CN105898583B - Image recommendation method and electronic equipment - Google Patents
Image recommendation method and electronic equipment Download PDFInfo
- Publication number
- CN105898583B CN105898583B CN201510038167.1A CN201510038167A CN105898583B CN 105898583 B CN105898583 B CN 105898583B CN 201510038167 A CN201510038167 A CN 201510038167A CN 105898583 B CN105898583 B CN 105898583B
- Authority
- CN
- China
- Prior art keywords
- video
- image data
- image
- user
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to the field of communication, and discloses an image recommendation method and electronic equipment, which are used for solving the technical problem that image recommendation cannot be timely performed on a user in the prior art, and the method is applied to the electronic equipment and comprises the following steps: obtaining a video record of a video watched by a user of the electronic device; determining first video information of a first video watched by a user from the video record; acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the first video information; and outputting recommendation information for recommending the image data. The technical effect of timely recommending the images to the user is achieved.
Description
Technical Field
The invention relates to the field of human-computer interaction, in particular to an image recommendation method and electronic equipment.
Background
Nowadays, people have entered the internet era, and a great deal of information is provided on the internet, so that users can obtain a great deal of image information through the internet.
Image information can be obtained in various ways in the prior art, two of which are described below:
first, please refer to fig. 1a, which specifically includes the following steps:
step S101: inputting keywords in a search engine for searching;
step S102: screening and searching are carried out in a search result in a manual mode;
step S103: and selecting images which are preferred by the user for downloading.
Secondly, please refer to fig. 1b, which specifically includes the following steps:
step S110: collecting data such as search records of a user;
step S120: processing the collected data to determine the preference of the user;
step S130: images related to the user's liking are recommended to the user.
However, the first method requires active searching by the user, so that the image is not timely and convenient to obtain, and forms a barrier to the use of the search engine, especially for users who are not familiar with network operation, are not skilled in typing, and cannot use the search engine. The second method needs to analyze the similarity according to the pictures recently searched or used by the user, and then recommends the related images to the user, so that the image resources to be recommended are often obtained from various large picture websites, the sources are limited, and the recommended images cannot timely fit with the continuously changing user interests.
Therefore, the technical problem that image recommendation cannot be timely performed on the user exists in the prior art.
Disclosure of Invention
The invention provides an image recommendation method and electronic equipment, and aims to solve the technical problem that image recommendation cannot be timely performed on a user in the prior art.
In a first aspect, an embodiment of the present invention provides an image recommendation method applied to an electronic device, including:
obtaining a video record of a video watched by a user of the electronic device;
determining first video information of a first video watched by the user from the video recording;
acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the first video information;
and outputting recommendation information for recommending the image data.
Optionally, the determining, from the video record, first video information of a first video watched by the user specifically includes:
and based on the playing record of the user to the video in the video record, screening out video information meeting a first preset rule from the video record as the first video information.
Optionally, the acquiring image data corresponding to the first video information specifically includes:
acquiring video data corresponding to the first video information;
and intercepting a target image frame from the video data as the image data.
Optionally, the intercepting a target image frame from the video data as the image data specifically includes:
determining a plurality of video clips corresponding to the video data;
intercepting a plurality of image frames corresponding to the plurality of video clips;
and determining the image data as a target image frame from the plurality of image frames.
Optionally, the determining the plurality of video segments corresponding to the video data specifically includes:
determining the plurality of video clips corresponding to the user operation of the user when the user watches the video corresponding to the first video information; or
Dividing the video data into the plurality of video segments.
Optionally, the determining, from the plurality of image frames, the image data as a target image frame specifically includes:
respectively determining the image variation of each image frame relative to the adjacent image frame in the plurality of image frames;
screening the front N image frames from the plurality of image frames according to the sequence of the image variation from low to high, wherein N is a positive integer;
determining the image data based on the first N image frames.
Optionally, the determining, from the plurality of image frames, the image data as a target image frame specifically includes:
acquiring the corresponding layout of each picture element in the established standard desktop wallpaper;
and respectively analyzing the matching degree of the corresponding layout of each picture element in each image frame in the image frames and the corresponding layout of each picture element in the standard desktop wallpaper, and determining the image data according to the matching degree.
Optionally, the method further includes:
preprocessing the image data;
the outputting of recommendation information for recommending the image data specifically includes:
outputting the recommendation information for recommending the image data after the preprocessing.
Optionally, the preprocessing the image data specifically includes:
and adjusting display parameters corresponding to the image data based on wallpaper display parameters of the established standard desktop wallpaper.
Optionally, the preprocessing the image data specifically includes:
and adjusting the resolution of the image data from a first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
In a second aspect, an embodiment of the present invention provides an electronic device, including:
an obtaining module, configured to obtain a video record of a video watched by a user of the electronic device;
a determining module for determining first video information of a first video watched by the user from the video recording;
an obtaining module, configured to obtain image data corresponding to the first video information, where the image data is image data captured from video data corresponding to the first video information;
and the output module is used for outputting recommendation information for recommending the image data.
Optionally, the obtaining module specifically includes:
the acquisition unit is used for acquiring video data corresponding to the first video information;
and the intercepting unit is used for intercepting a target image frame from the video data as the image data.
Optionally, the electronic device further includes:
the preprocessing module is used for preprocessing the image data;
the output module is specifically configured to:
outputting the recommendation information for recommending the image data after the preprocessing.
Optionally, the preprocessing module is specifically configured to:
and adjusting display parameters corresponding to the image data based on wallpaper display parameters of the established standard desktop wallpaper.
Optionally, the preprocessing module is specifically configured to:
and adjusting the resolution of the image data from a first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
The invention has the following beneficial effects:
in the embodiment of the present invention, an image recommendation method is provided, including: obtaining a video record of a video watched by a user of the electronic device; determining first video information of a first video watched by a user from the video record; acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the video information; and outputting recommendation information for recommending the image data. Therefore, even if the user does not search the image data, recommendation information for recommending the image data can be generated according to the first video information of the first video watched by the user, and the technical effect of timely recommending the image to the user is achieved;
and the recommended image data is the image data intercepted from the high-quality video corresponding to the first video information, so that the recommended image data is high in resolution, and the display effect of the recommended image data is guaranteed.
Drawings
FIG. 1a is a flow chart of a first prior art method of obtaining image information;
FIG. 1b is a flow chart of a first prior art method of obtaining image information;
FIG. 2 is a flowchart of an image recommendation method according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating an image data corresponding to a first video information is obtained in an image recommendation method according to an embodiment of the present invention;
fig. 4 is a flowchart of capturing partial images from video data as image data in the image recommendation method according to the embodiment of the present invention;
FIG. 5 is a flowchart illustrating an embodiment of a method for determining image data from a plurality of images according to the present invention;
fig. 6 is a block diagram of an electronic device in an embodiment of the invention.
Detailed Description
The invention provides an image recommendation method and electronic equipment, and aims to solve the technical problem that image recommendation cannot be timely performed on a user in the prior art.
In order to solve the technical problems, the general idea of the embodiment of the present application is as follows:
provided is an image recommendation method including: obtaining a video record of a video watched by a user of the electronic device; determining first video information of a first video watched by a user from the video record; acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the video information; and outputting recommendation information for recommending the image data. Therefore, even if the user does not search the image data, recommendation information for recommending the image data can be generated according to the first video information of the first video watched by the user, and the technical effect of timely recommending the image to the user is achieved;
and the recommended image data is the image data intercepted from the high-quality video corresponding to the first video information, so that the recommended image data is high in resolution, and the display effect of the recommended image data is guaranteed.
In order to better understand the technical solutions of the present invention, the following detailed descriptions of the technical solutions of the present invention are provided with the accompanying drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the examples of the present invention are the detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the examples of the present invention may be combined with each other without conflict.
In a first aspect, an embodiment of the present invention provides an image recommendation method, which is applied to an electronic device, where the electronic device includes: a notebook computer, a tablet computer, a mobile phone, etc., please refer to fig. 2, the method includes:
step S201: obtaining a video record of a video watched by a user of the electronic device;
step S202: determining first video information of a first video watched by a user from the video record;
step S203: acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the first video information;
step S204: and outputting recommendation information for recommending the image data.
In step S201, obtaining the video record of the video watched by the user can be divided into a plurality of cases, and two cases are listed below for description, and of course, in the specific implementation process, the two cases are not limited to the following two cases.
The first method is to obtain a video record of a video watched by a user of an electronic device, and specifically includes: and obtaining the video record of the video watched by the user detected by the server terminal in the preset time period.
For example, the preset time period is, for example: for 1 month, a week, and the like, the server may first obtain all video records of the video watched by the user, and then filter the video records by the playing time, so as to obtain the video records within the preset time period.
According to the scheme, the obtained video record is stored in the server within the preset time period, so that on one hand, the current requirements of the user can be reflected in real time, and the generated recommendation information is more accurate; on the other hand, the processing load of the electronic device can be reduced.
Second, obtaining a video record of a video watched by a user of an electronic device specifically includes: a full video recording of a video viewed locally by a user on an electronic device is obtained.
In step S202, all video information may be acquired from the video recording as the first video information, and as a preferred embodiment, the first video information of the first video watched by the user is determined from the video recording, specifically:
and based on the playing record of the video in the video record by the user, screening out the video information meeting a first preset rule from the video record as first video information.
For example, assume that the first video determined from analysis of the video recording is: the method comprises the steps of enabling a movie to fly by bullets, enabling a TV series to perform three kingdoms rehearsal, enabling the TV series to perform ancient Jianqi Tan, enabling a documentary to perform beautiful China and the like, and then respectively screening video information in the videos through a first preset rule, and further obtaining partial video information corresponding to the videos respectively to serve as first video information.
In the above scheme, the first video information needs to be screened from the video record corresponding to the video instead of acquiring all the video information corresponding to the video, so that the technical effect of reducing the processing load of the electronic device can be achieved.
In a specific implementation process, the first predetermined rule may be a plurality of different rules, and the obtained first video information is also different, and three of the rules are listed below for description, and of course, in the specific implementation process, the rule is not limited to the following three cases.
Firstly, determining video information corresponding to a first video with the playing time length of a user being longer than a preset time length from video records as the first video information.
For example, if the video information corresponding to the video recording includes video information of a movie class (e.g., movie "fly by bullet"), because the movie is a single video album relatively complete to the scenario, if the playing time of the movie exceeds a preset time, it can be basically determined that the user is interested in the movie. Different preset durations can be set according to the requirements of users, for example: 40%, 50% of the total duration of the movie, etc., and the preset duration may be adjusted with statistical accuracy. In addition, for the drama, the playing time length is greater than the preset time length to determine that the drama is the first video information, and the scheme is not limited to movies.
By the scheme, the technical effect of recommending the image data corresponding to the first video information with the playing time length of the user being longer than the preset time length can be achieved.
And secondly, determining video information corresponding to a first video set with the playing times of the user being greater than the preset times from the video record as the first video information.
For example, if the video information corresponding to the video record includes a series, since the series includes many episodes, the user plays many times, that is, the user watches videos of the series of the episodes, and thus, whether the corresponding video information is the first video information can be determined by whether the playing times of the user is greater than the preset times; in addition, for the video information of the movie, the user may not be able to finish watching the video information once, or the user is interested in the movie, and therefore the video information may be played for many times, so that the corresponding first video may be determined by whether the playing time is greater than the preset time, and whether the video information corresponding to the first video is the first video information. Wherein can set up different preset times according to actual demand, to film class video, the preset number of times can set up shorter, for example: 2 times, 3 times, etc.; for series videos, the preset number of times may be set to be longer, for example: 5 times, 10 times and so on, and in addition, based on series with different numbers of episodes, the preset times can also be set differently, for series with shorter number of episodes, the preset times is set shorter correspondingly, for series with longer number of episodes, the preset times is set longer correspondingly, and so on.
By the scheme, the technical effect of recommending the image data corresponding to the first video information with the playing times of the user being greater than the preset times can be achieved.
And thirdly, determining video information corresponding to a first video set with the playing set number of the user larger than the preset set number from the video record as the first video information.
For example, suppose that the video information corresponding to the video recording includes a series, and since the series includes a plurality of episodes, the corresponding first video can be determined by the number of play episodes of the user, and whether the video information corresponding to the first video is the first video information is determined, where the preset number of episodes is, for example: 5. 10, etc., embodiments of the present invention are not illustrated in detail and are not to be considered limiting.
By the scheme, the technical effect of recommending the image data corresponding to the first video information with the playing set number larger than the preset set number of the user can be achieved.
In other embodiments, the video information corresponding to the first video may be further filtered to form the first video information. Specifically, video attribute information such as "director", "director" and the like corresponding to the first video is searched according to the video record, and the video attribute information is used as the first video information. Particularly, the name information of each actor in the "starring" is used as the first video information, and then the name information is respectively searched in the first video, and the image frame containing a certain actor is used as the image data of the first video. If a user watches a television drama ' emissary ' on a certain video site and the number of episodes of the television drama watched by the user is larger than a predetermined threshold value, the ' emissary ' is used as a first video, corresponding video attribute information is obtained as first video information, and the main performances ' Miangqiao Weiwei ', ' Shishiman ', ' Linzhong ', ' Chenyingzhi ', ' and ' Xishaxiong ' are respectively used as elements in the first video information to perform image capture on image frames of the episodes of the ' emissary ', and corresponding image data is obtained. Specifically, if an image frame with a face corresponding to an actor is used as image data corresponding to the first video information, and if an image frame with a face corresponding to the actor is used as image data corresponding to the first video information, and if the image frame is used as image data corresponding to the actor "miao qiao", the image frame is used as image data corresponding to the actor "miao qiao wei" in the first video information, and the actor "miao qiao wei" and the video name "migratory actor" are used as corresponding labels of the image data.
Of course, the image data may also be directly obtained according to the attribute of the "actor" in the first video information, that is, the image data is extracted according to the facial features of the corresponding actor in the predetermined database, each image frame in the first video is directly searched according to the quantized facial features, a target image frame containing the facial features corresponding to the actor is extracted, the target image frame is further filtered according to the distribution rule of each element in the target image frame, the conditions that the actor is located at the top angle, the edge, and the like of the target image frame are removed, and the target image frame in which the area where the actor is located is the main body of the image frame is used as the image data corresponding to the actor.
In step S203, acquiring image data corresponding to the first video information, with reference to fig. 3, the method specifically includes:
step S301: acquiring video data corresponding to the first video information;
step S302: and intercepting the target image frame from the video data as image data. By the scheme, the picture resources which do not exist in the whole network can be generated, and the interest of the user is quickly and timely matched.
In step S301, the video data corresponding to the first video information may be divided into a plurality of cases, and three cases are listed below for description, and certainly, in the specific implementation process, the video data is not limited to the following three cases.
① corresponding to the first video information and viewed by the user.
For example, assume that the first video information is determined from the video recording to be: the movie "let bullet fly", and the user watches the high-definition video of "let bullet fly" through the video website a, then the high-definition video of the video website a is directly acquired as video data.
In the above scheme, the determined video data is the video data watched by the user, and the video data watched by the user is usually cached in the electronic device, so that the electronic device is not required to download the corresponding video data from the network again, and the technical effect of reducing the data transmission load is achieved.
② are the same video source as the video data corresponding to the first video information and viewed by the user, but are higher definition video data.
For example, assume that the first video information is determined from the video recording to be: let the bullet fly to the user has watched the high definition video of "let the bullet fly" through video website A, and video website A provides the video file of three kinds of definition degrees to the user, respectively: and standard definition, high definition and super definition (arranged according to the resolution from low to high), acquiring super definition video of 'let bullet fly' from a video website A as video data.
③ the video data corresponding to the first video information is specifically a high-definition video obtained by using the first video information as a keyword through full-network search.
For example, assume that the first video information is determined from the video recording to be: letting the bullet fly, and watching a high-definition video of 'letting the bullet fly' through a video website A, searching video data of 'letting the bullet fly' through the whole network, and further acquiring the video data with the highest resolution as first video data. By the scheme, the resolution ratio of the acquired image data can be ensured to be higher, and the application range of the acquired image data can be wider.
In general, the resolution of the video data corresponding to the selected first video information is not less than the resolution of the electronic device, for example, a mobile phone of 800 × 480 sees a film source of 480p and 720p, or a display of 1440 × 900 sees a film source of 1080p, or even a film source of 4K, that is, the resolution of the screen display of the electronic device is the resolution of the film source, so as to ensure that the captured image has no interpolation, and thus the effect of the obtained image data can be ensured.
In step S302, after determining the video data corresponding to the first video information, the video data may be directly decoded to obtain image data, and in order to reduce the processing load of the electronic device, as a further preferred embodiment, the server directly searches for the corresponding video data from the video site, and intercepts the target image frame from the video data as the image data, which specifically includes:
judging whether image data exist in the network or not, wherein the image data are uploaded to the network by users of other electronic equipment;
when image data does not exist in the network, a part of the image frame is cut out from the video data as image data.
For example, after watching the video corresponding to the first video information, the other electronic device may obtain corresponding image data based on the video data corresponding to the first video information and upload the corresponding image data to the server; after determining first video information corresponding to a first video, the electronic equipment searches at a server end by taking the first video information as a keyword, if corresponding image data can be searched, it is indicated that users of other electronic equipment have obtained and uploaded image data corresponding to the first video watched by the current user, and under the condition, the image data corresponding to the first video information is directly obtained from the server without intercepting the video data again; and if the corresponding image data can not be searched, the server directly searches the corresponding video data from the video website and intercepts the target image frame from the video data as the image data.
By the scheme, the electronic equipment can be ensured not to repeatedly intercept the image data corresponding to the first video information, so that the processing load of the electronic equipment can be reduced, and the speed of determining the image data can be improved under the condition that the image data exists in the network.
In step S302, a target image frame is captured from the video data as image data, with reference to fig. 4, which specifically includes:
step S401: determining a plurality of video clips corresponding to the video data;
step S402: intercepting a plurality of image frames corresponding to a plurality of video clips;
step S403: image data as a target image frame is determined from the plurality of image frames.
In step S401, a plurality of video segments corresponding to the video data may be determined in various manners, and two of them are listed below for description, and of course, in the specific implementation process, the following two cases are not limited.
①, determining the video segments corresponding to the video data, specifically including determining the video segments corresponding to the user operation of the user when the user watches the video corresponding to the first video information.
For example, when the user watches the video corresponding to the first video information, some user operations may be performed on the video, such as: pausing at a certain point in time, replaying from a first point in time to a second point in time, taking a screenshot at a certain point in time, etc., these user actions all indicate that the user is interested in the image at the corresponding point in time, so in this case, based on a plurality of videos corresponding to the user actions of the user, for example: a video segment within each 5min before and after the time point of the pause is determined as one of a plurality of video segments, a video segment between the second time point and the first time point is determined as one of a plurality of video segments, a video segment within each 2min before and after the time point of the screen shot is determined as one of a plurality of video segments, and so on.
According to the scheme, the plurality of video clips are determined through the user operation of the user, so that the determined video clips are more targeted, the number of the determined video clips does not account for too much of the whole video data, and the processing load of the electronic equipment can be reduced.
② determining a plurality of video segments corresponding to the video data includes dividing the video data into a plurality of video segments.
For example, if the first video information indicates that the corresponding video is a natural scene type movie, for example: the first video information is documentary beautiful China, and because the picture is mainly the display of natural wind and light, information labeling can be carried out by taking time as a unit according to diversity scenes and time-sharing scenes, and a plurality of video clips are formed;
if the first video information indicates that the corresponding video is a movie of a scenario class, for example: if the first video information is 'let bullet fly', the video data can be divided into a plurality of video segments by positioning and marking the overall plot, the diversity plot and the story background in the first video information and by time unit and time interval. In addition, information such as detailed plots, subtitles, character comparison, film comments and the like can be analyzed, and more suitable video segments can be screened from the plurality of video segments for further analysis.
As a further preferred embodiment, if the first video information indicates that the corresponding video is a natural scene type movie, the transition scene may be removed from each of the plurality of video segments according to the shot switching, and then a plurality of classical video segments may be obtained.
If the first video information indicates that the corresponding video is a movie of a scenario, a classical video segment can be screened from each video segment of the plurality of video segments according to information of the scenario, a starring actor and a picture scene, and then a plurality of classical video segments are obtained, for example: according to the obtained plot information, selecting a playing time interval according to the position of the target character in the plot information, and rejecting a transition scene of each video segment in the plurality of video segments; image frames can be randomly selected from the video clips to be respectively subjected to face recognition, and the non-dominant scenes of each video clip in the video clips are removed; the image frame scene may be analyzed, subject elements in the image frame may be detected, only scenery scenes in the plurality of video segments may be selected, and so on.
In addition, if the first video information indicates that the corresponding video is a movie of a scenario class, the movie can be further divided into a plurality of video segments according to the scenario, the lead actor, the dynamic subtitle information, the movie comment and the like, and taking the first video information as "let bullet fly", as an example, the first video information can be divided into the following video segments: the method comprises the following steps of eating a hot pot, riding a horse with ginger, hijacking a train, falling into water with kudzuvine, entering a city with ginger and the like on a white horse train or a kudzuvine excellent train, labeling and recording the description information, the picture scene, the starting time, the ending time, the drama, the characters and other information of each video clip, and screening out a plurality of classical clips from the plurality of video clips by labeling the plurality of video clips, for example: white horse draws train, Ge you fall into water, ginger literate team enter goose city, three great movie emperors play together etc..
If a plurality of classic video segments are screened out based on the steps, the plurality of classic video segments can be processed only when the plurality of video segments are processed subsequently, and therefore the processing efficiency can be improved.
In step S402, since each video segment in step S401 includes a start time and an end time, the video can be decoded by the start time and the end time of each video segment, so as to obtain each still video frame in the corresponding video segment, in order to ensure the viewing effect, the frame rate of the movie and drama video is usually 24 frames/second at minimum, and the duration of each episode segment is usually in units of seconds, so that a group of still video frames with a large number and high correlation can be obtained by decoding a single video segment, and these still video frames are the multiple image frames corresponding to each video segment.
In step S403, a plurality of image frames may be directly determined as image data, but there may be some image frames with not too high quality (for example, shake, blur, and the like) in the plurality of image frames, so as to improve the quality of the image data included in the recommendation information and reduce the screening work of the user, as a further preferred embodiment, in step S403, the determining of the image data from the plurality of image frames specifically includes, with reference to fig. 5:
step S501: respectively determining the image variation of each image frame relative to the adjacent image frame in the plurality of image frames;
step S502: screening the front N image frames from the plurality of image frames according to the sequence of the image variation from low to high, wherein N is a positive integer;
step S503: image data is determined based on the first N image frames.
Typically, a complete video is composed of episode segments, one after another. Each episode segment is usually dynamic, that is, the dynamic of the video is a dynamic effect formed by serially connecting one continuous static image frame with correlation and small or large change of each frame. Each image frame therein can be regarded as a stop-motion presentation of a motion, a scene, a storyline. Not every image frame is suitable for presentation as a good quality still picture as part of a complete action, scene, or episode. Even the vast majority of image frames function as components of a footage and do not have the aesthetic value of existing alone as a still picture. For example, if a person is speaking, each image frame represents changes of facial organs and emotions such as mouth shape, nose, eyes, eyebrows and the like during the speaking process, and the image frames are directly extracted, which have many problems such as mouth shape being not beautiful, blinking, eyebrow picking, unnatural emotion and the like, and often do not have aesthetic value and cannot be used as a qualified still picture, so that a plurality of image frames acquired in step S402 need to be screened.
In step S501, a certain number M (e.g., 2, 4, 5, etc.) of front and rear adjacent image frames may be continuously referred to for each image frame, and then a difference operation is performed, so as to obtain an image variation between the adjacent image frames. In this embodiment, if the change rate between adjacent image frames is too large, a pixel point with too large change during screenshot may interpolate between two frames, and if the screenshot causes blurring in some regions in the image, the screenshot is performed in a video frame sequence with less change rate than M image frames within a period of time, for example, 1s, and the display contents of the video frames are basically the same, and the pixel interpolation point is hardly intercepted during screenshot, so that the display effect of the screenshot is ensured. The number M can be adjusted differently according to different video clips, and for scenes with large relative change amplitude (such as action scenes), the value of M can be set to be relatively large; and for scenes with small relative change amplitude (e.g., landscape scenes), M to M can be set to be relatively small.
In step S503, all the first N image frames screened in step S502 may be used as image data, and in order to make the recommended image data more accurate, the determining the image data based on the first N image frames specifically includes: and eliminating images which do not meet the second preset rule from the first N image frames, and further acquiring image data.
Different second predetermined rules may be set according to actual requirements, and then the screening of the N image frames is also different, two of which are listed below for description, and certainly, in the specific implementation process, the two cases are not limited to the following two cases.
①, removing images which do not meet the second preset rule from the previous N images, and further acquiring image data, specifically comprising:
acquiring the corresponding layout of each picture element in the established standard desktop wallpaper;
and respectively analyzing the matching degree of the corresponding layout of each picture element in each image frame in the plurality of image frames and the corresponding layout of each picture element in the standard desktop wallpaper, and determining image data according to the matching degree.
For example, when recommending image data to a user, the image data may be recommended to the user as a desktop wallpaper, and the acquired image data needs to conform to an aesthetic style of the desktop wallpaper, so in this case, wallpaper display parameters of a plurality of standard desktop wallpapers need to be acquired from the server side, where the wallpaper display parameters are, for example: hue, contrast, corresponding layout of each picture element, etc., whereas in general, the corresponding layout of each picture element of a given standard desktop wallpaper is: the main elements are located at the golden section point and account for more than 30% of the area proportion of the desktop wallpaper, so that the image frames with the main elements not located at the golden section point or accounting for less than 30% of the area proportion of the image frames can be removed from the N image frames, and the image data recommended as the desktop wallpaper can be obtained.
② removing the image frames which do not meet the second predetermined rule from the previous N image frames, which specifically includes:
acquiring a plurality of facial features;
and judging whether the facial features of each image frame in the N image frames are matched with the plurality of facial features, and if so, determining that the corresponding image does not meet a second preset rule.
For example, in the case that N image frames are taken as human image frames, the image frames may include some image frames with various problems such as mouth-off beauty, blinking, eyebrow-picking, and unnatural emotion, which are not suitable for being recommended to the user as image data, so that the server may pre-store a plurality of facial features, for example: a mouth-type unattractive facial feature, a blinking feature, a brow-picking feature, an unnatural-mood feature, etc., and after obtaining N image frames, each of the N image frames is matched with the plurality of facial features, and if the matching is successful, the image frame is not aesthetically pleasing and thus does not satisfy the second predetermined condition.
As a further preferred embodiment, the method further comprises: the image data is pre-processed.
Different preprocessing methods can be adopted for the image data according to actual needs, and two of the preprocessing methods are listed below for description, but of course, in the specific implementation process, the method is not limited to the following two cases.
The first method for preprocessing image data specifically includes:
and adjusting the display effect of the image data from the first display effect to the second display effect.
For example, the dominant hue of the image data may be changed from red to gray, the contrast of the image data may be increased, the saturation of the image data may be decreased, and the like, when the display effect of the image data is adjusted, some effect adjusting filters may be built in the application program, and the display effect of the image data may be adjusted from the first display effect to the second display effect by directly adjusting the effect adjusting filters.
As a further preferred embodiment, the adjusting the display effect of the image data from the first display effect to the second display effect specifically includes:
and adjusting display parameters corresponding to the image data based on the wallpaper display parameters of the established standard desktop wallpaper.
For example, when recommending image data to a user through recommendation information, the image data may be recommended to the user as a desktop wallpaper, and the acquired image data needs to conform to an aesthetic style of a standard desktop wallpaper, so in this case, a plurality of wallpaper display parameters of a given standard desktop wallpaper need to be acquired, and then a display effect of the image data is adjusted through the wallpaper display parameters of the standard desktop wallpaper, where the wallpaper display parameters are, for example: hue, contrast, etc.
Second, preprocessing image data specifically includes:
and adjusting the resolution of the image data from the first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
For example, when recommending image data to a user through recommendation information, the image data may be recommended to the user as desktop wallpaper, and in this case, it is necessary to ensure that the resolution of the image data is the same as the screen resolution of the display unit of the electronic device, so that the resolution of the image data needs to be adjusted from the first resolution to the second resolution, and by adjusting, it is possible to ensure that image data of a size required by the user is obtained, and when using the image data as desktop wallpaper, the display effect is the best.
In the process of the embodiment, if the first resolution (for example, 2100px 1200px) is greater than the second resolution (for example, 1600px 960px), the image data can be adjusted from the first resolution to the second resolution by clipping and compressing; if the first resolution (e.g., 1200px 80px) is less than the second resolution (e.g., 1600px 960px), the size of the image data may be increased by an interpolation algorithm, thereby adjusting the image data from the first resolution to the second resolution.
The adjustment of the resolution of the image data from the first resolution to the second resolution can be divided into a plurality of cases, two of which are described below, and of course, the implementation is not limited to the following two cases.
① adjusting the resolution of the image data from the first resolution to the second resolution includes:
determining a screen resolution of a display unit of an electronic device;
the resolution of the image data is adjusted to a second resolution based on the screen resolution of the display unit.
For example, assume that the screen resolution of the display unit is: 1600px 900px, the resolution of the image data is directly adjusted to 1600px 900px, and the image data can be used as wallpaper by the electronic device.
Further, the image data may be added with the feature information after the resolution of the image data is adjusted to the second resolution, and for example, if the image data is image data corresponding to a scene of a maraging train in "let bullet fly", the feature information may be set as: and (4) flying bullets, Marrah trains, scene pictures, civilized clashes and the like, then caching the bullets, the Marrah trains, the scene pictures, the civilized clashes and the like in the server, and further downloading corresponding image data from the server through the characteristic information by other users.
In the scheme, only the image data with the second resolution is required to be generated, so that the processing time of the electronic equipment is prolonged.
② adjusting the resolution of the image data from the first resolution to the second resolution includes:
obtaining at least one screen resolution with the use frequency exceeding a preset frequency, wherein the at least one screen resolution comprises a second resolution;
at least one image corresponding to each of the at least one screen resolution is acquired separately for each image in the image data.
For example, assume that at least one of the common screen resolutions as shown in table 1 is obtained:
TABLE 1
| Resolution (px. px) | Ratio (%) |
| 1366*768 | 27.16 |
| 1440*900 | 19.37 |
| 1024*768 | 13.59 |
| 1920*1080 | 11.69 |
| 1600*900 | 9.17 |
| 1280*1024 | 4.54 |
| 1280*800 | 4.31 |
Then, for each piece of image data, one piece of image data is generated for the above 7 resolutions, and then 7 pieces of image data are obtained, where the 7 pieces of image data include image data of the second resolution (i.e. 1600px 900 px).
In this case, as a further preferred embodiment, after acquiring at least one image corresponding to each of the at least one screen resolution, respectively, the method further comprises:
adding corresponding characteristic information to each image in at least one image;
and caching the plurality of images in the server containing the characteristic information.
For example, when a plurality of images including feature information are cached in the server, images with different resolutions can be cached in different positions (e.g., different folders) of the server through different feature information, and then users of other electronic devices can download image data stored in different positions through screen resolutions of corresponding electronic devices, so as to meet the requirement that the corresponding image data is used as desktop wallpaper.
In the above solution, since the electronic device directly generates the plurality of images with different resolutions based on the image data, even if the electronic device is used by other users with different resolutions, the image data corresponding to the first video does not need to be regenerated, and after the current user of the electronic device adjusts the screen resolution, the corresponding image data does not need to be regenerated, so that the technical effect of reducing the processing load of the electronic device is achieved.
In step S204, if the image data is not processed after the image data corresponding to the first video information is obtained based on step S203, directly outputting recommendation information for recommending the image data; on the other hand, if the image data corresponding to the first video information is processed after being obtained based on step S203, the processed image data is output as recommendation information for making a recommendation.
In step S204, the output recommendation information for recommending image data may be in various forms, which are described below by way of example, and certainly, in the specific implementation process, the output recommendation information is not limited to the following cases.
First, image data is recommended to the user in the form of desktop wallpaper.
For example, if after acquiring the image data, the image data is processed, such as: the resolution of the image data is adjusted from the first resolution to the second resolution (i.e. the screen resolution of the display unit of the electronic device), and in this case, the image data is suitable for desktop wallpaper, so that the image data can be output as recommendation information of the desktop wallpaper. For example: when a user opens the wallpaper software, a thumbnail corresponding to a certain main action screenshot in a first video watched by the user is directly displayed on a page of the wallpaper software.
In a specific implementation process, if the resolution of the image data is adjusted from the first resolution to the second resolution, and a plurality of pieces of image data with different resolutions are acquired for the same piece of image data, outputting recommendation information for recommending the image data, specifically:
outputting recommendation information for recommending a second image of the at least one image, wherein the second image specifically is: an image having a resolution of a second resolution.
Specifically, even if a plurality of image data with different resolutions are acquired, only image data suitable for the display unit of the current electronic device is recommended, so that the user can be prevented from selecting wallpaper with different resolutions, and the efficiency of setting desktop wallpaper can be improved.
And secondly, directly recommending the image data corresponding to the first video to the user as recommendation information.
For example, the image data can be used as desktop wallpaper, and can be used for making electronic greeting cards, website banners and the like, so that the image data can be directly recommended to the user without prompting the user for the action of the image data, such as: after the user views the video corresponding to the first video information, a thumbnail of a screenshot corresponding to the first video is displayed through a webpage, for example: thumbnails of image data and the like may be displayed via a client, browser, search engine results page, and the like. In this case, the user may use the image data as desktop wallpaper as well as for other purposes. In addition, in this case, adjustment of the resolution of the image data may not be required after the image data is acquired.
In a second aspect, based on the same inventive concept, an embodiment of the present invention provides an electronic device, please refer to fig. 6, including:
an obtaining module 60 for obtaining a video recording of a video watched by a user of the electronic device;
a determining module 61, configured to determine, from the video record, first video information of a first video watched by the user;
an obtaining module 62, configured to obtain image data corresponding to the first video information, where the image data is image data captured from video data corresponding to the first video information;
and an output module 63, configured to output recommendation information for recommending image data.
Optionally, the determining module 61 is specifically configured to:
and based on the playing record of the video in the video record by the user, screening out the video information meeting a first preset rule from the video record as first video information.
Optionally, the obtaining module 62 specifically includes:
the acquisition unit is used for acquiring video data corresponding to the first video information;
and the intercepting unit is used for intercepting the target image frame from the video data as image data.
Optionally, the intercepting unit specifically includes:
the first determining submodule is used for determining a plurality of video clips corresponding to the video data;
the intercepting submodule is used for intercepting a plurality of image frames corresponding to a plurality of video clips;
and the second determining submodule is used for determining image data from the plurality of image frames.
Optionally, the first determining submodule is specifically configured to:
determining a plurality of video clips corresponding to user operation of a user when the user watches the video corresponding to the first video information; or
The video data is divided into a plurality of video segments.
Optionally, the second determining sub-module specifically includes:
the first determining subunit is used for respectively determining the image variation of each image frame relative to the adjacent image frame in the plurality of image frames;
the screening subunit is used for screening the front N image frames from the plurality of image frames according to the sequence of the image variation from low to high, wherein N is a positive integer;
a second determining subunit for determining the image data based on the first N image frames.
Optionally, the second determining sub-module specifically includes:
the acquisition subunit is used for acquiring the corresponding layout of each picture element in the established standard desktop wallpaper;
and the third determining subunit is used for respectively analyzing the matching degree of the corresponding layout of each picture element in each image frame in the plurality of image frames and the corresponding layout of each picture element in the standard desktop wallpaper, and determining the image data according to the matching degree.
Optionally, the electronic device further includes:
the preprocessing module is used for preprocessing the image data;
the output module 63 is specifically configured to:
and outputting recommendation information for recommending the preprocessed image data.
Optionally, the preprocessing module is specifically configured to:
and adjusting display parameters corresponding to the image data based on the wallpaper display parameters of the established standard desktop wallpaper.
Optionally, the preprocessing module is specifically configured to:
and adjusting the resolution of the image data from the first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
One or more embodiments of the invention have at least the following beneficial effects:
since in the embodiment of the present invention,
provided is an image recommendation method including: obtaining a video record of a video watched by a user of the electronic device; determining first video information of a first video watched by a user from the video record; acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the video information; and outputting recommendation information for recommending the image data. Therefore, even if the user does not search the image data, recommendation information for recommending the image data can be generated according to the first video information of the first video watched by the user, and the technical effect of timely recommending the image to the user is achieved;
and the recommended image data is the image data intercepted from the high-quality video corresponding to the first video information, so that the recommended image data is high in resolution, and the display effect of the recommended image data is guaranteed.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to an embedded controller of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the embedded controller of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.
Claims (11)
1. An image recommendation method applied to an electronic device is characterized by comprising the following steps:
obtaining a video record of a video watched by a user of the electronic device;
determining first video information of a first video watched by the user from the video recording;
acquiring image data corresponding to the first video information, wherein the image data is image data intercepted from the video data corresponding to the first video information;
outputting recommendation information for recommending the image data;
wherein the image data is acquired by:
determining a plurality of video segments corresponding to the video data, intercepting a plurality of image frames corresponding to the plurality of video segments, respectively determining the image variation of each image frame relative to the adjacent image frame in the plurality of image frames, screening the previous N image frames from the plurality of image frames according to the sequence of the image variation from low to high, wherein N is a positive integer, and determining the image data based on the previous N image frames.
2. The method according to claim 1, wherein the determining first video information of the first video watched by the user from the video recording comprises:
and based on the playing record of the user to the video in the video record, screening out video information meeting a first preset rule from the video record as the first video information.
3. The method of claim 1, wherein the determining the plurality of video segments corresponding to the video data specifically comprises:
determining the plurality of video clips corresponding to the user operation of the user when the user watches the video corresponding to the first video information; or
Dividing the video data into the plurality of video segments.
4. The method of claim 1, wherein said determining the image data based on the first N image frames comprises: removing the images which do not meet a second preset rule from the previous N images to further acquire image data, wherein the image data specifically comprises the following steps:
acquiring the corresponding layout of each picture element in the established standard desktop wallpaper;
and respectively analyzing the matching degree of the corresponding layout of each picture element in each image frame in the N image frames and the corresponding layout of each picture element in the standard desktop wallpaper, and determining the image data according to the matching degree.
5. The method of claim 1, wherein the method further comprises:
preprocessing the image data;
the outputting of recommendation information for recommending the image data specifically includes:
and outputting the preprocessed image data, and recommending the image data as the recommendation information.
6. The method according to claim 5, wherein the preprocessing the image data specifically comprises:
and adjusting display parameters corresponding to the image data based on wallpaper display parameters of the established standard desktop wallpaper.
7. The method according to claim 5, wherein the preprocessing the image data specifically comprises:
and adjusting the resolution of the image data from a first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
8. An electronic device, comprising:
an obtaining module, configured to obtain a video record of a video watched by a user of the electronic device;
a determining module for determining first video information of a first video watched by the user from the video recording;
an obtaining module, configured to obtain image data corresponding to the first video information, where the image data is image data captured from video data corresponding to the first video information;
the output module is used for outputting recommendation information for recommending the image data;
the obtaining module is specifically configured to:
determining a plurality of video segments corresponding to the video data, intercepting a plurality of image frames corresponding to the plurality of video segments, respectively determining the image variation of each image frame relative to the adjacent image frame in the plurality of image frames, screening the previous N image frames from the plurality of image frames according to the sequence of the image variation from low to high, wherein N is a positive integer, and determining the image data based on the previous N image frames.
9. The electronic device of claim 8, wherein the electronic device further comprises:
the preprocessing module is used for preprocessing the image data;
the output module is specifically configured to:
outputting the recommendation information for recommending the image data after the preprocessing.
10. The electronic device of claim 9, wherein the preprocessing module is specifically configured to:
and adjusting display parameters corresponding to the image data based on wallpaper display parameters of the established standard desktop wallpaper.
11. The electronic device of claim 9, wherein the preprocessing module is specifically configured to:
and adjusting the resolution of the image data from a first resolution to a second resolution, wherein the second resolution is the resolution of a display unit of the electronic equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510038167.1A CN105898583B (en) | 2015-01-26 | 2015-01-26 | Image recommendation method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510038167.1A CN105898583B (en) | 2015-01-26 | 2015-01-26 | Image recommendation method and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105898583A CN105898583A (en) | 2016-08-24 |
| CN105898583B true CN105898583B (en) | 2020-06-16 |
Family
ID=56999754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510038167.1A Active CN105898583B (en) | 2015-01-26 | 2015-01-26 | Image recommendation method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105898583B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107886939B (en) * | 2016-09-30 | 2021-03-30 | 北京京东尚科信息技术有限公司 | Pause-continue type text voice playing method and device at client |
| CN108021599B (en) * | 2016-10-31 | 2022-05-27 | 阿里巴巴集团控股有限公司 | Method and device for providing page version header |
| CN106454398A (en) * | 2016-11-02 | 2017-02-22 | 珠海市魅族科技有限公司 | Video processing method and terminal |
| CN108062739B (en) * | 2017-11-02 | 2021-07-02 | 广东数相智能科技有限公司 | Intelligent picture clipping method and device based on main body position |
| CN108134947A (en) * | 2017-12-25 | 2018-06-08 | 横琴国际知识产权交易中心有限公司 | A kind of video intercepting method and device |
| CN110210920B (en) * | 2018-04-26 | 2023-06-02 | 腾讯科技（深圳）有限公司 | Meal information recommending method and device |
| CN108829784A (en) * | 2018-05-31 | 2018-11-16 | 百度在线网络技术（北京）有限公司 | Panorama recommended method, device, equipment and computer-readable medium |
| CN109117813A (en) * | 2018-08-24 | 2019-01-01 | 北京新界教育科技有限公司 | Method for processing video frequency and device |
| CN111246254A (en) * | 2018-11-28 | 2020-06-05 | 北京字节跳动网络技术有限公司 | Video recommendation method and device, server, terminal equipment and storage medium |
| CN112911239B (en) * | 2021-01-28 | 2022-11-11 | 北京市商汤科技开发有限公司 | Video processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1874444A (en) * | 2005-05-31 | 2006-12-06 | 索尼株式会社 | Information processing apparatus, information processing method, and program for enabling computer to execute same method |
| CN101360204A (en) * | 2008-09-12 | 2009-02-04 | 中兴通讯股份有限公司 | Multimedia broadcasting channel historic data recording method and terminal |
| CN103813215A (en) * | 2012-11-13 | 2014-05-21 | 联想(北京)有限公司 | Information collection method and electronic device |
| CN104079999A (en) * | 2014-05-21 | 2014-10-01 | 四川长虹电器股份有限公司 | Video screenshot preview method and system used on smart television |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100563326C (en) * | 2005-10-21 | 2009-11-25 | 中央电视台 | The implementation method that the EPG highlight is recommended |
| JP4641269B2 (en) * | 2006-03-01 | 2011-03-02 | 富士通株式会社 | Display device, display program, and display method |
| JP4162015B2 (en) * | 2006-05-18 | 2008-10-08 | ソニー株式会社 | Information processing apparatus, information processing method, and program |
| JP2008312183A (en) * | 2007-05-15 | 2008-12-25 | Sony Corp | Information processing apparatus, method, and program |
| CN101833552A (en) * | 2009-03-10 | 2010-09-15 | 郝瑞林 | Method for marking and recommending streaming media |
| JP2012203773A (en) * | 2011-03-28 | 2012-10-22 | Hitachi Consumer Electronics Co Ltd | Moving image recommendation device and moving image recommendation method |
| CN102999493B (en) * | 2011-09-08 | 2018-07-03 | 北京小度互娱科技有限公司 | A kind of method and apparatus for being used to implement video resource recommendation |
| CN103020076B (en) * | 2011-09-23 | 2017-02-08 | 深圳市快播科技有限公司 | Dynamic preview method and device for player video file |
| CN103442299B (en) * | 2013-08-20 | 2017-03-15 | 乐视网信息技术（北京）股份有限公司 | A kind of display methods for playing record and electronic equipment |
| CN103442308A (en) * | 2013-08-22 | 2013-12-11 | 百度在线网络技术（北京）有限公司 | Audio and video file labeling method and device and information recommendation method and device |
| CN103916705B (en) * | 2014-03-13 | 2017-08-25 | 三星电子（中国）研发中心 | The method and apparatus of mosaic navigation is realized in electric terminal |
| CN103945241A (en) * | 2014-05-12 | 2014-07-23 | 腾讯科技（深圳）有限公司 | Streaming data statistical method, system and related device |
| CN104301760B (en) * | 2014-11-10 | 2018-11-20 | 华勤通讯技术有限公司 | TV programme method for pushing |
-
2015
- 2015-01-26 CN CN201510038167.1A patent/CN105898583B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1874444A (en) * | 2005-05-31 | 2006-12-06 | 索尼株式会社 | Information processing apparatus, information processing method, and program for enabling computer to execute same method |
| CN101360204A (en) * | 2008-09-12 | 2009-02-04 | 中兴通讯股份有限公司 | Multimedia broadcasting channel historic data recording method and terminal |
| CN103813215A (en) * | 2012-11-13 | 2014-05-21 | 联想(北京)有限公司 | Information collection method and electronic device |
| CN104079999A (en) * | 2014-05-21 | 2014-10-01 | 四川长虹电器股份有限公司 | Video screenshot preview method and system used on smart television |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105898583A (en) | 2016-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105898583B (en) | Image recommendation method and electronic equipment | |
| US10979761B2 (en) | Intelligent video interaction method | |
| US10896478B2 (en) | Image grid with selectively prominent images | |
| US11321385B2 (en) | Visualization of image themes based on image content | |
| US11482192B2 (en) | Automated object selection and placement for augmented reality | |
| US10275655B2 (en) | Intelligent video thumbnail selection and generation | |
| US9860593B2 (en) | Devices, systems, methods, and media for detecting, indexing, and comparing video signals from a video display in a background scene using a camera-enabled device | |
| KR102246305B1 (en) | Augmented media service providing method, apparatus thereof, and system thereof | |
| US20130301918A1 (en) | System, platform, application and method for automated video foreground and/or background replacement | |
| US20140223474A1 (en) | Interactive media systems | |
| US11990158B2 (en) | Computing system with DVE template selection and video content item generation feature | |
| CN103024607A (en) | Method and apparatus for displaying summary video | |
| CN105814905B (en) | Method and system for synchronizing use information between the device and server | |
| JP2017511627A (en) | Raw scene recognition that allows scene-dependent image modification before image recording or display | |
| KR101927965B1 (en) | System and method for producing video including advertisement pictures | |
| CN112188116B (en) | Video synthesis method, client and system based on object | |
| US20200366973A1 (en) | Automatic Video Preview Creation System | |
| CN109905766A (en) | A kind of dynamic video poster generation method, system, device and storage medium | |
| CN108833976B (en) | Method and device for evaluating picture quality after dynamic cut-stream of panoramic video | |
| CN118368490A (en) | Method and device for displaying, electronic equipment and storage medium | |
| CN113470123A (en) | Video toning method and device, storage medium and shooting equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |