determining module to be recommended, it is multiple to be recommended for being determined according to the corresponding label of the currently viewing video
Video；
Order module, for according to the corresponding label of the currently viewing video, multiple video correspondences to be recommended
Multiple videos to be recommended are ranked up by label and the corresponding label of the user, obtain ranking results；
Video recommendations module, for being recommended multiple videos to be recommended according to the ranking results.
For said apparatus, in a kind of possible implementation, the order module includes：
First ranking value determination sub-module, for for video to be recommended each described, respectively according to described currently viewing
The corresponding label of video, the video corresponding label to be recommended and the corresponding label of the user, determine described to be recommended
The ranking value of video；
Sorting sub-module, for being ranked up to multiple videos to be recommended according to the ranking value, obtains sequence knot
Really.
For said apparatus, in a kind of possible implementation, the first ranking value determination sub-module includes：
Predicted value determination sub-module, for for video to be recommended each described, being regarded according to described currently viewing respectively
Frequently corresponding label and the corresponding label of the video to be recommended determine the predicted value of the video to be recommended；
Second ranking value determination sub-module, for the prediction according to the corresponding label of the user to the video to be recommended
Value is adjusted, and obtains the ranking value of the video to be recommended.
For said apparatus, in a kind of possible implementation, the second ranking value determination sub-module includes：
Similarity Measure submodule, for calculating the corresponding label of user label corresponding with the video to be recommended
Similarity；
3rd ranking value determination sub-module, for being adjusted to the predicted value of the video to be recommended according to the similarity
It is whole, obtain the ranking value of the video to be recommended.
For said apparatus, in a kind of possible implementation, the 3rd ranking value determination sub-module includes：
Weight determination sub-module, for determining the corresponding weight of the predicted value and the corresponding weight of the similarity；
4th ranking value determination sub-module, for according to the predicted value, the corresponding weight of the predicted value, described similar
Degree and the corresponding weight of the similarity determine the ranking value of the video to be recommended.
For said apparatus, in a kind of possible implementation, the label includes multilayer.
For said apparatus, in a kind of possible implementation, the Similarity Measure submodule includes：
Identical layer Similarity Measure submodule, it is corresponding with the video to be recommended for calculating the corresponding label of the user
Label identical layer similarity.
For said apparatus, in a kind of possible implementation, described device also includes：
Label increase module, for the similarity more than the first preset value and less than 1 in the case of, wait to push away to described
Recommending video increases the corresponding label of the user, wherein, first preset value is more than or equal to 0 and less than 1.
In order to solve above-mentioned technical problem, according to another embodiment of the present disclosure, there is provided a kind of video recommendations device, bag
Include：
Processor；
For storing the memory of processor executable；
Wherein, the processor is configured to：
Determine the corresponding label of the currently viewing video of user；
Multiple videos to be recommended are determined according to the corresponding label of the currently viewing video；
According to the corresponding label of the currently viewing video, multiple video corresponding labels to be recommended and the use
Multiple videos to be recommended are ranked up by the corresponding label in family, obtain ranking results；
Multiple videos to be recommended are recommended according to the ranking results.
Beneficial effect
The video corresponding label currently viewing by determining user, determines according to the currently viewing corresponding label of video
Multiple videos to be recommended, according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended and user couple
Multiple videos to be recommended are ranked up by the label answered, and obtain ranking results, and according to ranking results to multiple videos to be recommended
Recommended, thus, it is possible in the video for recommending the video currently viewing to user related, it is considered to the corresponding label of user, from
And the effect of video recommendations can be improved.
According to below with reference to the accompanying drawings, to detailed description of illustrative embodiments, the further feature and aspect of the disclosure will become
It is clear.
Description of the drawings
Comprising in the description and accompanying drawing and the specification of the part that constitutes specification together illustrates the disclosure
Exemplary embodiment, feature and aspect, and for explaining the principle of the disclosure.
Fig. 1 illustrates the flowchart of the video recommendation method according to the embodiment of the disclosure one.
Fig. 2 illustrates an exemplary flowchart of video recommendation method step S13 according to the embodiment of the disclosure one.
Fig. 3 illustrates an exemplary flowchart of video recommendation method step S21 according to the embodiment of the disclosure one.
Fig. 4 illustrates an exemplary flowchart of video recommendation method step S32 according to the embodiment of the disclosure one.
Fig. 5 illustrates an exemplary flowchart of video recommendation method step S42 according to the embodiment of the disclosure one.
Fig. 6 illustrates the structured flowchart of the video recommendations device according to another embodiment of the disclosure.
Fig. 7 illustrates an exemplary structured flowchart of the video recommendations device according to another embodiment of the disclosure.
Fig. 8 is a kind of block diagram of the device 1900 for video recommendations according to an exemplary embodiment.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to accompanying drawing.It is identical in accompanying drawing
Reference represent the same or analogous element of function.Although the various aspects of embodiment are shown in the drawings, remove
Non-specifically is pointed out, it is not necessary to accompanying drawing drawn to scale.
Here special word " exemplary " means " being used as example, embodiment or illustrative ".Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, in order to better illustrate the disclosure, numerous details are given in specific embodiment below.
It will be appreciated by those skilled in the art that without some details, the disclosure equally can be implemented.In some instances, for
Method well known to those skilled in the art, means, element and circuit are not described in detail, in order to highlight the purport of the disclosure.
