CN116132760A - Video cover display method and device, electronic equipment and storage medium - Google Patents
Video cover display method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116132760A CN116132760A CN202310034481.7A CN202310034481A CN116132760A CN 116132760 A CN116132760 A CN 116132760A CN 202310034481 A CN202310034481 A CN 202310034481A CN 116132760 A CN116132760 A CN 116132760A
- Authority
- CN
- China
- Prior art keywords
- cover
- video
- target
- map
- user
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000010586 diagram Methods 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 abstract description 12
- 238000004519 manufacturing process Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 6
- 238000013145 classification model Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 102100024607 DNA topoisomerase 1 Human genes 0.000 description 2
- 101000830681 Homo sapiens DNA topoisomerase 1 Proteins 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 208000004350 Strabismus Diseases 0.000 description 1
- 101150041570 TOP1 gene Proteins 0.000 description 1
- 101150107801 Top2a gene Proteins 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8549—Creating video summaries, e.g. movie trailer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Human Computer Interaction (AREA)
- User Interface Of Digital Computer (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
The embodiment of the invention provides a video cover display method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a plurality of cover charts corresponding to user preferences and a plurality of videos, scoring the cover charts according to the text descriptions and the user preferences, obtaining preference scores of the cover charts, sorting the cover charts based on the preference scores to obtain a first cover chart set, and sequentially displaying the plurality of target cover charts in the target first cover chart set of the target video when the residence time of the user on the target video is detected to exceed the preset residence time. According to the embodiment of the invention, each video is associated with the plurality of cover diagrams, so that the plurality of cover diagrams can be dynamically displayed on each video, the content richness of a user when browsing the video can be effectively improved, the attention of the user can be helped to be grasped, the user can quickly grasp the key points of the whole video, the displayed cover diagrams are matched with the user preference, and the distribution efficiency and the user experience of the cover diagrams can be greatly improved.
Description
Technical Field
The present invention relates to the field of video processing technologies, and in particular, to a video cover display method, a video cover display device, an electronic device, and a computer readable storage medium.
Background
In the online video field, the video content is displayed in two ways, one is displayed to the user in the form of a cover map, the distribution efficiency of the video content can be greatly improved by combining with a personalized recommendation system, and the other is displayed to the user in the form of video highlight clips, wherein the clips can help the user to find interesting points.
However, the first way of displaying is to display the cover map in a static single mode, the content of the display is limited, the attraction to users is not strong, and the distribution efficiency of the cover map is often an aspect which is ignored, because we are all the recommendation to the video, but rarely stop the recommendation to the cover map, and there is no effective mature scheme for matching the distribution of the cover map with the individuation of the users. The second way of presentation is for the whole, the segments do not represent the figures, emotions, etc. of the whole video, and the user does not have good help to understand the video, but rather misses the whole video content because the segments are disliked, and the visual quality of the whole presentation is lower because of the change of the playing frame number.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention have been developed to provide a video cover presentation method and corresponding video cover presentation apparatus, an electronic device, and a computer-readable storage medium that overcome or at least partially solve the foregoing problems.
In a first aspect of the present invention, there is provided a video cover displaying method, the method including:
acquiring user preferences of a user, and respectively acquiring a plurality of cover images corresponding to a plurality of videos; wherein each cover map carries a text description;
scoring each cover map according to the text description and the user preference to obtain preference scores corresponding to each cover map; each preference score is used for representing the click probability of the user on each cover map;
ordering the corresponding cover maps based on the preference scores for each video to obtain a first cover map set corresponding to each video;
when the time length of the user staying on the target video exceeds the preset stay time length, acquiring a target first cover diagram set corresponding to the target video;
And sequentially displaying the plurality of target cover diagrams in the target first cover diagram set.
Optionally, after the sequentially presenting the plurality of target cover maps in the target first cover map set, the method further includes:
counting click through rates CTR corresponding to the cover diagrams;
clustering the corresponding cover maps based on the CTR for each video to obtain a first style corresponding to each video;
generating first feedback information according to the first style corresponding to each video; the first feedback information is used for guiding the cover map making and optimizing of the creator.
Optionally, for each video, based on the preference score, sorting the corresponding plurality of cover maps to obtain a first cover map set corresponding to each video, including:
and for each video, based on the preference scores, performing descending processing on the corresponding cover maps to obtain a first cover map set corresponding to each video.
Optionally, for each video, based on the preference score, sorting the corresponding plurality of cover maps to obtain a first cover map set corresponding to each video, including:
For each video, performing descending processing on the corresponding cover images based on the preference scores to obtain a plurality of cover images corresponding to each video after descending;
screening a first preset number of front cover images from the corresponding descending cover images for each video;
and determining the front-ordered first preset number of cover diagrams as a first cover diagram set corresponding to each video respectively.
Optionally, the sequentially displaying the plurality of target cover diagrams in the target first cover diagram set includes:
and sequentially displaying the plurality of target cover diagrams in the target first cover diagram set according to the preset interval duration.
Optionally, for each video, clustering the corresponding plurality of cover maps based on the CTR to obtain a first style type corresponding to each video, including:
for each video, performing descending processing on the corresponding cover images based on the CTR to obtain a plurality of cover images corresponding to each video after descending;
screening a second preset number of front-ordered cover images from the corresponding descending cover images for each video;
Determining the front-ordered second preset number of cover diagrams as second cover diagram sets corresponding to the videos respectively;
and clustering a plurality of cover maps in the corresponding second cover map set aiming at each video to obtain a first style type corresponding to each video.
Optionally, the method further comprises:
determining a plurality of videos of the same type;
clustering a plurality of cover maps in a second cover map set corresponding to the plurality of videos of the same type to obtain a second style type of the plurality of videos of the same type;
generating second feedback information according to a second style type of the plurality of videos of the same type; the second feedback information is used for guiding the cover map making and optimizing of the creator.
In a second aspect of the present invention, there is also provided a video cover presentation apparatus, the apparatus comprising:
the cover map acquisition module is used for acquiring user preferences of a user and respectively acquiring a plurality of cover maps corresponding to a plurality of videos; wherein each cover map carries a text description;
the cover map scoring module is used for scoring each cover map according to the text description and the user preference to obtain preference scores corresponding to each cover map; each preference score is used for representing the click probability of the user on each cover map;
The cover map ordering module is used for ordering the corresponding plurality of cover maps according to the preference scores of the videos to obtain first cover map sets respectively corresponding to the videos;
the target first cover chart set acquisition module is used for acquiring a target first cover chart set corresponding to a target video when the time length of the user staying on the target video exceeds the preset stay time length;
and the target cover diagram sequence display module is used for sequentially displaying the plurality of target cover diagrams in the target first cover diagram set.
Optionally, after the sequentially displaying the plurality of target cover maps in the target first cover map set, the apparatus further includes:
the CTR statistics module is used for counting CTRs corresponding to the cover diagrams;
the first clustering module is used for clustering the corresponding cover maps based on the CTR for each video to obtain a first style corresponding to each video;
the first feedback information generation module is used for generating first feedback information according to the first style types corresponding to the videos; the first feedback information is used for guiding the cover map making and optimizing of the creator.
Optionally, the cover map ordering module includes:
and the first descending processing sub-module is used for descending the sequence of the corresponding cover images based on the preference scores for each video to obtain a first cover image set corresponding to each video.
Optionally, the cover map ordering module includes:
the second descending processing sub-module is used for descending the corresponding plurality of cover images according to the preference scores of the videos to obtain a plurality of descending cover images corresponding to the videos;
the first screening sub-module is used for screening a first preset number of front cover images from the corresponding descending cover images for each video;
and the first cover chart set determining sub-module is used for determining the first preset number of cover charts which are ranked at the front as first cover chart sets corresponding to the videos respectively.
Optionally, the target cover map sequence display module includes:
and the target cover diagram sequential display sub-module is used for sequentially displaying the plurality of target cover diagrams in the target first cover diagram set according to the preset interval duration.
Optionally, the first clustering module includes:
a third descending processing sub-module, configured to, for each video, perform descending processing on the corresponding plurality of cover maps based on the CTR, to obtain a plurality of descending cover maps corresponding to each video;
the second screening sub-module is used for screening a second preset number of front cover images from the corresponding cover images in descending order according to the videos;
the second cover chart set submodule is used for determining the second preset number of cover charts which are ranked at the front as second cover chart sets corresponding to the videos respectively;
and the first clustering sub-module is used for clustering a plurality of cover maps in the corresponding second cover map set aiming at each video to obtain a first style type corresponding to each video.
Optionally, the apparatus further comprises:
the video determining module of the same type is used for determining a plurality of videos of the same type;
the second clustering module is used for clustering a plurality of cover graphs in a second cover graph set corresponding to the plurality of videos of the same type to obtain a second style type of the plurality of videos of the same type;
The second feedback information generation module is used for generating second feedback information according to a second style type of the plurality of videos with the same type; the second feedback information is used for guiding the cover map making and optimizing of the creator.
In still another aspect of the present invention, there is also provided an electronic device including: a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor, performs the steps of the video cover presentation method as described above.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the video cover presentation method as described above.
Compared with the prior art, the embodiment of the invention has the following advantages:
in the embodiment of the invention, user preference of a user is acquired, a plurality of cover charts corresponding to a plurality of videos are acquired respectively, each cover chart carries text description, then each cover chart is scored according to the text description and the user preference to obtain preference scores corresponding to each cover chart, each preference score is used for representing click probability of the user on each cover chart, then the corresponding plurality of cover charts are ordered according to the preference scores to obtain first cover chart sets corresponding to the videos respectively, and further when the residence time of the user on the target videos is detected to exceed the preset residence time, the target first cover chart sets corresponding to the target videos are acquired, so that the plurality of target cover charts in the target first cover chart sets are displayed sequentially. According to the embodiment of the invention, each video is associated with the plurality of cover diagrams, so that the plurality of cover diagrams can be dynamically displayed on each video, the content richness of a user when browsing the video can be effectively improved, the attention of the user can be helped to be grasped, the user can quickly grasp the key points of the whole video, the displayed cover diagrams are matched with the user preference, and the distribution efficiency and the user experience of the cover diagrams can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart illustrating steps of a first embodiment of a method for displaying a video cover according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a second embodiment of a method for displaying a video cover according to an embodiment of the present invention;
FIGS. 3A-3D are flowcharts of sub-steps of a video cover presentation method embodiment two of the embodiments of the present invention;
FIG. 4 is a block diagram illustrating a video cover display apparatus according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the online video field, video content is usually presented to users in the form of cover sheets, and the distribution efficiency of the video content can be greatly improved through a personalized recommendation system, however, the following problems exist in the conventional manner in the industry:
1. the static cover map is mainly shown, but from the viewpoint of visual attention, a user can more easily capture dynamic changes;
2. the same video content often has a large number of cover diagrams with different styles, but only one cover diagram can be displayed, the communicated information is not rich enough, and the waste of resources is caused;
3. the efficiency of distribution of the cover map is often an aspect that is ignored because we are all recommends to video, but rarely stop to cover map, and there is no effective maturation scheme for matching the distribution of the cover map to the personalization of the user.
There are also some ways in which the industry can utilize GIFs (Graphics Interchange Format, image interchange formats) to present video content, which can help users find interesting points of interest, but for the whole, segment and
people, emotion and the like which do not represent the whole video do not have good help for users to understand the video, 5 can miss the whole video content because of dislike of the clips, and the visual quality of the whole display is lower due to the change of the playing frame number.
The cover diagram mode is adopted for displaying, so that a user can quickly grasp the key points of the video, because the production needs to be completed by a professional, the video is understood to a certain extent, the production cost is high,
if the display effect is not good, huge waste is caused. However, in comparison with GIF, a static seal 0 panel is very elegant and has limited display.
In view of the above problems, an embodiment of the present invention provides a method for displaying a video cover, where each video is associated with a plurality of cover diagrams, so that each video can dynamically display a plurality of cover diagrams, which can effectively promote the content richness of a user when browsing videos, and is helpful for grasping the attention of the user and is quick
The user can grasp the key points of the whole video rapidly, the displayed cover map is matched with the user preference, and 5, the distribution efficiency and the user experience of the cover map can be greatly improved.
Referring to fig. 1, a flowchart illustrating steps of a first embodiment of a method for displaying a video cover according to an embodiment of the present invention is shown, where the method may specifically include the following steps:
0 in the embodiment of the invention, the method and the device can be applied to a server, and the server can collect the history lines of the user
The historical behavior data is then analyzed for data, resulting in user preferences, which may include channel preferences and genre preferences.
The server can acquire a plurality of covers corresponding to a plurality of videos respectively while acquiring user preferences
The image, namely, each video corresponds to a plurality of cover charts, wherein the cover charts can be manufactured by a professional, and 5, because the professional has made a certain knowledge on the video before the cover charts are manufactured, the professional is clear how to design the plurality of cover charts of the video, so that the overall gist of the video is expressed through the cover charts.
The machine can know the value of each pixel of the cover map, but cannot directly understand the meaning of the cover map, so that a professional can express the characteristics of the cover map in a text mode, the cover map carries text description, and a server can recognize the characteristics of the cover map by reading the text description.
After obtaining the user preference and the text description of each cover map, the user preference and the text description of each cover map may be matched, and each cover map may be scored according to the matching result, so as to obtain the preference score of each cover map.
The preference score can predict the click probability of the user on the cover map. For example, the higher the preference score, the higher the estimated click probability, indicating that the user is likely to like the cover map, thereby clicking the cover map; the lower the preference score, the lower the estimated click probability, indicating that the user is less interested in the cover map and thus does not click on the cover map.
Since each video corresponds to a plurality of cover charts, and when the cover charts are displayed, the cover charts are displayed one by one, the display sequence of the cover charts corresponding to each video needs to be determined.
The cover map presentation order may be determined based on the preference scores obtained above. Specifically, for each video, the plurality of cover maps corresponding to each video may be ordered based on the preference score of each cover map, thereby obtaining a first cover map set corresponding to each video.
And 104, when the time length of the user staying on the target video exceeds the preset stay time length, acquiring a target first cover map set corresponding to the target video.
When the user browses the video, the page can be slid through an up-sliding operation or a down-sliding operation. The user slides the page with the data record, so that the time length of the user staying on the video in the page can be detected based on the data record, and whether the time length of the user staying on a certain video exceeds a certain time length can be detected. If the duration of the user staying on a certain video exceeds a certain duration, the user can be stated to be interested in the video, and therefore, when the duration of the user staying on the target video exceeds the preset stay duration, the target first cover map set corresponding to the target video can be acquired. The preset residence time length can be set to be 0.5s/1s/2s, and the numerical value of the preset residence time length is not limited in the embodiment of the invention.
And 105, sequentially displaying the plurality of target cover diagrams in the target first cover diagram set.
Because the first cover map set is obtained by sorting the plurality of cover maps, the plurality of target cover maps in the target first cover map set are sequential, so that the plurality of target cover maps can be displayed sequentially. For example, assuming that the target cover map a is Top1, the target cover map b is Top2, … …, and the target cover map c is TopN (N is a positive integer greater than 2), then the target cover map a may be displayed first, then the cover maps b, … …, and finally the target cover map c may be displayed during dynamic display.
In summary, in the embodiment of the invention, a user preference of a user is obtained, a plurality of cover charts corresponding to a plurality of videos are respectively obtained, each cover chart carries text description, then each cover chart is scored according to the text description and the user preference to obtain preference scores corresponding to each cover chart, each preference score is used for representing click probability of the user on each cover chart, then the corresponding plurality of cover charts are sequenced based on the preference scores for each video to obtain first cover chart sets corresponding to each video respectively, and further when the fact that the stay time of the user on the target video exceeds the preset stay time is detected, the target first cover chart sets corresponding to the target videos are obtained, and therefore the plurality of target cover charts in the target first cover chart sets are displayed sequentially. According to the embodiment of the invention, each video is associated with the plurality of cover diagrams, so that the plurality of cover diagrams can be dynamically displayed on each video, the content richness of a user when browsing the video can be effectively improved, the attention of the user can be helped to be grasped, the user can quickly grasp the key points of the whole video, the displayed cover diagrams are matched with the user preference, and the distribution efficiency and the user experience of the cover diagrams can be greatly improved.
Referring to fig. 2, a flowchart illustrating steps of a second embodiment of a method for displaying a video cover according to an embodiment of the present invention is shown, where the method specifically includes the following steps:
The embodiment of the invention can be applied to a server, the server can collect historical behavior data of each user from each video client, the historical behavior data comprise records of videos frequently watched by the user, and the server analyzes the records to obtain user preferences corresponding to each user, wherein the user preferences can comprise channel preferences and type preferences.
Specifically, for a user, logging in a video website or a video APP (Application), a cover map is seen first, and the feature of channel preference can determine whether the user clicks on a certain video, so as to enhance the determination of the click probability of the cover map. Illustratively, channel preferences may include, but are not limited to, movies, television shows, cartoons, documentaries, and the like.
In particular, the type of user is highly diverse. For example, users like characters in the cover map to be relatively tense, or to be exaggeratedly expressed, or to be expressed; for another example, users like cover drawings to be thrilling, either hot or artistic; still other potential types of preferences may be analyzed from big data, for example, the user likes the character in the cover chart to be direct-looking, or strabismus, or leg length, or hot.
The server may acquire a plurality of cover maps corresponding to a plurality of videos, that is, each video corresponds to a plurality of cover maps, while acquiring user preferences. Since the hot-play period of each video is not so long, each video corresponds to a cover map of at most, i.e., on the order of hundreds of digits, for example, each video may correspond to 100 cover maps.
The cover map can be manufactured by a professional, and because the professional has made a certain knowledge about the video before the cover map is manufactured, the professional can configure a corresponding text description for each cover map in the process of manufacturing the cover map, so that the cover map carries the text description, wherein the text description refers to design languages involved in the process of manufacturing the cover map, such as image blurring, main angle highlighting, font color, number of characters, expression type, three-dimensional angle of character posture, whether animals are contained, and the like.
It should be noted that, the gesture is mainly described by the face or the body of the person, and the gesture may be described by using a three-dimensional angle, where the three-dimensional angle refers to the right-hand cartesian coordinate in three-dimensional space, and includes Pitch, yaw, roll, where Pitch is rotated about the X-axis, yaw is rotated about the Y-axis, roll is rotated about the Z-axis, and the gesture of the person in the cover map, such as the person is looking straight, such as the person is standing obliquely, and so on, may be determined by Pitch, yaw, roll.
In the embodiment of the invention, the server comprises a pre-trained classification model, and the classification model can be trained and iterated based on the characteristics of the cover map sample, the characteristics of the user sample and the cross characteristics of the user sample and the cover map sample.
After obtaining the user preference and the text description of each cover map, the user preference and the text description can be input into the classification model, the user preference and the text description of each cover map can be matched through the classification model, and each cover map is scored according to the matching result, so that the preference score of each cover map is obtained.
Wherein each preference score may be used to characterize the probability of a user clicking on each cover sheet. For example, if the preference score of a cover sheet is higher, the higher the click probability of the user on the cover sheet is, which indicates that the user is likely to like the cover sheet, so as to click the cover sheet; if the preference score of a cover sheet is lower, the lower the probability of clicking on the cover sheet by the user is indicated, indicating that the cover sheet is less interesting to the user and is not clicked.
In one example, assuming that the user's channel preferences are movies, the genre preferences are like the characters in the cover map are happy, happy and straight ahead, and like pets, then when matching the user's user preferences with the text description of each cover map, the cover maps are of the movie genre, the characters in the cover map are happy, happy and straight ahead, the cover maps contain animals, the cover maps are highly matched with the user's preferences, and the resulting preference scores of the cover maps are high.
After the preference score for each cover sheet is obtained, the cover sheets may be ranked using the preference score. Specifically, for each video, the plurality of cover maps corresponding to each video may be ordered based on the preference score of each cover map, so as to obtain a first cover map set corresponding to each video respectively.
In an alternative embodiment of the present invention, referring to fig. 3A, which shows a flowchart of sub-steps of a second embodiment of a video cover presentation method in an embodiment of the present invention, step 203 may include the following sub-steps:
And S11, aiming at each video, carrying out descending processing on the corresponding cover maps based on the preference scores to obtain a first cover map set corresponding to each video.
In a specific implementation, for each video, a plurality of cover maps corresponding to each video may be arranged according to a sequence from the big to the small of the preference score, so as to obtain a first cover map set corresponding to each video respectively.
In one example, assuming video A and video B, the cover map of video A includes cover map A 1 ～A 100 The cover map of video B includes cover map B 1 ～B 100 . Then for video a, cover map a may be displayed in order of the preference score from greater to lesser 1 ～A 100 Arranged, e.g. cover sheet A 100 The preference score of (2) is highest, then cover map A 100 Can be arranged at the first position (Top 1), cover map A 1 Is the lowest, then cover map A 1 Can be arranged at position 100 (Top 100). Similarly, for video B, cover map B may be displayed in order of the preference score from greater to lesser 1 ～B 100 Arranged, e.g. cover sheet B 10 Is lower than the cover map B 20 Then cover map B 20 Can be arranged on the cover map B 10 Is provided.
In another alternative embodiment of the present invention, referring to fig. 3B, which shows a flowchart of sub-steps of a second embodiment of a video cover displaying method in an embodiment of the present invention, step 203 may include the following sub-steps:
Step S21, for each video, performing descending processing on the corresponding cover images based on the preference scores to obtain descending cover images corresponding to each video;
step S22, screening a first preset number of front cover images from the corresponding descending cover images for each video;
and S23, determining the front-ordered first preset number of cover images as a first cover image set corresponding to each video.
Since the magnitude of the cover map corresponding to each video is a hundred, for example, each video can correspond to 100 cover maps, however, in practice, considering the condition of network speed loading, a certain limit can be made on the number of cover map displays corresponding to each video.
In a specific implementation, for each video, the plurality of cover maps corresponding to each video may be arranged according to the order of the preference scores from the large to the small, so as to obtain the plurality of cover maps corresponding to each video after descending. Then, a certain limit may be further made on the number of cover images displayed corresponding to each video, specifically, for each video, a first preset number of cover images with a front ranking may be screened out from a plurality of cover images with a descending ranking corresponding to each video, and then the first preset number of cover images with the front ranking may be determined as a first cover image set corresponding to each video, where the first preset number may be set according to an actual situation, for example, the first preset number may be set to 10/15/20, etc., and the value of the first preset number is not limited in the embodiments of the present invention.
In one example, assuming video C, the cover map of video C includes cover map C 1 ～C 100 Then for video C, cover map C may be displayed in order of the preference score from greater to lesser 1 ～C 100 The arrangement is performed to obtain a plurality of cover maps after descending the order of the video C, then a first preset number of cover maps before ordering are further screened out of the plurality of cover maps after descending the order of the video C, and assuming that the first preset number is 10, the first 10 cover maps before ordering can be screened out of the plurality of cover maps after descending the order of the video C, so that the 10 cover maps are determined as a first cover map set of the video C, for example, the cover maps at TOP1 to TOP10 are sequentially C99, C85, C90, C100, C25, C84, C75, C1, C12, and C15, and the cover maps at TOP1 to TOP10 are sequentially 10 cover maps before ordering, so that the cover maps can be determined as the first cover map set of the video C.
And 204, when the time length of the user staying on the target video exceeds the preset stay time length, acquiring a target first cover map set corresponding to the target video.
In the embodiment of the invention, the time window dynamically displayed can be that the time length of a user staying on a certain video exceeds the preset stay time length, the preset stay time length can be set according to actual conditions, for example, the preset stay time length can be set to be 0.5s/1s/2s, and the numerical value of the preset stay time length is not limited.
If the time length of the user staying on the target video exceeds the preset stay time length, the user can be indicated to be interested in the target video, and therefore the target first cover map set corresponding to the target video can be obtained.
In the embodiment of the present invention, the number of the target cover sheets included in the target first cover sheet set may be all the cover sheets in descending order in the substep S11, or may be a first preset number of cover sheets in descending order and after screening in the substeps S21 to S23. For example, assuming that 100 cover sheets are corresponding to each video, and the first preset number is set to 10, the number of target cover sheets may be 100 cover sheets in descending order through the substep S11, or 10 cover sheets in descending order and screening through the substeps S21 to S23.
Whether the 100 cover charts are subjected to descending order or the 10 cover charts are subjected to descending order and screening, the plurality of target cover charts in the target first cover chart set are sequential, so that the 100 target cover charts can be displayed sequentially or the 10 target cover charts can be displayed sequentially.
In an alternative embodiment of the present invention, referring to fig. 3C, which shows a flowchart of sub-steps of a video cover presentation method embodiment two in an embodiment of the present invention, step 205 may include the sub-steps of:
and S31, sequentially displaying the plurality of target cover diagrams in the target first cover diagram set according to a preset interval duration.
In the embodiment of the invention, the preset interval duration can be set, and the preset interval duration refers to the switching duration of the cover images, namely the display duration of a single cover image, and can be set according to practical situations, for example, the preset interval duration can be set to be 1s/0.5s/0.1s, etc., and the numerical value of the preset interval duration is not limited in the embodiment of the invention.
In one example, assuming that the preset stay time period is 0.5s, the preset interval time period is 0.5s, and the time period when the user stays in the target video C is 8s, which exceeds the preset stay time period, then the plurality of target cover images in the target first cover image set C of the target video C can be dynamically displayed, if the target first cover image set C contains 10 target cover images, C99, C85, C90, C100, C25, C84, C75, C1, C12 and C15 in sequence, then from 0.5s, the first cover image C99 is displayed, after displaying for 0.5s, the next cover image C85 is switched, after displaying for 0.5s, the next cover image C90, … … is switched, after displaying for 0.5s, the last cover image C15 is switched, after displaying for 0.5s, the first cover image C99 can be returned, and the cyclic display is performed.
Furthermore, the conventional manner in the industry has problems, in addition to those mentioned in the background, of:
the production of the cover map is often completed by professionals, and the clicking condition of the cover map on a website is not concerned, so that the cover map user lacks feedback and guidance to the creator, the creator lacks data description of the design concept of the cover map, and the collaboration efficiency between the upstream and the downstream is low, so that the resource is wasted.
In view of the above problems, the embodiment of the present invention may further perform feedback and guidance on the creator after grasping the preference of the user for the cover map, specifically refer to steps 206 to 208.
And 206, counting CTRs corresponding to the cover diagrams.
In the embodiment of the invention, a preset period can be set, and each time the preset period is reached, a corresponding CTR (Click-Through-Rate) of each cover map can be counted, specifically, the actual Click times of the cover map can be counted first, and then the ratio of the actual Click times to the total actual Click times is calculated, wherein the ratio is the Click Rate CTR of the cover map.
The actual number of clicks refers to the actual number of clicks +1 of a cover chart if the user clicks the cover chart when displaying the cover chart.
The actual total clicking times are obtained by adding the actual clicking times corresponding to the cover diagrams in the first cover diagram set.
The click through rate CTR can be used for determining the cover map with high click rate, and popular cover map style types can be known by clustering the cover map with high click rate. Specifically, for each video, based on the click through rate CTR of each cover map, a plurality of cover maps corresponding to each video may be clustered, so as to obtain a first style corresponding to each video.
In an alternative embodiment of the present invention, referring to fig. 3D, which shows a flowchart of sub-steps of a second embodiment of a video cover presentation method in an embodiment of the present invention, step 207 may include the following sub-steps:
step S41, for each video, performing descending processing on the corresponding cover images based on the CTR to obtain a plurality of cover images corresponding to each video after descending;
Step S42, screening out a second preset number of front cover images from the corresponding cover images in descending order according to the videos;
step S43, determining the front-ordered second preset number of cover images as second cover image sets corresponding to the videos respectively;
and a substep S44, for each video, clustering a plurality of cover maps in the corresponding second cover map set to obtain a first style corresponding to each video.
In a specific implementation, for each video, a plurality of cover graphs corresponding to each video may be arranged according to a sequence from high to low of a click through rate CTR, so as to obtain a plurality of cover graphs corresponding to each video after descending, then a second preset number of cover graphs with a front ranking may be screened out from the plurality of cover graphs corresponding to each video after descending, then the second preset number of cover graphs with the front ranking may be determined as a second cover graph set corresponding to each video, and then a plurality of cover graphs in the second cover graph set corresponding to each video may be clustered respectively, so as to obtain a first style type corresponding to each video, where the second preset number may be set according to an actual situation, for example, the second preset number may be set to 20%, and the numerical value of the second preset number is not limited in the embodiment of the present invention.
In one example, assuming a video D, the cover map of the video D includes cover map D 1 ～D 100 Then, for the video D, the cover map D of the video D may be displayed in order of the click through rate CTR from large to small 1 ～D 100 The plurality of front cover maps are sorted in descending order to obtain a plurality of front cover maps for the video D, then the front second preset number of front cover maps can be sorted out of the plurality of front cover maps for the video D, if the second preset number is 20%, the front 20 front cover maps can be sorted out of the plurality of front cover maps for the video D, so that the 20 front cover maps can be determined as a second front cover map set of the video D, for example, the front cover maps at TOP 1-TOP 20 are sequentially D100, D20, D87, D24, D3, D6, D92, D14, D45, D55, D77, D41, D42, D32, D39, D94, D9, D11, D70, D69, and the front cover maps at TOP 1-TOP 20 are the front 20 front cover maps, so that the front cover maps can be determined as a second front cover map set of the video D, and then the front cover maps of the second front cover maps of the video D can be clustered to obtain a style of the first front cover map set of the video D.
It should be noted that, the first cover map set is obtained by descending order based on user preference, or the first cover map set is obtained by descending order based on user preference and screening based on the first preset number, and the second cover map set is obtained by descending order based on click through rate CTR and screening based on the second preset number.
After the first style corresponding to each video is obtained, the first style can be used as first feedback information for feeding back and guiding the cover drawing production and optimization of the subsequent creative of the creator, such as guiding the creation of links such as the drawing of the cover drawing, figures, expressions and the like.
In an alternative embodiment of the present invention, the method may further include:
determining a plurality of videos of the same type; clustering a plurality of cover maps in a second cover map set corresponding to the plurality of videos of the same type to obtain a second style type of the plurality of videos of the same type; generating second feedback information according to a second style type of the plurality of videos of the same type; the second feedback information is used for guiding the cover map making and optimizing of the creator.
Besides the first style corresponding to each video, the second style of a plurality of videos of the same type can be fed back, and more originals which are not related to the current video can be found through the second style.
It should be noted that the first genre is a popular cover style type for a single video, and the second genre is a popular cover style type for multiple videos of the same type.
In a specific implementation, a plurality of videos of the same type are determined, then second cover map sets corresponding to the videos of the same type are respectively obtained, and then the plurality of cover maps in each second cover map set can be clustered uniformly, so that a second style type of the videos of the same type is obtained.
After the second style type of the plurality of videos with the same type is obtained, the second style type can be used as second feedback information for feeding back and guiding the cover drawing production and optimization of the subsequent creative of the creator, such as guiding of link creation of the cover drawing, such as drawing of a figure, expression and the like.
In one example, assuming that video C and video D are the same type of video, the second cover map set of video C includes 20 high-click-rate cover maps, and the second cover map set of video D also includes 20 high-click-rate cover maps, then the 20 high-click-rate cover maps of video C and the 20 high-click-rate cover maps of video D may be clustered together, so as to obtain a second style type belonging to video C and video D, and further, more creatives that are not related to video C or video D may be found.
In summary, in the embodiment of the invention, a user preference of a user is obtained, a plurality of cover charts corresponding to a plurality of videos are respectively obtained, each cover chart carries text description, then each cover chart is scored according to the text description and the user preference to obtain preference scores corresponding to each cover chart, each preference score is used for representing click probability of the user on each cover chart, then the corresponding plurality of cover charts are sequenced based on the preference scores for each video to obtain first cover chart sets corresponding to each video respectively, and further when the fact that the stay time of the user on the target video exceeds the preset stay time is detected, the target first cover chart sets corresponding to the target videos are obtained, and therefore the plurality of target cover charts in the target first cover chart sets are displayed sequentially. According to the embodiment of the invention, each video is associated with the plurality of cover diagrams, so that the plurality of cover diagrams can be dynamically displayed on each video, the content richness of a user when browsing the video can be effectively improved, the attention of the user can be helped to be grasped, the user can quickly grasp the key points of the whole video, the displayed cover diagrams are matched with the user preference, and the distribution efficiency and the user experience of the cover diagrams can be greatly improved.
In addition, the embodiment of the invention also counts CTR corresponding to each cover map, and then clusters a plurality of corresponding cover maps based on CTR for each video to obtain a first style corresponding to each video, so as to generate first feedback information according to the first style corresponding to each video, wherein the first feedback information is used for guiding the cover map production and optimization of an creator. According to the embodiment of the invention, the production text description is produced during production and the production preference evaluation is carried out during display by linking the production link and the display link, so that a scientific and effective closed loop is realized, the development efficiency is greatly improved, and the business presents the spiral rising effect.
Referring to fig. 4, a block diagram of a video cover display device according to an embodiment of the present invention is shown, which may specifically include the following modules:
the cover map obtaining module 401 is configured to obtain user preferences of a user, and obtain a plurality of cover maps corresponding to a plurality of videos respectively; wherein each cover map carries a text description;
a cover map scoring module 402, configured to score each cover map according to the text description and the user preference, so as to obtain a preference score corresponding to each cover map; each preference score is used for representing the click probability of the user on each cover map;
The cover map ordering module 403 is configured to order, for each video, a plurality of corresponding cover maps based on the preference score, to obtain a first cover map set corresponding to each video respectively;
the target first cover chart set obtaining module 404 is configured to obtain a target first cover chart set corresponding to a target video when it is detected that a stay time period of a user on the target video exceeds a preset stay time period;
the target cover map sequence display module 405 is configured to sequentially display a plurality of target cover maps in the target first cover map set.
In an optional embodiment of the present invention, after the sequentially presenting the plurality of target cover maps in the target first cover map set, the apparatus may further include:
the CTR statistics module is used for counting click through rates CTR corresponding to the cover graphs;
the first clustering module is used for clustering the corresponding cover maps based on the CTR for each video to obtain a first style corresponding to each video;
the first feedback information generation module is used for generating first feedback information according to the first style types corresponding to the videos; the first feedback information is used for guiding the cover map making and optimizing of the creator.
In an alternative embodiment of the present invention, the cover sheet sorting module 403 may include:
and the first descending processing sub-module is used for descending the sequence of the corresponding cover images based on the preference scores for each video to obtain a first cover image set corresponding to each video.
In an alternative embodiment of the present invention, the cover sheet sorting module 403 may include:
the second descending processing sub-module is used for descending the corresponding plurality of cover images according to the preference scores of the videos to obtain a plurality of descending cover images corresponding to the videos;
the first screening sub-module is used for screening a first preset number of front cover images from the corresponding descending cover images for each video;
and the first cover chart set determining sub-module is used for determining the first preset number of cover charts which are ranked at the front as first cover chart sets corresponding to the videos respectively.
In an alternative embodiment of the present invention, the target cover map sequence display module 405 may include:
and the target cover diagram sequential display sub-module is used for sequentially displaying the plurality of target cover diagrams in the target first cover diagram set according to the preset interval duration.
In an alternative embodiment of the present invention, the first clustering module may include:
a third descending processing sub-module, configured to, for each video, perform descending processing on the corresponding plurality of cover maps based on the CTR, to obtain a plurality of descending cover maps corresponding to each video;
the second screening sub-module is used for screening a second preset number of front cover images from the corresponding cover images in descending order according to the videos;
the second cover chart set submodule is used for determining the second preset number of cover charts which are ranked at the front as second cover chart sets corresponding to the videos respectively;
and the first clustering sub-module is used for clustering a plurality of cover maps in the corresponding second cover map set aiming at each video to obtain a first style type corresponding to each video.
In an alternative embodiment of the present invention, the apparatus may further include:
the video determining module of the same type is used for determining a plurality of videos of the same type;
the second clustering module is used for clustering a plurality of cover graphs in a second cover graph set corresponding to the plurality of videos of the same type to obtain a second style type of the plurality of videos of the same type;
The second feedback information generation module is used for generating second feedback information according to a second style type of the plurality of videos with the same type; the second feedback information is used for guiding the cover map making and optimizing of the creator.
In summary, in the embodiment of the invention, a user preference of a user is obtained, a plurality of cover charts corresponding to a plurality of videos are respectively obtained, each cover chart carries text description, then each cover chart is scored according to the text description and the user preference to obtain preference scores corresponding to each cover chart, each preference score is used for representing the click probability of the user on each cover chart, then the corresponding plurality of cover charts are ordered according to each video based on the preference scores to obtain a first cover chart set corresponding to each video, and when the time length of the user staying on the target video is detected to exceed the preset staying time length, a target first cover chart set corresponding to the target video is obtained, and therefore the plurality of target cover charts in the target first cover chart set are sequentially displayed. According to the embodiment of the invention, each video is associated with the plurality of cover diagrams, so that the plurality of cover diagrams can be dynamically displayed on each video, the content richness of a user when browsing the video can be effectively improved, the attention of the user can be helped to be grasped, the user can quickly grasp the key points of the whole video, the displayed cover diagrams are matched with the user preference, and the distribution efficiency and the user experience of the cover diagrams can be greatly improved.
In addition, the embodiment of the invention also counts CTR corresponding to each cover map, and then clusters a plurality of corresponding cover maps based on CTR for each video to obtain a first style corresponding to each video, so as to generate first feedback information according to the first style corresponding to each video, wherein the first feedback information is used for guiding the cover map production and optimization of an creator. According to the embodiment of the invention, the production text description is produced during production and the production preference evaluation is carried out during display by linking the production link and the display link, so that a scientific and effective closed loop is realized, the development efficiency is greatly improved, and the business presents the spiral rising effect.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The embodiment of the invention also provides an electronic device, as shown in fig. 5, which comprises a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502 and the memory 503 complete communication with each other through the communication bus 504,
a memory 503 for storing a computer program;
The processor 501 is configured to implement the processes of the video cover display method embodiment when executing the program stored in the memory 503.
The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface is used for communication between the terminal and other devices.
The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
The embodiment of the invention also provides a computer readable storage medium, wherein instructions are stored in the computer readable storage medium, when the computer readable storage medium runs on a computer, the computer is caused to execute the video cover showing method in any of the above embodiments.
Embodiments of the present invention also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the video cover presentation method of any of the above embodiments.
In the above embodiments, it may be implemented in whole or in part 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, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It is noted that relational terms such as first and second, and the like are 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. Moreover, 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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (10)
1. A method of displaying a video cover, the method comprising:
acquiring user preferences of a user, and respectively acquiring a plurality of cover images corresponding to a plurality of videos; wherein each cover map carries a text description;
scoring the cover diagrams according to the text description and the user preference to obtain 5 preference scores corresponding to the cover diagrams; each preference score is used for representing the click probability of the user on each cover map;
ordering the corresponding cover maps based on the preference scores for each video to obtain a first cover map set corresponding to each video;
when the time length of the user staying on the target video exceeds the preset stay time length, acquiring a target first cover diagram set corresponding to the 0 target video;
and sequentially displaying the plurality of target cover diagrams in the target first cover diagram set.
2. The method of claim 1, wherein after sequentially presenting the plurality of target cover maps in the target first set of cover maps, the method further comprises:
counting click through rates CTR corresponding to the cover diagrams;
5, clustering the corresponding cover maps based on the CTR aiming at each video to obtain a first style corresponding to each video;
generating first feedback information according to the first style corresponding to each video; the first feedback information is used for guiding the cover map making and optimizing of the creator.
3. The method of claim 1, wherein the ranking the corresponding plurality of cover maps for each video based on the preference score of 0 to obtain the first set of cover maps for each video, respectively, comprises:
and for each video, based on the preference scores, performing descending processing on the corresponding cover maps to obtain a first cover map set corresponding to each video.
4. The method of claim 1, wherein the ranking the corresponding plurality of cover maps based on the preference score for each video based on 5 to obtain the first cover map set for each video, respectively, comprises:
For each video, performing descending processing on the corresponding cover images based on the preference scores to obtain a plurality of cover images corresponding to each video after descending;
screening a first preset number of front cover images from the corresponding descending cover images for each video;
and determining the front-ordered first preset number of cover diagrams as a first cover diagram set corresponding to each video respectively.
5. The method of claim 1, wherein sequentially presenting the plurality of target cover maps in the target first set of cover maps comprises:
and sequentially displaying the plurality of target cover diagrams in the target first cover diagram set according to the preset interval duration.
6. The method of claim 2, wherein the clustering the corresponding plurality of cover maps based on the CTR for the respective videos to obtain the first style type corresponding to the respective videos comprises:
for each video, performing descending processing on the corresponding cover images based on the CTR to obtain a plurality of cover images corresponding to each video after descending;
Screening a second preset number of front-ordered cover images from the corresponding descending cover images for each video;
determining the front-ordered second preset number of cover diagrams as second cover diagram sets corresponding to the videos respectively;
and clustering a plurality of cover maps in the corresponding second cover map set aiming at each video to obtain a first style type corresponding to each video.
7. The method of claim 6, wherein the method further comprises:
determining a plurality of videos of the same type;
clustering a plurality of cover maps in a second cover map set corresponding to the plurality of videos of the same type to obtain a second style type of the plurality of videos of the same type;
generating second feedback information according to a second style type of the plurality of videos of the same type; the second feedback information is used for guiding the cover map making and optimizing of the creator.
8. A video cover presentation device, the device comprising:
the cover map acquisition module is used for acquiring user preferences of a user and respectively acquiring a plurality of cover maps corresponding to a plurality of videos; wherein each cover map carries a text description;
The cover map scoring module is used for scoring each cover map according to the text description and the user preference to obtain preference scores corresponding to each cover map; each preference score is used for representing the click probability of the user on each cover map;
the cover map ordering module is used for ordering the corresponding plurality of cover maps according to the preference scores of the videos to obtain first cover map sets respectively corresponding to the videos;
the target first cover chart set acquisition module is used for acquiring a target first cover chart set corresponding to a target video when the time length of the user staying on the target video exceeds the preset stay time length;
and the target cover diagram sequence display module is used for sequentially displaying the plurality of target cover diagrams in the target first cover diagram set.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor for implementing the video cover presentation method of any one of claims 1-7 when executing a program stored on a memory.
10. A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the video cover presentation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310034481.7A CN116132760A (en) | 2023-01-10 | 2023-01-10 | Video cover display method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310034481.7A CN116132760A (en) | 2023-01-10 | 2023-01-10 | Video cover display method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116132760A true CN116132760A (en) | 2023-05-16 |
Family
ID=86306013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310034481.7A Pending CN116132760A (en) | 2023-01-10 | 2023-01-10 | Video cover display method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116132760A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020076A (en) * | 2011-09-23 | 2013-04-03 | 深圳市快播科技有限公司 | Dynamic preview method and device for player video file |
| CN106610993A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Display method and device for video preview |
| 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 |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| CN113382301A (en) * | 2021-04-30 | 2021-09-10 | 阿里巴巴新加坡控股有限公司 | Video processing method, storage medium and processor |
-
2023
- 2023-01-10 CN CN202310034481.7A patent/CN116132760A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020076A (en) * | 2011-09-23 | 2013-04-03 | 深圳市快播科技有限公司 | Dynamic preview method and device for player video file |
| CN106610993A (en) * | 2015-10-23 | 2017-05-03 | 北京国双科技有限公司 | Display method and device for video preview |
| 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 |
| CN112383830A (en) * | 2020-11-06 | 2021-02-19 | 北京小米移动软件有限公司 | Video cover determining method and device and storage medium |
| CN113382301A (en) * | 2021-04-30 | 2021-09-10 | 阿里巴巴新加坡控股有限公司 | Video processing method, storage medium and processor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6821149B2 (en) | Information processing using video for advertisement distribution | |
| US9972360B2 (en) | Computerized system and method for automatically generating high-quality digital content thumbnails from digital video | |
| CN111178970B (en) | Advertisement putting method and device, electronic equipment and computer readable storage medium | |
| CN103455524B (en) | Method and device for displaying and acquiring entry information | |
| KR20190052028A (en) | Detect objects from visual search queries | |
| CN106878405B (en) | Method and device for adjusting push items | |
| US9177341B2 (en) | Determining search relevance from user feedback | |
| CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
| CN109992187B (en) | Control method, device, equipment and storage medium | |
| CN104216885B (en) | Recommendation system and method for automatically combining static and dynamic recommendation reasons | |
| CN112579822A (en) | Video data pushing method and device, computer equipment and storage medium | |
| CN109063080B (en) | Video recommendation method and device | |
| CN109213933B (en) | Content item recommendation method, device, equipment and storage medium | |
| CN111581435B (en) | Video cover image generation method and device, electronic equipment and storage medium | |
| KR101687377B1 (en) | Method of preparing an advertisement images on image materials, preparation system using the same, and playing method on prepared image data | |
| CN116132760A (en) | Video cover display method and device, electronic equipment and storage medium | |
| US11947616B2 (en) | Systems and methods for implementing session cookies for content selection | |
| CN113077295B (en) | Advertisement graded delivery method based on user terminal, user terminal and storage medium | |
| CN111353052B (en) | Multimedia object recommendation method and device, electronic equipment and storage medium | |
| CN111552883B (en) | Content recommendation method and computer-readable storage medium | |
| CN110399527B (en) | Movie recommendation method, device and storage medium | |
| Mujtaba et al. | Client-driven Lightweight Method to Generate Artistic Media for Feature-length Sports Videos. | |
| CN113590942A (en) | Automatic short video recommendation method and system | |
| CN112445921A (en) | Abstract generation method and device | |
| CN113709529B (en) | Video synthesis method, device, electronic equipment and computer readable 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 |