Embodiment 1
Fig. 1 illustrates the flowchart of the video recommendation method according to the embodiment of the disclosure one.The method can apply to
In server.As shown in figure 1, the method includes：
In step s 11, the corresponding label of the currently viewing video of user is determined.
As an example of the present embodiment, can according to it is following at least one determine the corresponding label of video：Video
Title, video uploader are that the label that arranges of video, user's portrait of video uploader, the affiliated type of video, video are mainly interior
Hold the comment content with video.
In a kind of possible implementation, label includes multilayer.
Used as an example of the implementation, label can include ground floor label, second layer label and third layer mark
Sign.For example, word segmentation processing can be carried out to the title of video, obtains the corresponding third layer label of video；Corresponding to video
Three layers of label carries out abstract, obtains the corresponding second layer label of video；The corresponding second layer label of video is carried out abstract, obtained
The corresponding ground floor label of video.For example, a certain video is entitled《<No. 1 shop of coffee prince>Yin Enhui excessively sufficient " tomboy "
Addiction》.Word segmentation processing is carried out to the title, the corresponding three third layer labels of the title can be obtained：" No. 1 shop of coffee prince "
" Yin Enhui " and " tomboy ".Third layer label " No. 1 shop of coffee prince " is carried out abstract, third layer label " coffee can be obtained
The corresponding second layer label " South Korean TV soaps " in No. 1 shop of coffee prince ", carries out abstract to second layer label " South Korean TV soaps ", can obtain the second layer
The corresponding ground floor label " TV play " of label " South Korean TV soaps ".Third layer label " Yin Enhui " is carried out abstract, the 3rd can be obtained
Layer label " Yin Enhui " corresponding second layer label " Korea female star ", second layer label " Korea female star " is carried out it is abstract,
The corresponding ground floor label " star in amusement circle " of second layer label " Korea female star " can be obtained.To third layer label " tomboy "
Carry out abstract, the corresponding second layer label of third layer label " tomboy " " character features noun " can be obtained, to second layer mark
Signing " character features noun " carries out abstract, can obtain the corresponding ground floor label of second layer label " character features noun " and " take out
As noun ".
In addition, being the label that video is arranged according to the title and video uploader of video, it is also possible to can directly obtain
The corresponding second layer label of video or ground floor label, are not limited thereto.
Although it should be noted that including ground floor label, second layer label and third layer label as an example with label
Multilayer labels are described as above, it is understood by one of ordinary skill in the art that the disclosure answers not limited to this.In fact, this area skill
Art personnel can flexibly set completely the number of plies of label according to personal like and/or practical application scene.For example, can be from label
Multiple dimensions such as the corresponding time cost for storing magnitude and model training of data that quantity, sample increase consider to determine
Which floor need that label arranged.
In step s 12, multiple videos to be recommended are determined according to the currently viewing corresponding label of video.
As an example of the present embodiment, can be according to the currently viewing corresponding label of video from video library to be selected
Filter out multiple videos to be recommended.
In step s 13, according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended and use
Multiple videos to be recommended are ranked up by the corresponding label in family, obtain ranking results.
Wherein, the corresponding label of user can be according to following at least one determination：The title of the video that user has watched, use
Video uploader is that the label that arranges of video, the affiliated type of video watched of user, user see in the video that family has been watched
Main contents, the user of the video that user's portrait of video uploader, user have watched is in the comment of video in the video seen
Hold the corresponding video related information of paying behavior with user.
For example, a certain user Jing often watches South Korean TV soaps, and Jing often watches the collection of drama of some or several Korea stars protagonist, or
Jing often watches the works of certain playwright, screenwriter.Statistical disposition is carried out to the viewing behavioral data of the user, the corresponding mark of user can be obtained
Sign, it is possible to obtain the label of the corresponding different levels of user.
It should be noted that those skilled in the art can determine according to demand the corresponding label of currently viewing video,
Video corresponding label to be recommended and the corresponding label of user determine that the present embodiment is not limited this with specific reference to which data
It is fixed.
In step S14, multiple videos to be recommended are recommended according to ranking results.
As an example of the present embodiment, the preceding N number of video to be recommended that sorts in ranking results can be pushed away
Recommend, wherein, N is positive integer, and N is less than or equal to the total number of video to be recommended.
As an example of the present embodiment, can be in the right side of video playback window, downside, upside and left side appoint
Meaning one side or the multi-lateral shows the video recommended.
The present embodiment can be in the video for recommending the video currently viewing to user related, it is considered to the corresponding mark of user
Sign, that is, user related information is considered, thus, it is possible to realize personalized recommendation for user such that it is able to improve the effect of video recommendations
Really.
According to the present embodiment, in a kind of possible implementation, can be according only to the currently viewing video correspondence of user
Label and the corresponding label of user determine the ranking results of video to be recommended and video to be recommended.
According to the present embodiment, in alternatively possible implementation, can be corresponding by the currently viewing video of user
The video related informations such as label, the corresponding label of user keyword, type, the scoring of video currently viewing with user are mutually tied
Close, to determine the ranking results of video to be recommended and video to be recommended.For example, can in the characteristic set of existing model,
Increase the currently viewing corresponding label of video of user and the corresponding label of user, to enrich the corresponding feature of model, so as to
Improve the effect of video recommendations.Wherein, existing model can be the video recommendations model in correlation technique, be not limited thereto.
According to the present embodiment, in alternatively possible implementation, can determined by existing model it is to be recommended
It is corresponding according to the corresponding label of the currently viewing video of user and user after the ranking results of video and video to be recommended
Label carries out two minor sorts to video to be recommended, to improve the effect of video recommendations.
Fig. 2 illustrates an exemplary flowchart of video recommendation method step S13 according to the embodiment of the disclosure one.
As shown in Fig. 2 according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended and the corresponding mark of user
Sign, multiple videos to be recommended are ranked up, obtain ranking results, including：
In the step s 21, for each video to be recommended, respectively according to the currently viewing corresponding label of video, wait to push away
Video corresponding label and the corresponding label of user are recommended, the ranking value of video to be recommended is determined.
The ranking value of a certain video to be recommended is bigger, then may indicate that the user watches the possibility of the video to be recommended and gets over
Greatly.
In step S22, multiple videos to be recommended are ranked up according to ranking value, obtain ranking results.
For example, multiple videos to be recommended can be ranked up according to the descending order of ranking value, obtains sequence knot
Really.
As an example of the present embodiment, can be right according to the descending order of ranking value with by the way of offline
All videos to be recommended are ranked up, and obtain ranking results, it is possible to ranking results are updated to storage environment on line.
As another example of the present embodiment, can be calculated with carrying out sequence in real time by the way of online, according to sequence
The descending order of value is ranked up to all videos to be recommended, obtains ranking results.
Fig. 3 illustrates an exemplary flowchart of video recommendation method step S21 according to the embodiment of the disclosure one.
As shown in figure 3, for each video to be recommended, respectively according to the currently viewing corresponding label of video, video to be recommended correspondence
Label and the corresponding label of user, determine the ranking value of video to be recommended, including：
In step S31, for each video to be recommended, according to the currently viewing corresponding label of video and treat respectively
The corresponding label of video is recommended to determine the predicted value of video to be recommended.
In this example, for each video to be recommended, first according to the currently viewing corresponding label of video and treat
The corresponding label of video is recommended to determine the predicted value of video to be recommended.For example, the corresponding mark of currently viewing video can be calculated
The similarity of label corresponding with video to be recommended is signed, the predicted value of video to be recommended is determined according to similarity.Wherein, predicted value
Can be with similarity positive correlation, in other words, the phase of the corresponding label of currently viewing video label corresponding with video to be recommended
Bigger like degree, then the predicted value of video to be recommended is bigger.
It should be noted that those skilled in the art can adopt various methods to calculate the currently viewing corresponding mark of video
The similarity between label corresponding with video to be recommended is signed, this example is not defined to this.
In step s 32, the predicted value of video to be recommended is adjusted according to user's corresponding label, obtains to be recommended
The ranking value of video.
In this example, determined according to the currently viewing corresponding label of the corresponding label of video and video to be recommended
After the predicted value of video to be recommended, the predicted value of video to be recommended is adjusted according to user's corresponding label.
Due to for a collection of video to be recommended, different user for the wherein fancy grade of each video to be recommended and
The ranking results being more prone to are likely to different.Therefore, in this example, according to the corresponding label of user to each video to be recommended
Predicted value be adjusted, the thus sequence using the corresponding label of user to video to be recommended is intervened, so as to be directed to not
Same user obtains different ranking results, and then realizes the personalized recommendation of video, it is possible to increase Consumer's Experience, and can carry
High video recommendations effect.
In a kind of possible implementation, the method can also include：Determine the weight of corresponding each label of user.
For example, the video of a certain user's viewing is mostly TV play, and wherein South Korean TV soaps are more, then the South Korean TV soaps video counts that can be watched user
With the ratio of the video sum of user's viewing as the corresponding weight of label " South Korean TV soaps ".In the implementation, user is corresponding
Each label has weight information, is treated according to the weight of corresponding each label of user and corresponding each label of user and is pushed away
The predicted value for recommending video is adjusted, and can further optimize the ranking value of video to be recommended, pushes away so as to further improve video
Recommend effect.
It should be noted that according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended with
And during the corresponding label training pattern of user, using there is metric [0,1] to describe label, or can adopt without metric
Description label.Wherein, can be to be determined in interval [0,1] according to the weight of label using there is metric [0,1] to describe label
The corresponding characteristic value of label, wherein, the weight of label can be obtained by model training.Adopt label is described without metric can be with
For when video or user do not include the label, the characteristic value of video or the corresponding label of user is 0；When video or
When person user includes the label, the characteristic value of video or the corresponding label of user is 1.In addition, model training can be adopted
Offline mode, it would however also be possible to employ online mode, is not limited thereto.
Fig. 4 illustrates an exemplary flowchart of video recommendation method step S32 according to the embodiment of the disclosure one.
As shown in figure 4, being adjusted to the predicted value of video to be recommended according to the corresponding label of user, the sequence of video to be recommended is obtained
Value, including：
In step S41, the similarity of the corresponding label of user label corresponding with video to be recommended is calculated.
It should be noted that those skilled in the art can using various methods calculate the corresponding label of user with it is to be recommended
Similarity between the corresponding label of video, this example is not defined to this.
In a kind of possible implementation, the similar of the corresponding label of user label corresponding with video to be recommended is calculated
Degree, including：Calculate similarity of the corresponding label of the user label corresponding with video to be recommended in identical layer.For example, it is a certain to treat
The label A 3 for recommending video is third layer label, and the corresponding label B 2 of user is second layer label, then can first determine third layer
The corresponding second layer label A 2 of label A 3, then the similarity for calculating second layer label A 2 and second layer label B 2, it is possible to by
Two layers of label A 2 are defined as the similarity of third layer label A 3 and second layer label B 2 with the similarity of second layer label B 2.
In step S42, the predicted value of video to be recommended is adjusted according to similarity, obtains the row of video to be recommended
Sequence value.
In a kind of possible implementation, in the phase for calculating the corresponding label of user label corresponding with video to be recommended
After spending, the method also includes：Similarity more than the first preset value and less than 1 in the case of, to video to be recommended increase
The corresponding label of user, wherein, the first preset value is more than or equal to 0 and less than 1.In the implementation, if user is corresponding
The similarity of label label corresponding with video to be recommended then may indicate that user is corresponding more than the first preset value and less than 1
The similarity of label label corresponding with video to be recommended is higher, and the corresponding label of user label corresponding with video to be recommended
Difference, in this case, increases video to be recommended the corresponding label of user, to enrich the label of video to be recommended, so as to
Be conducive to follow-up video recommendations.
Fig. 5 illustrates an exemplary flowchart of video recommendation method step S42 according to the embodiment of the disclosure one.
As shown in figure 5, being adjusted to the predicted value of video to be recommended according to similarity, the ranking value of video to be recommended is obtained, including：
In step s 51, the corresponding weight of predicted value and the corresponding weight of similarity are determined.
In this example, treated according to the similarity between the corresponding label of user label corresponding with video to be recommended
When recommending the predicted value of video to be adjusted, it is thus necessary to determine that the corresponding weight of predicted value and the corresponding weight of similarity.Need
Illustrate, those skilled in the art can according to the actual demand of application scenarios arrange the size of the corresponding weight of predicted value with
The size of the corresponding weight of similarity.The corresponding weight of similarity is bigger, then row of the corresponding label of user to video to be recommended
The impact of sequence is bigger.
It is true according to predicted value, the corresponding weight of predicted value, similarity and the corresponding weight of similarity in step S52
The ranking value of fixed video to be recommended.
For example, S=Q1×R+Q2× C, wherein, S represents the ranking value of video to be recommended, and R represents predicted value, Q1Represent pre-
The corresponding weight of measured value, C represents similarity, Q2Represent the corresponding weight of similarity.
Embodiment 2
Fig. 6 illustrates the structured flowchart of the video recommendations device according to another embodiment of the disclosure.Device shown in Fig. 6 can be with
For running the video recommendation method shown in Fig. 1 to Fig. 5.For convenience of description, illustrate only in figure 6 related to the present embodiment
Part.
As shown in fig. 6, the device includes：First label determining module 61, the video pair currently viewing for determining user
The label answered；Video determining module 62 to be recommended, it is multiple to be recommended for being determined according to the currently viewing corresponding label of video
Video；Order module 63, for according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended and use
Multiple videos to be recommended are ranked up by the corresponding label in family, obtain ranking results；Video recommendations module 64, for according to row
Sequence result is recommended multiple videos to be recommended.
Fig. 7 illustrates an exemplary structured flowchart of the video recommendations device according to another embodiment of the disclosure.Shown in Fig. 7
Device can be used for run Fig. 1 to Fig. 5 shown in video recommendation method.For convenience of description, illustrate only in the figure 7 and this
The related part of embodiment.Label has identical function with Fig. 6 identical components in Fig. 7, for simplicity's sake, omits to these
The detailed description of component.As shown in Figure 7：
In a kind of possible implementation, order module 63 includes：First ranking value determination sub-module 631, for right
In each video to be recommended, respectively according to the currently viewing corresponding label of video, video corresponding label to be recommended and user
Corresponding label, determines the ranking value of video to be recommended；Sorting sub-module 632, for be recommended being regarded to multiple according to ranking value
Frequency is ranked up, and obtains ranking results.
In a kind of possible implementation, the first ranking value determination sub-module 631 includes：Predicted value determination sub-module,
For for each video to be recommended, respectively according to the currently viewing corresponding label of video and the corresponding mark of video to be recommended
Sign the predicted value for determining video to be recommended；Second ranking value determination sub-module, for according to the corresponding label of user to be recommended
The predicted value of video is adjusted, and obtains the ranking value of video to be recommended.
In a kind of possible implementation, the second ranking value determination sub-module includes：Similarity Measure submodule, is used for
Calculate the similarity of the corresponding label of user label corresponding with video to be recommended；3rd ranking value determination sub-module, for root
The predicted value of video to be recommended is adjusted according to similarity, obtains the ranking value of video to be recommended.
In a kind of possible implementation, the 3rd ranking value determination sub-module includes：Weight determination sub-module, for true
Determine the corresponding weight of predicted value and the corresponding weight of similarity；4th ranking value determination sub-module, for according to predicted value, pre-
The corresponding weight of measured value, similarity and the corresponding weight of similarity determine the ranking value of video to be recommended.
In a kind of possible implementation, label includes multilayer.
In a kind of possible implementation, Similarity Measure submodule includes：Identical layer Similarity Measure submodule, uses
In calculating similarity of the corresponding label of the user label corresponding with video to be recommended in identical layer.
In a kind of possible implementation, the device also includes：Label increases module 65, in similarity more than the
One preset value and less than 1 in the case of, the corresponding label of user is increased to video to be recommended, wherein, the first preset value be more than or
Equal to 0 and less than 1.
The video corresponding label currently viewing by determining user, determines according to the currently viewing corresponding label of video
Multiple videos to be recommended, according to the currently viewing corresponding label of video, multiple video corresponding labels to be recommended and user couple
Multiple videos to be recommended are ranked up by the label answered, and obtain ranking results, and according to ranking results to multiple videos to be recommended
Recommended, thus, it is possible in the video for recommending the video currently viewing to user related, it is considered to the corresponding label of user, from
And the effect of video recommendations can be improved.
Embodiment 3
Fig. 8 is a kind of block diagram of the device 1900 for video recommendations according to an exemplary embodiment.For example, fill
Put 1900 and may be provided in a server.With reference to Fig. 8, device 1900 includes process assembly 1922, and it further includes one
Or multiple processors, and the memory resource by representated by memory 1932, can holding by process assembly 1922 for storage
Capable instruction, such as application program.The application program stored in memory 1932 can include one or more each
The individual module for corresponding to one group of instruction.Additionally, process assembly 1922 is configured to execute instruction, to perform above-mentioned video recommendations side
Method.
Device 1900 can also include that power supply module 1926 be configured to the power management of performs device 1900, one
Wired or wireless network interface 1950 is configured to for device 1900 to be connected to network, and input and output (I/O) interface
1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing including instruction, example are additionally provided
Such as include the memory 1932 of instruction, above-mentioned instruction can be performed to complete said method by the process assembly 1922 of device 1900.
The present invention can be system, method and/or computer program.Computer program can include computer
Readable storage medium storing program for executing, containing the computer-readable program instructions for being used to make processor realize various aspects of the invention.
Computer-readable recording medium can be the tangible of the instruction that holding and storage are used by instruction execution equipment
Equipment.Computer-readable recording medium for example can be-- but be not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electromagnetism storage device, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer-readable recording medium
More specifically example (non exhaustive list) includes：Portable computer diskette, hard disk, random access memory (RAM), read-only deposit
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), portable
Compact disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
Be stored with instruction punch card or groove internal projection structure and above-mentioned any appropriate combination.Calculating used herein above
Machine readable storage medium storing program for executing is not construed as instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations, logical
Cross electromagnetic wave (for example, by the light pulse of fiber optic cables) that waveguide or other transmission mediums propagate or by wire transfer
Electric signal.
Computer-readable program instructions as described herein can from computer-readable recording medium download to each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network can include copper transmission cable, Optical Fiber Transmission, be wirelessly transferred, router, fire wall, switch, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment is received from network and counted
Calculation machine readable program instructions, and forward the computer-readable program instructions, for being stored in each calculating/processing equipment in meter
In calculation machine readable storage medium storing program for executing.
For perform the present invention operation computer program instructions can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming language
The source code write of any combination or object code, the programming language includes OO programming language-such as
Smalltalk, C++ etc., and the procedural programming languages of routine-such as " C " language or similar programming language.Computer
Readable program instructions can perform fully on the user computer, partly perform on the user computer, as one solely
Vertical software kit is performed, on the user computer part performs on the remote computer or completely in remote computer for part
Or perform on server.In the situation of remote computer is related to, remote computer can be by the network-bag of any kind
LAN (LAN) or wide area network (WAN)-be connected to subscriber computer are included, or, it may be connected to outer computer (such as profit
With ISP come by Internet connection).In certain embodiments, by using computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as PLD, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can perform computer-readable program instructions, so as to realize each side of the present invention
Face.
Referring herein to method according to embodiments of the present invention, device (system) and computer program flow chart and/
Or block diagram describes various aspects of the invention.It should be appreciated that each square frame and flow chart of flow chart and/or block diagram and/
Or in block diagram each square frame combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special-purpose computer or other programmable datas
The processor of processing meanss, so as to produce a kind of machine so that these instructions are by computer or other programmable datas
During the computing device of processing meanss, flowchart is generated and/or work(specified in one or more square frames in block diagram
The device of energy/action.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
Order causes computer, programmable data processing unit and/or other equipment to work in a specific way, so as to be stored with instruction
Computer-readable medium then includes a manufacture, and it is included in flowchart and/or one or more square frames in block diagram
The instruction of the various aspects of the function/action of regulation.
Can also computer-readable program instructions be loaded into computer, other programmable data processing units or other
On equipment so that perform series of operation steps on computer, other programmable data processing units or miscellaneous equipment, to produce
The computer implemented process of life, so that perform on computer, other programmable data processing units or miscellaneous equipment
Function/action specified in one or more square frames in instruction flowchart and/or block diagram.
Flow chart and block diagram in accompanying drawing shows system, method and the computer journey of multiple embodiments of the invention
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
A part for table one module, program segment or instruction a, part for the module, program segment or instruction is used comprising one or more
In the executable instruction of the logic function for realizing regulation.In some realizations as replacement, the function of being marked in square frame
Can be with different from the order marked in accompanying drawing generation.For example, two continuous square frames can essentially be held substantially in parallel
OK, they can also be performed in the opposite order sometimes, and this is depending on involved function.It is also noted that block diagram and/or
The combination of each square frame and block diagram and/or the square frame in flow chart in flow chart, can be with the function of performing regulation or dynamic
The special hardware based system made is realizing, or can be realized with the combination of computer instruction with specialized hardware.
It is described above various embodiments of the present invention, described above is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.In the case of the scope and spirit without departing from illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
Best explaining principle, practical application or the technological improvement to the technology in market of each embodiment, or lead this technology
Other those of ordinary skill in domain are understood that each embodiment disclosed herein.
Claims (17)
1. a kind of video recommendation method, it is characterised in that include：
Determine the corresponding label of the currently viewing video of user；
Multiple videos to be recommended are determined according to the corresponding label of the currently viewing video；
According to the corresponding label of the currently viewing video, multiple video corresponding labels to be recommended and the user couple
Multiple videos to be recommended are ranked up by the label answered, and obtain ranking results；
Multiple videos to be recommended are recommended according to the ranking results.
2. method according to claim 1, it is characterised in that according to the corresponding label of the currently viewing video, many
Multiple videos to be recommended are ranked up by the individual video corresponding label to be recommended and the corresponding label of the user,
Ranking results are obtained, including：
For video to be recommended each described, respectively according to the corresponding label of the currently viewing video, described to be recommended regard
Frequency corresponding label and the corresponding label of the user, determine the ranking value of the video to be recommended；
Multiple videos to be recommended are ranked up according to the ranking value, obtain ranking results.
3. method according to claim 2, it is characterised in that for video to be recommended each described, respectively according to described
The corresponding label of currently viewing video, the video corresponding label to be recommended and the corresponding label of the user, determine institute
The ranking value of video to be recommended is stated, including：
For video to be recommended each described, respectively according to the corresponding label of the currently viewing video and described to be recommended
The corresponding label of video determines the predicted value of the video to be recommended；
The predicted value of the video to be recommended is adjusted according to the user corresponding label, obtains the video to be recommended
Ranking value.
4. method according to claim 3, it is characterised in that to be recommended regarded to described according to the corresponding label of the user
The predicted value of frequency is adjusted, and obtains the ranking value of the video to be recommended, including：
Calculate the similarity of the corresponding label of user label corresponding with the video to be recommended；
The predicted value of the video to be recommended is adjusted according to the similarity, obtains the sequence of the video to be recommended
Value.
5. method according to claim 4, it is characterised in that according to prediction of the similarity to the video to be recommended
Value is adjusted, and obtains the ranking value of the video to be recommended, including：
Determine the corresponding weight of the predicted value and the corresponding weight of the similarity；
It is true according to the predicted value, the corresponding weight of the predicted value, the similarity and the corresponding weight of the similarity
The ranking value of the fixed video to be recommended.
6. method as claimed in any of claims 1 to 5, it is characterised in that the label includes multilayer.
7. method according to claim 4, it is characterised in that calculate the corresponding label of the user and to be recommended regard with described
Frequently the similarity of corresponding label, including：
Calculate similarity of the corresponding label of the user label corresponding with the video to be recommended in identical layer.
8. method according to claim 4, it is characterised in that the corresponding label of the user is to be recommended with described calculating
After the similarity of the corresponding label of video, methods described also includes：
In the case where the similarity is more than the first preset value and less than 1, the user couple is increased to the video to be recommended
The label answered, wherein, first preset value is more than or equal to 0 and less than 1.
9. a kind of video recommendations device, it is characterised in that include：
First label determining module, for determining the corresponding label of the currently viewing video of user；
Video determining module to be recommended, for determining multiple to be recommended regard according to the corresponding label of the currently viewing video
Frequently；
Order module, for according to the corresponding label of the currently viewing video, multiple video corresponding labels to be recommended
And the corresponding label of the user, multiple videos to be recommended are ranked up, obtain ranking results；
Video recommendations module, for being recommended multiple videos to be recommended according to the ranking results.
10. device according to claim 9, it is characterised in that the order module includes：
First ranking value determination sub-module, for for video to be recommended each described, being regarded according to described currently viewing respectively
Frequently corresponding label, the video corresponding label to be recommended and the corresponding label of the user, determine the video to be recommended
Ranking value；
Sorting sub-module, for being ranked up to multiple videos to be recommended according to the ranking value, obtains ranking results.
11. devices according to claim 10, it is characterised in that the first ranking value determination sub-module includes：
Predicted value determination sub-module, for for video to be recommended each described, respectively according to the currently viewing video pair
The label and the corresponding label of the video to be recommended answered determine the predicted value of the video to be recommended；
Second ranking value determination sub-module, for being entered to the predicted value of the video to be recommended according to the corresponding label of the user
Row adjustment, obtains the ranking value of the video to be recommended.
12. devices according to claim 11, it is characterised in that the second ranking value determination sub-module includes：
Similarity Measure submodule, for calculating the phase of the corresponding label of user label corresponding with the video to be recommended
Like degree；
3rd ranking value determination sub-module, for being adjusted to the predicted value of the video to be recommended according to the similarity,
Obtain the ranking value of the video to be recommended.
13. devices according to claim 12, it is characterised in that the 3rd ranking value determination sub-module includes：
Weight determination sub-module, for determining the corresponding weight of the predicted value and the corresponding weight of the similarity；
4th ranking value determination sub-module, for according to the predicted value, the corresponding weight of the predicted value, the similarity with
And the corresponding weight of the similarity determines the ranking value of the video to be recommended.
14. devices according to any one in claim 9 to 13, it is characterised in that the label includes multilayer.
15. devices according to claim 12, it is characterised in that the Similarity Measure submodule includes：
Identical layer Similarity Measure submodule, for calculating the corresponding label of user mark corresponding with the video to be recommended
Sign the similarity in identical layer.
16. devices according to claim 12, it is characterised in that described device also includes：
Label increases module, in the case where the similarity is more than the first preset value and less than 1, to be recommended regarding to described
Frequency increases the corresponding label of the user, wherein, first preset value is more than or equal to 0 and less than 1.
17. a kind of video recommendations devices, it is characterised in that include：
Processor；
For storing the memory of processor executable；
Wherein, the processor is configured to：
Determine the corresponding label of the currently viewing video of user；
Multiple videos to be recommended are determined according to the corresponding label of the currently viewing video；
According to the corresponding label of the currently viewing video, multiple video corresponding labels to be recommended and the user couple
Multiple videos to be recommended are ranked up by the label answered, and obtain ranking results；
Multiple videos to be recommended are recommended according to the ranking results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611256126.0A CN106649848B (en) | 2016-12-30 | 2016-12-30 | Video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611256126.0A CN106649848B (en) | 2016-12-30 | 2016-12-30 | Video recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106649848A true CN106649848A (en) | 2017-05-10 |
| CN106649848B CN106649848B (en) | 2020-12-29 |
Family
ID=58838241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611256126.0A Active CN106649848B (en) | 2016-12-30 | 2016-12-30 | Video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106649848B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944026A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
| CN108228911A (en) * | 2018-02-11 | 2018-06-29 | 北京搜狐新媒体信息技术有限公司 | The computational methods and device of a kind of similar video |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN108509584A (en) * | 2018-03-29 | 2018-09-07 | 北京百度网讯科技有限公司 | Selection method, device and the computer equipment of surface plot |
| CN108563670A (en) * | 2018-01-12 | 2018-09-21 | 武汉斗鱼网络科技有限公司 | Video recommendation method, device, server and computer readable storage medium |
| CN109558500A (en) * | 2018-11-21 | 2019-04-02 | 杭州网易云音乐科技有限公司 | Multimedia sequence generation method, medium, device and calculating equipment |
| CN110059221A (en) * | 2019-03-11 | 2019-07-26 | 咪咕视讯科技有限公司 | Video recommendation method, electronic equipment and computer readable storage medium |
| CN110413837A (en) * | 2019-05-30 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN110555157A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555131A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555135A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN111104550A (en) * | 2018-10-09 | 2020-05-05 | 北京奇虎科技有限公司 | Video recommendation method and device, electronic equipment and computer-readable storage medium |
| CN111212303A (en) * | 2019-12-30 | 2020-05-29 | 咪咕视讯科技有限公司 | Video recommendation method, server and computer-readable storage medium |
| CN111490929A (en) * | 2020-03-27 | 2020-08-04 | 威比网络科技(上海)有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN112256915A (en) * | 2020-09-29 | 2021-01-22 | 当趣网络科技(杭州)有限公司 | Search processing method and device suitable for split screen, electronic equipment and medium |
| CN112541115A (en) * | 2020-12-02 | 2021-03-23 | 创盛视联数码科技（北京）有限公司 | Method for recommending teaching video, electronic equipment and computer readable medium |
| CN113010739A (en) * | 2021-03-18 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Video tag auditing method and device and electronic equipment |
| CN113139083A (en) * | 2020-01-19 | 2021-07-20 | Tcl集团股份有限公司 | Video recommendation method and device, terminal equipment and storage medium |
| WO2021174890A1 (en) * | 2020-03-02 | 2021-09-10 | 腾讯科技（深圳）有限公司 | Data recommendation method and apparatus, and computer device and storage medium |
| CN113382279A (en) * | 2021-06-15 | 2021-09-10 | 北京百度网讯科技有限公司 | Live broadcast recommendation method, device, equipment, storage medium and computer program product |
| CN114040214A (en) * | 2021-10-13 | 2022-02-11 | 北京达佳互联信息技术有限公司 | Live broadcast room recommendation method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521321A (en) * | 2011-12-02 | 2012-06-27 | 华中科技大学 | Video search method based on search term ambiguity and user preferences |
| CN103440335A (en) * | 2013-09-06 | 2013-12-11 | 北京奇虎科技有限公司 | Video recommendation method and device |
| CN104219575A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津）科技有限公司 | Related video recommending method and system |
| CN104462573A (en) * | 2014-12-29 | 2015-03-25 | 北京奇艺世纪科技有限公司 | Method and device for displaying video retrieval results |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
-
2016
- 2016-12-30 CN CN201611256126.0A patent/CN106649848B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521321A (en) * | 2011-12-02 | 2012-06-27 | 华中科技大学 | Video search method based on search term ambiguity and user preferences |
| CN104219575A (en) * | 2013-05-29 | 2014-12-17 | 酷盛(天津）科技有限公司 | Related video recommending method and system |
| CN103440335A (en) * | 2013-09-06 | 2013-12-11 | 北京奇虎科技有限公司 | Video recommendation method and device |
| CN104462573A (en) * | 2014-12-29 | 2015-03-25 | 北京奇艺世纪科技有限公司 | Method and device for displaying video retrieval results |
| CN106202475A (en) * | 2016-07-18 | 2016-12-07 | 合网络技术（北京）有限公司 | The method for pushing of a kind of video recommendations list and device |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944026A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
| CN108563670A (en) * | 2018-01-12 | 2018-09-21 | 武汉斗鱼网络科技有限公司 | Video recommendation method, device, server and computer readable storage medium |
| CN108228911A (en) * | 2018-02-11 | 2018-06-29 | 北京搜狐新媒体信息技术有限公司 | The computational methods and device of a kind of similar video |
| CN108307240A (en) * | 2018-02-12 | 2018-07-20 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN108307240B (en) * | 2018-02-12 | 2019-10-22 | 北京百度网讯科技有限公司 | Video recommendation method and device |
| CN110555135A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555157A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN110555131A (en) * | 2018-03-27 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Content recommendation method, content recommendation device and electronic equipment |
| CN108509584A (en) * | 2018-03-29 | 2018-09-07 | 北京百度网讯科技有限公司 | Selection method, device and the computer equipment of surface plot |
| CN111104550A (en) * | 2018-10-09 | 2020-05-05 | 北京奇虎科技有限公司 | Video recommendation method and device, electronic equipment and computer-readable storage medium |
| CN109558500A (en) * | 2018-11-21 | 2019-04-02 | 杭州网易云音乐科技有限公司 | Multimedia sequence generation method, medium, device and calculating equipment |
| CN110059221A (en) * | 2019-03-11 | 2019-07-26 | 咪咕视讯科技有限公司 | Video recommendation method, electronic equipment and computer readable storage medium |
| CN110059221B (en) * | 2019-03-11 | 2023-10-20 | 咪咕视讯科技有限公司 | Video recommendation method, electronic device and computer readable storage medium |
| CN110413837A (en) * | 2019-05-30 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN110413837B (en) * | 2019-05-30 | 2023-07-25 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN111212303A (en) * | 2019-12-30 | 2020-05-29 | 咪咕视讯科技有限公司 | Video recommendation method, server and computer-readable storage medium |
| CN113139083A (en) * | 2020-01-19 | 2021-07-20 | Tcl集团股份有限公司 | Video recommendation method and device, terminal equipment and storage medium |
| WO2021174890A1 (en) * | 2020-03-02 | 2021-09-10 | 腾讯科技（深圳）有限公司 | Data recommendation method and apparatus, and computer device and storage medium |
| CN111490929B (en) * | 2020-03-27 | 2022-07-15 | 深圳市企鹅网络科技有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN111490929A (en) * | 2020-03-27 | 2020-08-04 | 威比网络科技(上海)有限公司 | Video clip pushing method and device, electronic equipment and storage medium |
| CN112256915A (en) * | 2020-09-29 | 2021-01-22 | 当趣网络科技(杭州)有限公司 | Search processing method and device suitable for split screen, electronic equipment and medium |
| CN112541115A (en) * | 2020-12-02 | 2021-03-23 | 创盛视联数码科技（北京）有限公司 | Method for recommending teaching video, electronic equipment and computer readable medium |
| CN113010739A (en) * | 2021-03-18 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Video tag auditing method and device and electronic equipment |
| CN113010739B (en) * | 2021-03-18 | 2024-01-26 | 北京奇艺世纪科技有限公司 | Video tag auditing method and device and electronic equipment |
| CN113382279A (en) * | 2021-06-15 | 2021-09-10 | 北京百度网讯科技有限公司 | Live broadcast recommendation method, device, equipment, storage medium and computer program product |
| CN113382279B (en) * | 2021-06-15 | 2022-11-04 | 北京百度网讯科技有限公司 | Live broadcast recommendation method, device, equipment, storage medium and computer program product |
| CN114040214A (en) * | 2021-10-13 | 2022-02-11 | 北京达佳互联信息技术有限公司 | Live broadcast room recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106649848B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649848A (en) | Video recommendation method and video recommendation device | |
| CN108460060A (en) | Video recommendation method and device | |
| CN110309353A (en) | Video index method and device | |
| CN104102819B (en) | A kind of determination method and apparatus of user's natural quality | |
| CN107341272A (en) | A kind of method for pushing, device and electronic equipment | |
| CN110442788A (en) | A kind of information recommendation method and device | |
| CN107545301B (en) | Page display method and device | |
| CN110225368B (en) | Video positioning method and device and electronic equipment | |
| CN109918662A (en) | A kind of label of e-sourcing determines method, apparatus and readable medium | |
| CN110110139A (en) | The method, apparatus and electronic equipment that a kind of pair of recommendation results explain | |
| CN108833990A (en) | Video caption display methods and device | |
| CN110413867A (en) | Method and system for commending contents | |
| US11074043B2 (en) | Automated script review utilizing crowdsourced inputs | |
| US11250468B2 (en) | Prompting web-based user interaction | |
| CA3021193A1 (en) | System, method, and device for analyzing media asset data | |
| CN110046278A (en) | Video classification methods, device, terminal device and storage medium | |
| CN112182281B (en) | Audio recommendation method, device and storage medium | |
| CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation | |
| CN109446324B (en) | Sample data processing method and device, storage medium and electronic equipment | |
| CN114969512A (en) | Object recommendation method and device and electronic equipment | |
| CN108733684A (en) | The recommendation method and device of multimedia resource | |
| US10678800B2 (en) | Recommendation prediction based on preference elicitation | |
| CN106686414B (en) | Video recommendation method and device | |
| CN110008348A (en) | The method and apparatus for carrying out network insertion in conjunction with node and side | |
| CN108833971A (en) | A kind of method for processing video frequency and device |
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 | ||
| CB02 | Change of applicant information |
Address after: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant after: Youku network technology (Beijing) Co.,Ltd. Address before: 100080 area a and C, 5 / F, block a, Sinosteel International Plaza, No. 8, Haidian Street, Haidian District, Beijing Applicant before: 1VERGE INTERNET TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200609 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100080 area a and C, 5 / F, block a, Sinosteel International Plaza, No. 8, Haidian Street, Haidian District, Beijing Applicant before: Youku network technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |