WO2021031917A1 - 视频处理方法、装置、电子设备及可读介质 - Google Patents

视频处理方法、装置、电子设备及可读介质 Download PDF

Info

Publication number
WO2021031917A1
WO2021031917A1 PCT/CN2020/108326 CN2020108326W WO2021031917A1 WO 2021031917 A1 WO2021031917 A1 WO 2021031917A1 CN 2020108326 W CN2020108326 W CN 2020108326W WO 2021031917 A1 WO2021031917 A1 WO 2021031917A1
Authority
WO
WIPO (PCT)
Prior art keywords
scoring
video
client user
data
video data
Prior art date
Application number
PCT/CN2020/108326
Other languages
English (en)
French (fr)
Inventor
姜子阳
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2021031917A1 publication Critical patent/WO2021031917A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/475End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4756End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie

Definitions

  • the embodiments of the present application relate to the field of Internet technology, for example, to a video processing method, device, electronic device, and readable medium.
  • video playback or video live broadcast applications usually support users to publish their own video data to the service platform of the application for other users to watch.
  • the service platform of the application directly sends the video stream of the video data to each client user for other client users to watch.
  • Users who publish video data will continuously adjust their published video content based on their own experience to improve the quality of the published video.
  • the video quality parameters posted to the service platform are not uniform, which seriously affects the overall quality of the video resources of the service platform.
  • the embodiments of the present application provide a video processing method, device, electronic equipment, and readable medium to realize automatic scoring of videos, and assist users in optimizing video quality based on the scoring results, thereby ensuring the overall quality of the video resources of the service platform.
  • an embodiment of the present application provides a video processing method, which includes:
  • scoring parameters score the video data released by the client user to obtain the scoring result of the video data;
  • the scoring parameters include at least one of author historical data, fan portraits, content distribution within the site, and video clarity;
  • the scoring result is sent to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • an embodiment of the present application also provides a video processing device, which includes:
  • the scoring module is set to score the video data released by the client user according to the scoring parameters to obtain the scoring result of the video data; the scoring parameters include: author historical data, fan portraits, content distribution within the site, and video clarity At least one of
  • the sending module is configured to send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • an electronic device which includes:
  • Memory used to store programs
  • the processor realizes the video processing method according to any embodiment of the present application.
  • an embodiment of the present application provides a readable medium with a computer program stored on the readable medium, and when the computer program is executed by a processor, the video processing method as described in any embodiment of the present application is implemented.
  • FIG. 1 is a flowchart of a video processing method provided by an embodiment of the application
  • 2A is a flowchart of a method for performing video processing based on author historical data provided by an embodiment of the application
  • 2B is a schematic diagram of an interface corresponding to the author's historical data provided in an embodiment of the application
  • 2C is a flowchart of a method for performing video processing based on fan portraits according to an embodiment of the application
  • FIG. 2D is a flowchart of a method for performing video processing based on content distribution within a site according to an embodiment of the application
  • FIG. 3 is a flowchart of another video processing method provided by an embodiment of the application.
  • FIG. 4 is a schematic structural diagram of a video processing device provided by an embodiment of this application.
  • FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the application.
  • Figure 1 is a flow chart of a video processing method provided by an embodiment of this application. This embodiment can be applied to a situation in which a video posted by a user is scored and the score result is fed back to the user.
  • the method can be implemented by a video processing device or an electronic device.
  • the device may be implemented by a device, and the apparatus may be implemented by software and/or hardware, and the apparatus may be configured in an electronic device.
  • the electronic device may be a device corresponding to the back-end service platform of the application program, or a mobile terminal device with an application program client installed.
  • the video processing method of the embodiment of the present application can be used to process the shooting video (such as short video or small video, etc.) uploaded by the client user, and can also be suitable for processing each live video of the host client .
  • the method in this embodiment may include the following steps:
  • S101 According to the scoring parameter, score the video data released by the client user to obtain a scoring result of the video data.
  • the scoring parameter is the parameter by which the video data is scored, which can include at least one of author historical data, fan portraits, site content distribution, and video clarity; among them, author historical data can include client user history
  • Data of various aspects involved in each published video may include: specific content, publishing time, number of times of playback, number of reposts, number of favorites, video content scores, comment data, etc. of each video that have been published in history.
  • the fan portrait may be a user portrait of a fan owned by the client user, which may include the age, gender, and preferred video theme type of the fan, and so on.
  • the content distribution in the site can refer to the total video resources owned by the service platform, and the distribution of each topic type video in the total video resources. For example, it can be the number of each topic type video or the total amount of each topic type video Proportion in video resources, etc.
  • the video clarity may refer to the clarity of the video playback effect.
  • the operation of scoring the video data released by the client user received within the preset period may be triggered every preset period (for example, 1 hour).
  • the execution of the operation of scoring the video data published by the current client user may also be triggered.
  • a corresponding scoring system can be set for each scoring parameter, and based on the scoring system corresponding to each scoring parameter, the video released by the client user Data is scored.
  • the feedback data of the subject type in the author historical data of the client user (such as video playback times, favorites) At least one of the number of times, the number of reposts, the video content score, and the comment data), and the topic type to which the video data belongs is scored according to the feedback data.
  • the percentage of fans of the theme type in the client user’s fan portrait can be determined according to the theme type to which the video data posted by the client user belongs; The topic type to which the video data belongs is scored; among them, the proportion of fans is directly proportional to the score of the video data.
  • the proportion of videos of the topic type in the site can be determined according to the topic type to which the video data posted by the client user belongs and the content distribution within the site; according to the proportion of the video, the proportion of the video data is determined The subject type of the scoring; among them, the proportion of video is inversely proportional to the scoring result.
  • the definition of the video data released by the client user can be calculated according to the relevant algorithm, and the overall effect of the video data currently released by the client user can be scored according to the calculation result. Among them, the level of clarity is related to The scoring result is directly proportional. It should be noted that the process of how to score the video data published by the client user according to the above-mentioned scoring system of various scoring parameters will be described in detail in subsequent embodiments.
  • this step may use the scoring result determined by the scoring system of the scoring parameter as the The scoring result of the video data released by the client user. If the scoring parameters are at least two of the author’s historical data, fan portraits, content distribution within the site, and video clarity, the scoring results of the video data can be obtained through the following sub-steps:
  • S1011 Perform subject type scoring on the video data posted by the client user according to at least one of the author's historical data, fan portraits, and site content distribution in the scoring parameters, to obtain a first scoring result.
  • this sub-step determines the corresponding sub-score under each scoring parameter according to the scoring system of the scoring parameter by using at least one scoring parameter from the author's historical data, fan portrait, and content distribution in the site (it should be noted that , The execution method of this operation will be described in detail in subsequent embodiments).
  • the set of sub-scores may be directly used as the first scoring result.
  • the comprehensive processing may be to directly perform average or sum operation processing on each sub-score, or to set a weight value for each scoring parameter, and perform weighted sum or weighted average processing on the sub-score corresponding to each scoring parameter .
  • S1012 Perform an overall effect score on the video data released by the client user according to the video clarity in the score parameter, to obtain a second score result.
  • this sub-step it is possible to determine whether the resolution of the video data published by the client user meets the definition requirements, whether there are fuzzy pixels in the video, and according to the scoring system of the video definition and the definition calculation algorithm. Whether there is at least one of the ghost area, etc., and then score the overall effect of the video data currently posted by the client user according to the judgment result. For example, if the judgment result is that the resolution meets the requirement of sharpness, there is no blurred pixel or at least one of the ghost area, the overall effect score of the corresponding video data (that is, the second score result) will also increase accordingly.
  • S1013 Obtain a final scoring result of the video data according to the first scoring result and the second scoring result.
  • the first scoring result and the second scoring result may be averaged or summed to obtain the video data
  • the scoring result of is used as the final scoring result of the video data; in this step, different weight values can be set for the first scoring result and the second scoring result, and the first scoring result and the second scoring result can be weighted and summed or weighted
  • the mean operation is performed to obtain the final scoring result of the video data; in this step, the set of the first scoring result and the second scoring result can also be used as the final scoring result.
  • S102 Send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the electronic device may directly use the obtained scoring result Sent to the client user.
  • the scoring result may be sent to the application client installed on the terminal to which the client user belongs, where the scoring result may be sent to the client user in the form of a notification message, a video release receipt message, or a pop-up window.
  • the client user can use the scoring result to understand the scoring result of the video data he released this time, that is, whether the video data he released is high-quality video data, and then optimize the subsequent release video according to the scoring result. Improve the quality of subsequent videos to attract more fans.
  • the definition of the video is relatively high, but the scoring result is still low, it means that the client user’s fans are not interested in the landscape video.
  • a client user publishes a video, he can adjust the topic type of the published video to reduce or avoid sending scenery-type videos.
  • the operations of the embodiments of the present application can also be applied to the following scenarios: after the electronic device detects that the client user triggers the video data publishing event (such as clicking the video upload button), it does not perform the video data publishing operation first.
  • S101 scores the video data published by the client user according to the scoring parameters, and S102 sends the score result back to the client user to prompt the user whether to continue publishing the video data. If a user trigger is received After confirming the release instruction, perform the release operation of the video data. For example, after a client user uploads a piece of video data through the video publishing interface of the application, the electronic device first scores the video data, and then displays a prompt box on the current video publishing interface.
  • the prompt box displays the video data
  • the electronic device executes the video after detecting the user-triggered confirmation publishing instruction Data publishing operation. If the user thinks that the score is low and needs to be adjusted, click the unpublish button. After the electronic device detects the cancel release instruction triggered by the user, it may not perform the release operation on the video data, and may wait for the user to modify the video data before uploading the video data, and then re-execute the scoring and scoring of the uploaded video data in the embodiment of the present application. Send scoring result operation.
  • the advantage of this setting is that when the user publishes the video, by scoring the video data, it assists the client user to optimize the video released this time according to the scoring result, thereby ensuring that every video released by the user is a high-quality video.
  • the embodiment of the application provides a video processing method, which automatically scores the video data published by the client user according to at least one of the author's historical data, fan portraits, site content distribution, and video clarity, and the score results Sent to the client user.
  • the solution of the embodiment of the present application can realize real-time scoring of the video data released by the client, and feedback the scoring results to the client user, so as to assist the client user in optimizing the subsequent release of the video based on the score of the current release of the video, and improve the subsequent release
  • the quality of the video not only attracts more fans, but also improves the quality of video resources on the service platform as a whole.
  • the embodiment of the present application may further include: obtaining the scoring parameter.
  • the method of obtaining the author historical data in the scoring parameter can be that the server platform has pre-recorded the author historical data of each client user, and the electronic device can directly interact with the service platform to obtain; the method of obtaining the author historical data in the scoring parameter is also It can be that the electronic device recognizes all the data involved in the historical video data that the user has released, such as obtaining all the text data involved in the historical video data through text recognition, and obtain all the image data involved in the historical video data through image recognition .
  • the acquired text data and image data can be used as author historical data.
  • the way to obtain the fan portrait in the scoring parameter can be: the server platform has pre-drawn and recorded the fan portrait of each client user, and the electronic device can directly interact with the service platform to obtain it; the fan portrait in the scoring parameter can also be obtained in the way The electronic device obtains the fan data of the client user; inputs the fan data into the neural network model to obtain the fan portrait of the fan data.
  • a neural network model for drawing user portraits can be pre-trained, and then all fan data related to the client user's fans (such as the fan's username, gender, age, location, and all information on the application) can be obtained.
  • Operational behavior data For each fan, input the fan data of the fan into the trained neural network model, and the neural network model will draw the user portrait of the fan (ie fan portrait) based on the input fan data.
  • the method of obtaining the content distribution in the site can be that the server platform has pre-stated the distribution of the video content in the site, and the electronic device can directly interact with the service platform to obtain; the method of obtaining the content distribution in the site can also be when the electronic device needs to use the content distribution in the site , Real-time statistics of the video resources owned by the service platform station.
  • the relevant algorithm for video definition judgment can be stored locally in the electronic device. When the definition of video data needs to be judged, the relevant algorithm for local recording can be directly called.
  • Figure 2A is a flowchart of a method for performing video processing based on author historical data provided by an embodiment of this application
  • Figure 2B is a schematic diagram of an interface corresponding to author historical data provided in an embodiment of this application
  • Figure 2C is a fan portrait based on an embodiment of this application
  • FIG. 2D is a flowchart of a method for performing video processing based on content distribution in a station provided by an embodiment of the application. This embodiment is modified on the basis of the various optional solutions provided in the foregoing embodiment, and gives a detailed introduction on how to score the video data published by the client user based on the author's historical data, fan portraits, and the distribution of content in the site.
  • the method of this embodiment may include the following steps:
  • S201 Determine feedback data of the topic type in the author history data of the client user according to the topic type to which the video data posted by the client user belongs.
  • the subject type of the video data can be that the video data is classified into different types according to the subject matter of the content, for example, it can include: scenery, food, singing and dancing, sports, etc.
  • the feedback data may be data information related to fan feedback in the author's historical data, which may include at least one of the number of times of video playback, the number of favorites, the number of reposts, the score of video content, and the comment data.
  • a pre-trained subject category recognition model can be used to subject the video data.
  • Recognition can also be pre-built a database that records the relationship between each topic type and its corresponding candidate keywords, extracts keywords from the description information or content of the video data released by the client user, and combines the extracted keywords with The candidate keywords recorded in the database are matched, and the topic type corresponding to the matched candidate keywords is used as the topic type to which the video data posted by the client user belongs; in this step, a field in the video data may also record the video The topic type of the data, the topic type to which the pair belongs can be directly extracted from the corresponding field of the video data.
  • this step needs to determine the topic type to which the video data published by the client user belongs.
  • the feedback data of the topic type is determined from the author history data of the client user.
  • the determination method can be: the service platform has recorded the feedback data of each topic type in the author history data of each client user, and directly interacts with the service platform to obtain the feedback data of the required topic type; the feedback data of the topic type can also be through the following sub Steps to determine:
  • the method described above can be used similar to the method of determining the subject type to which the video data currently posted by the client user belongs. From the author historical data of the client user, the author historical data belonging to the same topic type as the video data to be scored (that is, the video data published by the client user) is filtered out as the target author historical data.
  • the feedback icon is an icon related to the feedback operation of the fan after watching the video, and it may include at least one of a forwarding icon, a play icon, a favorite icon, and a rating icon.
  • this sub-step may use image recognition technology to identify feedback icons, such as forwarding icons, play icons, favorite icons, and rating icons, from the historical data of the target author, and use the preset range around the feedback icon as a feedback icon area. For example, as shown in FIG. 2B, if a scoring icon is identified from the target author's historical data, a preset size range around the scoring icon, that is, the area where the box 20 is located, is used as a feedback icon area.
  • the multiple feedback icons may be taken as a whole, and the preset range around it may be used as a feedback icon area.
  • the preset range around it may be used as a feedback icon area.
  • the distance between the recognized play icon, forward icon, and favorite icon is less than the distance threshold of 1 cm, then these three icons can be used as one shape, and the size range around them can be preset. That is, the area where the box 21 is located is used as a feedback icon area.
  • text recognition technology is used for the feedback icon area to recognize numbers and count words (such as thousands, trillions, etc.) around the feedback icon as the feedback icon in the historical data of the target author
  • the numerical information represents the number of times the feedback icon is operated, and belongs to part of the feedback data of the topic type in the author's historical data. For example, as shown in FIG. 2B, text recognition is performed on the feedback icon area 20, and the recognized 7.2 is used as the score data in the feedback data.
  • the feedback data of the topic type in the author’s historical data also includes comment data.
  • the determination method may be to first locate the comment page from the target author’s historical data, and then perform the content of the page. Line text recognition, using the recognized text as comment data in the feedback data.
  • the feedback data is the numerical information corresponding to the feedback icon, that is, the number of times the video is played and the number of reposts corresponding to the topic type determined in S201 in the author's historical data
  • the number of favorites the higher the value corresponding to the numerical information, the more popular the video of the topic type published by the client user is, and the higher the score for the topic type to which the video data belongs.
  • the feedback data is comment data, it can be a semantic analysis of the comment data, and the proportion of the positive data in the total comment data in the statistics of the comment data. The higher the proportion, the more popular the video of this topic type published by the client user If the fans like it, the higher the score for the topic type to which the video data belongs.
  • S203 Send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the method of this embodiment may include the following steps:
  • S204 Determine the proportion of fans of the theme type in the client user's fan portrait according to the theme type to which the video data posted by the client user belongs.
  • a method similar to S201 can be used to first determine the topic type to which the video data posted by the client user belongs, and then analyze the topic type that each fan likes based on the fan portrait of the client user. Finally, determine the percentage of fans who like the topic type to which the video data posted by the client user belongs to the total number of fans, and obtain the percentage of fans of the topic type in the fan portrait of the client user.
  • the service platform may also count and record the proportion of fans corresponding to each topic type in the fan portraits of each client user. After determining the topic type to which the video data posted by the client user belongs, The electronic device can directly interact with the service platform to obtain the proportion of fans of the topic type in the fan portrait of the client user.
  • the video may be evaluated according to the association relationship between the preset proportion of fans and the video data score of the corresponding topic type.
  • S206 Send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the score when scoring the video data published by the client user based on the fan portrait, the score may also be based on the fan gender or age in the fan portrait. If the topic type of the video data matches the fan gender or age For the preferred type, the score for the video data is high, otherwise the score is low. For example, if the video data released by the client user is extreme sports video data, if the client user’s fan age group is between 20-30 years old, the score of the video data is high. If the client user’s fan age is If the segment is over 50 years old, the score of the video data is low.
  • the method of this embodiment may include the following steps:
  • S207 Determine the proportion of videos of the topic type in the site according to the topic type to which the video data posted by the client user belongs and the content distribution in the site.
  • a method similar to S201 can be used to first determine the topic type to which the video data posted by the client user belongs, and then perform classification statistics on all the video data owned by the service platform station by topic type to determine the site The percentage of the number of video data of each topic type in the total number of videos, and the percentage of videos of the topic type to which the video data posted by the client user in the site belongs.
  • the service platform may also count and record the proportion of videos of each topic type corresponding to the video data owned by the station.
  • the electronic device can directly communicate with The service platform interacts to obtain the proportion of videos of that topic type in the site.
  • S208 Score the topic type to which the video data belongs according to the proportion of the video.
  • the video may be evaluated according to the association relationship between the preset video proportion and the video data score of the corresponding topic type.
  • S209 Send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the video data published by the client user may be scored through the above-mentioned scoring parameter.
  • the embodiment of the application provides a method for scoring the video data published by the client user based on three different scoring parameters, namely the author's historical data, fan portraits, and the distribution of content in the site, and then sending the scoring result to the client user.
  • a kind of scoring parameter is set with different video scoring methods.
  • FIG. 3 is a flowchart of another video processing method provided by an embodiment of the application. This embodiment is modified on the basis of the various optional solutions provided in the foregoing embodiment, and shows that the scoring result is sent to the client user Detailed introduction.
  • the method in this embodiment may include the following steps:
  • S301 According to the scoring parameter, score the video data released by the client user to obtain a scoring result of the video data.
  • the scoring parameters include at least one of author's historical data, fan portraits, content distribution within the site, and video clarity.
  • the high-quality standard can be to evaluate whether the score of a video data meets the evaluation standard of high-quality video, which can be a high-quality score threshold (such as 85 points); the high-quality standard can also be determined by various scoring parameters (ie, author history). At least one of data, fan portraits, content distribution in the site, and video clarity) a score threshold set composed of multiple score thresholds corresponding to it; the high quality standard can also be a comprehensive threshold set composed of the above high quality score threshold and score threshold set. .
  • a high-quality score threshold such as 85 points
  • the high-quality standard can also be determined by various scoring parameters (ie, author history). At least one of data, fan portraits, content distribution in the site, and video clarity) a score threshold set composed of multiple score thresholds corresponding to it; the high quality standard can also be a comprehensive threshold set composed of the above high quality score threshold and score threshold set.
  • the scoring result of the video data obtained in S301 can be the total score corresponding to each scoring parameter; it can also be a collection of sub-scores corresponding to each scoring parameter; it can also be the sub-scoring and the total score corresponding to each scoring parameter. set.
  • the corresponding high-quality standard form mentioned above can be selected for comparison.
  • the high quality standard is also a high quality score threshold.
  • the high-quality standard is also a scoring threshold set composed of multiple scoring thresholds corresponding to each scoring parameter. If each sub-score in the score set obtained in S301 is greater than or equal to the corresponding score threshold in the score threshold set, it indicates that the score result meets the high quality standard, otherwise the score result does not meet the high quality standard.
  • the high quality standard is a comprehensive threshold set consisting of a high-quality score threshold and a scoring threshold set.
  • the comparison method It can be similar to the second embodiment described above, and will not be repeated here.
  • the video data can be determined according to the reason why the scoring result does not meet the high-quality standard Direction for improvement. Since in this embodiment S301 according to the scoring parameters, when scoring the video data released by the client user, the score is based on two aspects: topic type and/or clarity. Therefore, if the scoring result does not meet the high quality standard, the reason should be the video The topic type of the data is not suitable and/or the definition is not high, so the direction of the corresponding data to be improved is to adjust the topic type of the published video and/or improve the definition of the video.
  • the direction to be improved can also be narrowed down more accurately.
  • the score corresponding to the video definition in the scoring parameter does not meet the high quality standard, it means that the reason for the failure to meet the high quality standard is that the definition of the video is not high, and the corresponding improvement direction is to improve the clarity of the video.
  • the direction is to adjust the topic type of the posted video.
  • the scoring result obtained in S301 meets the high-quality standard, the scoring result and the judgment result of reaching the high-quality standard may be directly sent to the client user.
  • the association relationship between the improvement direction and the improvement suggestion may be established in advance.
  • the improvement suggestion corresponding to the current direction to be improved can be determined directly by searching for the association relationship between the improvement direction and the improvement suggestion. For example, in order to improve the definition of the video, you can pre-associate some suggestions to improve the video definition, such as not shaking your hands when shooting a video, adjusting the focus position, and increasing the resolution of the shooting. It can also be based on the actual situation in the current scene to determine improvement suggestions.
  • the client user’s fan preferences can be combined with the fan’s favorite topic type as Suggested improvement topic types; in one embodiment, it is also possible to combine the video data held in the service platform station under the current scene, and use the scarce video topic types in the station as the suggested topic types for improvement.
  • S304 Send the scoring result, the direction to be improved and the improvement suggestion to the client user, so that the client user optimizes the quality of the published video according to the scoring result, the direction to be improved and the improvement suggestion.
  • This embodiment of the application provides a video processing method that automatically scores video data published by client users through scoring parameters. If the scoring result does not meet high-quality standards, determine the direction to be improved and suggestions for improvement of the video data, and score The results, directions for improvement and suggestions for improvement are sent to the client user.
  • the solution of the embodiment of the present application can feed back the scoring result, direction to be improved, and improvement suggestions to the client user when the quality of the video data is not high, so as to better assist the client to optimize its subsequent video quality. Even if the client user is an inexperienced new user, he can quickly improve the quality of the published video based on the received scoring results, improvement directions and improvement suggestions, attract more fans, and improve the quality of video resources on the service platform.
  • FIG. 4 is a schematic structural diagram of a video processing device provided by an embodiment of the application.
  • the embodiment of the application may be applicable to a situation where a video posted by a user is scored and the score result is fed back to the user.
  • the device can be implemented by software and/or hardware, and integrated in the electronic device that executes the method. As shown in Fig. 4, the device can include:
  • the scoring module 401 is set to score the video data released by the client user according to the scoring parameters to obtain the scoring result of the video data;
  • the scoring parameters include: author historical data, fan portraits, content distribution within the site, and video clarity At least one of the degrees;
  • the sending module 402 is configured to send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the embodiment of the application provides a video processing device, which automatically scores the video data published by the client user according to at least one of the author's historical data, fan portraits, site content distribution, and video clarity, and the score results Sent to the client user.
  • the solution of the embodiment of the present application can realize real-time scoring of the video data released by the client, and feedback the scoring results to the client user, so as to assist the client user in optimizing the subsequent release of the video based on the score of the current release of the video, and improve the subsequent release
  • the quality of the video not only attracts more fans, but also improves the quality of video resources on the service platform as a whole.
  • the scoring module 401 may be configured as:
  • Score the overall effect of the video data released by the client user according to the video clarity in the scoring parameter, and obtain a second scoring result
  • the scoring module 401 when the scoring module 401 scores the video data published by the client user according to the author's historical data in the scoring parameter, it can be set to:
  • the feedback data of the topic type in the author history data of the client user is determined; the feedback data includes: the number of times the video is played, the number of favorites, the number of forwarding, and the video content At least one of rating and review data;
  • the topic type to which the video data belongs is scored.
  • the scoring module 401 when the scoring module 401 executes to determine the feedback data of the topic type in the author history data of the client user, it can be set to:
  • Identifying a feedback icon area in the historical data of the target author where the feedback icon area is a preset range around the feedback icon, and the feedback icon includes at least one of a forward icon, a play icon, a favorite icon, and a rating icon;
  • the scoring module 401 when the scoring module 401 scores the video data posted by the client user according to the fan portrait in the scoring parameter, it can be set to:
  • the proportion of fans the topic type to which the video data belongs is scored; where the proportion of fans is directly proportional to the score of the video data.
  • the scoring module 401 scores the video data published by the client user according to the distribution of the content in the site in the scoring parameter, which can be set as:
  • the topic type to which the video data posted by the client user belongs and the content distribution within the site determine the proportion of videos of the topic type within the site
  • the proportion of the video the topic type to which the video data belongs is scored; wherein the proportion of the video is inversely proportional to the level of the scoring result.
  • the sending module 402 may be configured to:
  • the scoring result, the direction to be improved, and the improvement suggestion are sent to the client user.
  • the device further includes: a fan portrait determination module, which can be configured as:
  • the video processing device provided in the embodiments of this application belongs to the same inventive concept as the video processing methods provided in the above embodiments.
  • the above embodiments have the same beneficial effects.
  • FIG. 5 is a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present application.
  • the electronic device in the embodiment of the present application may be a device corresponding to the back-end service platform of the application program, or may be a mobile terminal device with an application program client installed.
  • the electronic device may include mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle terminals (such as car navigation Terminal) and other mobile terminals and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device 500 shown in FIG. 5 is only an example.
  • the electronic device 500 may include a processing device (such as a central processing unit, a graphics processor, etc.) 501, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 502 or from a storage device 508.
  • the program in the memory (RAM) 503 executes various appropriate actions and processing.
  • the RAM 503 also stores various programs and data required for the operation of the electronic device 500.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to the bus 504.
  • the following devices can be connected to the I/O interface 505: including input devices 506 such as touch screen, touch panel, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 507 such as a device; a storage device 508 such as a magnetic tape and a hard disk; and a communication device 509.
  • the communication device 509 may allow the electronic device 500 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 5 shows an electronic device 500 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • the process described above with reference to the flowchart can be implemented as a computer software program.
  • the embodiments of the present application include a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program includes program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502.
  • the processing device 501 the above-mentioned functions defined in the method in the embodiment of the present application are executed.
  • the above-mentioned computer-readable medium in the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the above.
  • Examples of computer-readable storage media may include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, which carries computer-readable program code. This propagated data signal can take many forms, including electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, which may include: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the electronic device can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with any form or medium of digital data (
  • communication networks are interconnected.
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • LAN local area networks
  • WAN wide area networks
  • the Internet e.g., the Internet
  • end-to-end networks e.g., ad hoc end-to-end networks
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs.
  • the internal process of the electronic device is executed: according to the scoring parameters, the video data released by the client user is scored, Obtain the scoring result of the video data; the scoring parameter includes: at least one of author historical data, fan portraits, content distribution in the site, and video clarity; and send the scoring result to the client user so that the customer The end user optimizes the quality of the released video according to the scoring result.
  • the computer program code used to perform the operations of the present application can be written in one or more programming languages or a combination thereof.
  • the aforementioned programming languages can include object-oriented programming languages-such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present application can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
  • machine-readable storage media may include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) Or flash memory), optical fiber, compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory flash memory
  • optical fiber compact disk read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • the method includes:
  • scoring parameters score the video data released by the client user to obtain the scoring result of the video data;
  • the scoring parameters include at least one of author historical data, fan portraits, content distribution within the site, and video clarity;
  • the scoring result is sent to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • scoring the video data published by the client user according to the scoring parameter includes:
  • Score the overall effect of the video data released by the client user according to the video clarity in the scoring parameter, and obtain a second scoring result
  • scoring the video data published by the client user according to the author's historical data in the scoring parameter includes:
  • the feedback data of the topic type in the author history data of the client user is determined; the feedback data includes: the number of times the video is played, the number of favorites, the number of forwarding, and the video content At least one of rating and review data;
  • the topic type to which the video data belongs is scored.
  • determining the feedback data of the topic type in the author history data of the client user includes:
  • Identifying a feedback icon area in the historical data of the target author where the feedback icon area is a preset range around the feedback icon, and the feedback icon includes at least one of a forward icon, a play icon, a favorite icon, and a rating icon;
  • scoring the video data published by the client user according to the fan portrait in the scoring parameter includes:
  • the proportion of fans the topic type to which the video data belongs is scored; where the proportion of fans is directly proportional to the score of the video data.
  • scoring the video data published by the client user according to the distribution of the site content in the scoring parameter includes:
  • the topic type to which the video data posted by the client user belongs and the content distribution within the site determine the proportion of videos of the topic type within the site
  • the proportion of the video the topic type to which the video data belongs is scored; wherein the proportion of the video is inversely proportional to the level of the scoring result.
  • sending the scoring result to the client user includes:
  • the scoring result, the direction to be improved, and the improvement suggestion are sent to the client user.
  • the method before scoring the video data published by the client user according to the scoring parameter, the method further includes:
  • a video processing device which includes:
  • the scoring module is set to score the video data released by the client user according to the scoring parameters to obtain the scoring result of the video data; the scoring parameters include: author historical data, fan portraits, content distribution within the site, and video clarity At least one of
  • the sending module is configured to send the scoring result to the client user, so that the client user optimizes the quality of the published video according to the scoring result.
  • the scoring module in the above-mentioned device may be configured as:
  • Score the overall effect of the video data released by the client user according to the video clarity in the scoring parameter, and obtain a second scoring result
  • the scoring module in the aforementioned device scores the video data published by the client user according to the author's historical data in the scoring parameter, it can be set to:
  • the feedback data of the topic type in the author history data of the client user is determined; the feedback data includes: the number of times the video is played, the number of favorites, the number of forwarding, and the video content At least one of rating and review data;
  • the topic type to which the video data belongs is scored.
  • the scoring module in the above device executes the feedback data for determining the topic type in the author history data of the client user, it can be set to:
  • Identifying a feedback icon area in the historical data of the target author where the feedback icon area is a preset range around the feedback icon, and the feedback icon includes at least one of a forward icon, a play icon, a favorite icon, and a rating icon;
  • the scoring module in the above-mentioned device scores the video data published by the client user according to the fan portrait in the scoring parameter, it can be set to:
  • the proportion of fans the topic type to which the video data belongs is scored; where the proportion of fans is directly proportional to the score of the video data.
  • the scoring module in the above-mentioned device scores the video data published by the client user according to the distribution of the site content in the scoring parameter, which can be set as:
  • the topic type to which the video data posted by the client user belongs and the content distribution within the site determine the proportion of videos of the topic type within the site
  • the proportion of the video the topic type to which the video data belongs is scored; wherein the proportion of the video is inversely proportional to the level of the scoring result.
  • the sending module in the above-mentioned device may be set to:
  • the scoring result, the direction to be improved, and the improvement suggestion are sent to the client user.
  • the above-mentioned device further includes: a fan portrait determination module, which can be configured as:
  • the electronic device includes:
  • One or more processors are One or more processors;
  • Memory used to store one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the video processing method according to any embodiment of the present application.
  • a readable medium provided according to one or more embodiments of the present application has a computer program stored thereon, and when the program is executed by a processor, the video processing method as described in any embodiment of the present application is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请公开了一种视频处理方法、装置、电子设备及可读介质。该方法包括:按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;将所述评分结果发送给所述客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。

Description

视频处理方法、装置、电子设备及可读介质
本公开要求在2019年08月20日提交中国专利局、申请号为201910769741.9的中国专利申请的优先权,以上申请的全部内容通过引用结合在本公开中。
技术领域
本申请实施例涉及互联网技术领域,例如涉及一种视频处理方法、装置、电子设备及可读介质。
背景技术
相关技术中,视频播放或视频直播类的应用程序,通常支持用户将自己拍摄的视频数据发布至应用程序的服务平台,供其他用户进行观看。
相关技术中,用户通过应用程序客户端发布视频后,应用程序的服务平台会直接将该视频数据的视频流发送至各客户端用户,以供其他客户端用户观看。发布视频数据的用户会根据自己的经验不断调整其发布的视频内容,来提高发布视频的质量。但是,由于应用程序的客户端用户水平不等,导致发布至服务平台站内的视频质量参数不齐,严重影响服务平台视频资源的整体质量。
发明内容
本申请实施例提供一种视频处理方法、装置、电子设备及可读介质,以实现自动对视频进行评分,并基于该评分结果辅助用户优化视频质量,保证了服务平台视频资源的整体质量。
第一方面,本申请实施例提供了一种视频处理方法,该方法包括:
按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
将所述评分结果发送给所述客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
第二方面,本申请实施例还提供了一种视频处理装置,该装置包括:
评分模块,被设置为按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
发送模块,被设置为将所述评分结果发送给所述客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
第三方面,本申请实施例还提供了一种电子设备,该电子设备包括:
处理器;
存储器,用于存储程序;
当所述程序被所述处理器执行,使得所述处理器实现如本申请任意实施例 所述的视频处理方法。
第四方面,本申请实施例提供了一种可读介质,所述可读介质上存储有计算机程序,所述计算机程序被处理器执行时实现如本申请任意实施例所述的视频处理方法。
附图说明
结合附图并参考以下具体实施方式,本申请各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中,相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的,原件和元素不一定按照比例绘制。
图1为本申请实施例提供的一种视频处理方法的流程图;
图2A为本申请实施例提供的基于作者历史数据执行视频处理方法的流程图;
图2B为本申请实施例提供的作者历史数据对应的界面示意图;
图2C为本申请实施例提供的基于粉丝画像执行视频处理方法的流程图;
图2D为本申请实施例提供的基于站内内容分布执行视频处理方法的流程图;
图3为本申请实施例提供的另一种视频处理方法的流程图;
图4为本申请实施例提供的一种视频处理装置的结构示意图;
图5为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本申请的实施例。虽然附图中显示了本申请的一些实施例,然而应当理解的是,本申请可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例。提供这些实施例是为了更加透彻和完整地理解本申请。应当理解的是,本申请的附图及实施例仅用于示例性作用,并非用于限制本申请的保护范围。
应当理解,本申请的方法实施方式中记载的各个步骤可以按照不同的顺序执行,和/或并行执行。此外,方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本申请的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括,即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”;术语“另一实施例”表示“至少一个另外的实施例”;术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意,本申请中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分,并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意,本申请中提及的“一个”、“多个”的修饰是示意性而非限制性的,本领域技术人员应当理解,除非在上下文另有明确指出,否则应该理解为“一个或多个”。本申请实施方式中的多方之间所交互的消息或者信息的名称仅用于说明性的目的,而并不是用于对这些消息或信息的范围进行限制。
图1为本申请实施例提供的一种视频处理方法的流程图,本实施例可适用于对用户发布的视频进行评分,并向用户反馈评分结果的情况,该方法可以由视频处理装置或电子设备来执行,该装置可以通过软件和/或硬件的方式来实现,该装置可以配置在电子设备中。可选的,该电子设备可以是应用程序的后端服务平台对应的设备,还可以是安装有应用程序客户端的移动终端设备。
需要说明的是,本申请实施例的视频处理方法既可用于对客户端用户上传的拍摄视频(如短视频或小视频等)进行处理,还可适用于对主播客户每次的直播视频进行处理。
可选的,如图1所示,本实施例中的方法可以包括如下步骤:
S101,按照评分参数,对客户端用户发布的视频数据进行评分,得到视频数据的评分结果。
其中,评分参数是对视频数据进行评分时所依据的参数,其可以包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;其中,作者历史数据可以包括客户端用户历史发布的各视频所涉及的各个方面的数据,其可以包括:历史发布的各视频的具体内容、发布时间、播放次数、转发次数、收藏次数、视频内容评分以及评论数据等等。粉丝画像可以是客户端用户所拥有的粉丝的用户画像,其可以包括:粉丝的年龄、性别以及喜好的视频主题类型等等。站内内容分布可以是指服务平台站内所拥有的总视频资源中,各主题类型视频在总视频资源中的分布情况,例如,可以是各主题类型视频的数量,还可以是各主题类型视频占总视频资源中的比例等。视频清晰度可以是指视频播放效果的清晰程度。
可选的,本实施例中,可以每隔预设周期(如1小时),触发执行对该预设周期内接收到的客户端用户发布的视频数据进行评分的操作。本实施例中,还可以在检测到客户端用户上传了新的视频数据后,触发执行对当前客户端用户发布的视频数据进行评分的操作。可选的,在按照评分参数,对客户端用户发布的视频数据进行评分时,可以针对各评分参数设置一个与其对应的评分体系,基于各评分参数对应的评分体系,对客户端用户发布的视频数据进行评分。
在一实施例中,作者历史数据的评分体系中,可以根据客户端用户发布的视频数据所属的主题类型,确定客户端用户的作者历史数据中该主题类型的反馈数据(如视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中 的至少一个),根据所述反馈数据,对所述视频数据所属的主题类型进行评分。粉丝画像的评分体系中,可以根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的粉丝画像中所述主题类型的粉丝占比;根据所述粉丝占比,对所述视频数据所属的主题类型进行评分;其中,粉丝占比的高低与视频数据评分的高低成正比。站内内容分布的评分体系中,可以根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比;根据所述视频占比,对所述视频数据所属的主题类型进行评分;其中,视频占比的高低与评分结果的高低成反比。视频清晰度的评分体系中,可以按照相关算法对客户端用户发布的视频数据进行清晰度计算,根据计算结果对客户端用户当前发布的视频数据的整体效果进行评分,其中,清晰程度的高低与评分结果的高低成正比。需要说明的是,如何根据上述各种评分参数的评分体系对客户端用户发布的视频数据进行评分的过程将在后续实施例进行详细介绍。
可选的,本申请实施例中,若评分参数为作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的一个,则本步骤可以将该评分参数的评分体系确定出的评分结果作为该客户端用户发布的视频数据的评分结果。若评分参数为作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少两个时,可以通过如下子步骤得到视频数据的评分结果:
S1011,按照评分参数中作者历史数据、粉丝画像和站内内容分布中的至少一种,对客户端用户发布的视频数据进行主题类型评分,得到第一评分结果。
在一实施例中,本子步骤通过作者历史数据、粉丝画像、站内内容分布中的至少一种评分参数,按照该评分参数的评分体系,确定出各评分参数下对应的子评分(需要说明的是,该操作的执行方法将在后续实施例详细介绍)。在一实施例中,可以直接将各子评分构成的集合作为第一评分结果。在一实施例中,还可以对各子评分进行综合处理,将综合处理后的结果作为第一评分结果。可选的,所述综合处理可以是对各子评分直接进行均值或求和运算处理,还可以是为各评分参数设置权重值,对各评分参数对应的子评分进行加权求和或加权均值处理。
S1012,按照评分参数中的视频清晰度对客户端用户发布的视频数据进行整体效果评分,得到第二评分结果。
在一实施例中,本子步骤中,可以按照视频清晰度的评分体系,按照清晰度计算算法,判断客户端用户发布的视频数据的分辨率是否达到清晰度要求、视频中是否存在模糊像素点以及是否存在重影区域等中的至少一项,然后根据判断结果对客户端用户当前发布的视频数据的整体效果进行评分。例如,判断结果为分辨率达到清晰度要求、不存在模糊的像素点或不存在重影区域中的至 少一种,对应视频数据的整体效果评分(即第二评分结果)也会相应的增加。
S1013,根据第一评分结果和第二评分结果,得到视频数据最终的评分结果。
在一实施例中,本步骤中,在根据第一评分结果和第二评分结果确定视频数据的评分结果时,可以对第一评分结果和第二评分结果进行均值或求和运算,得到视频数据的评分结果,作为视频数据最终的评分结果;本步骤中,还可以为第一评分结果和第二评分结果设置不同的权重值,对第一评分结果和第二评分结果进行加权求和或加权均值运算,得到视频数据最终的评分结果;本步骤中,还可以将第一评分结果和第二评分结果的集合作为最终的评分结果。
需要说明的是,若本步骤中的至少两个评分参数中不包含视频清晰度,则可以对所述至少两个评分参数只执行S1011的操作,并将第一评分结果作为最终的客户端用户发布的视频数据的评分结果。
S102,将评分结果发送给客户端用户,以使客户端用户根据评分结果优化发布视频的质量。
可选的,本申请实施例中,在S101得到视频数据的评分结果后,为了让客户端用户更好的了解自己本次发布视频的质量以及受欢迎程度,电子设备可以直接将得到的评分结果发送至客户端用户。在一实施例中,可以向客户端用户所属终端上安装的应用程序客户端发送评分结果,其中,评分结果可以是以通知消息、视频发布的回执消息、弹窗等形式发送给客户端用户。客户端用户接收到评分结果后,可以通过评分结果了解自己本次发布的视频数据的评分结果,即自己发布的视频数据是否是高质量的视频数据,进而根据评分结果对后续发布视频进行优化,提高后续发布视频的质量,吸引更多的粉丝。例如,若客户端用户本次发布的视频数据为风景类型的视频,该视频的清晰度比较高,但评分结果仍较低,则说明该客户端用户的粉丝对风景类型的视频不感兴趣,下一次客户端用户在发布视频时就可以调整发布视频的主题类型,减少或避免发送风景类型的视频。
需要说明的是,本申请实施例的操作还可以适用于如下场景:电子设备检测到客户端用户触发视频数据发布事件(如点击视频上传按键)后,先不执行视频数据的发布操作,而是先执行本实施例S101按照评分参数,对客户端用户发布的视频数据进行评分以及S102将评分结果反发送至客户端用户,以提示用户是否还要继续发布该视频数据,若接收到用户触发的确定发布指令后,再执行该视频数据的发布操作。例如,客户端用户通过应用程序的视频发布界面上传一个视频数据后,电子设备先对该视频数据进行评分,然后在当前视频发布界面上显示提示弹框,该提示弹框上显示该视频数据的评分结果以及询问用户是否继续发布该视频数据的提示语,若用户认为评分满足自己的要求,可以直 接上传,就点击确认发布按键,电子设备在检测到用户触发的确认发布指令后,执行该视频数据的发布操作。若用户认为评分较低,需要进行调整时,就点击取消发布按键。电子设备在检测到用户触发的取消发布指令后,可以不对该视频数据执行发布操作,可以等待用户修改后再上传视频数据后,再重新执行本申请实施例的上述对上传的视频数据进行评分以及发送评分结果操作。这样设置的好处是在用户发布视频时,通过对该视频数据进行评分,辅助客户端用户根据评分结果优化本次发布视频,从而保证用户每一次发布视频都是高质量的视频。
本申请实施例提供了一种视频处理方法,通过按照作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个评分参数自动对客户端用户发布的视频数据进行评分,并将评分结果发送给客户端用户。本申请实施例的方案可以实现实时对客户端发布的视频数据进行评分,并向客户端用户反馈评分结果,以辅助客户端用户根据本次发布视频的评分对后续发布视频进行优化,提高后续发布视频的质量,吸引更多粉丝的同时从整体上提高了服务平台站内的视频资源质量。
本申请实施例在按照评分参数,对客户端用户发布的视频数据进行评分之前,还可包括:获取评分参数。其中,评分参数中的作者历史数据的获取方式可以是服务器平台已预先记录各客户端用户的作者历史数据,电子设备直接与服务平台交互获取即可;评分参数中的作者历史数据的获取方式还可以是电子设备通过对用户已发布的历史视频数据所涉及的所有数据进行识别获取,如通过文字识别得到历史视频数据所涉及的所有文字数据,通过图像识别得到历史视频数据所涉及的所有图像数据。可以将获取的文字数据和图像数据一并作为作者历史数据。评分参数中的粉丝画像的获取方式可以是:服务器平台已预先绘制并记录各客户端用户的粉丝画像,电子设备直接与服务平台交互获取即可;评分参数中的粉丝画像的获取方式还可以是电子设备通过获取客户端用户的粉丝数据;将粉丝数据输入神经网络模型,得到该粉丝数据的粉丝画像。在一实施例中,可以预先训练一个绘制用户画像的神经网络模型,然后获取与客户端用户粉丝相关的所有粉丝数据(如粉丝的用户名、性别、年龄、所在地区、在应用程序上的所有操作行为数据等)针对每一个粉丝,将该粉丝的粉丝数据输入训练好的神经网络模型中,该神经网络模型就会基于输入的粉丝数据,绘制出该粉丝的用户画像(即粉丝画像)。站内内容分布的获取方式可以是服务器平台已预先统计好站内视频内容的分布情况,电子设备直接与服务平台交互获取即可;站内内容分布的获取方式还可以是电子设备在需要使用站内内容分布时,实时对服务平台站内所拥有的视频资源进行统计得到的。视频清晰度判断的相 关算法可以是电子设备本地存储的,需要判断视频数据的清晰度时,直接调用本地记录的相关算法即可。
图2A为本申请实施例提供的基于作者历史数据执行视频处理方法的流程图,图2B为本申请实施例提供的作者历史数据对应的界面示意图;图2C为本申请实施例提供的基于粉丝画像执行视频处理方法的流程图,图2D为本申请实施例提供的基于站内内容分布执行视频处理方法的流程图。本实施例在上述实施例提供的各可选方案的基础上进行了改动,给出了如何基于作者历史数据、粉丝画像和站内内容分布,对客户端用户发布的视频数据进行评分的详细介绍。
可选的,如图2A所示,当评分参数为作者历史数据时,本实施例的方法可以包括如下步骤:
S201,根据客户端用户发布的视频数据所属的主题类型,确定客户端用户的作者历史数据中该主题类型的反馈数据。
其中,视频数据的主题类型可以是对视频数据按照内容的主题题材分为不同的类型,例如,可以包括:风景类、美食类、歌舞类、运动类等。反馈数据可以是作者历史数据中和粉丝反馈相关的数据信息,其可以包括:视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中的至少一个。
可选的,本步骤中,可以先对客户端用户当前发布的视频数据进行主题类别的识别,识别方法可以有很多,例如,可以是采用预先训练的主题类别识别模型来对视频数据进行主题的识别,还可以是预先构建一个记录各主题类型及其对应的候选关键词的关联关系的数据库,对客户端用户发布的视频数据的描述信息或内容进行关键词提取,并将提取的关键词与数据库中记录的候选关键词进行匹配,将匹配的候选关键词对应的主题类型作为客户端用户发布的视频数据所属的主题类型;本步骤中,还可以是视频数据中的一字段记载有该视频数据的主题类型,可以直接从该视频数据的对应字段提取其对所属的主题类型。
可选的,由于客户端用户的作者历史数据中包括该客户端用户已发布的所有历史视频数据所涉及的信息,所以本步骤在确定了客户端用户发布的视频数据所属的主题类型后,需要从客户端用户的作者历史数据中确定出该主题类型的反馈数据。确定方法可以是:服务平台已记录各客户端用户的作者历史数据中各主题类型的反馈数据,直接与服务平台交互获取所需主题类型的反馈数据;主题类型的反馈数据还可以是通过如下子步骤来确定:
S2011,从客户端用户的作者历史数据中,查找属于该主题类型的目标作者历史数据。
在一实施例中,由于作者历史数据中包含了历史视频数据所涉及的全部数据,所以本步骤中,可以采用上述介绍的与确定客户端用户当前发布视频数据 所属主题类型相类似的方法,先从客户端用户的作者历史数据中,筛选出与待进行评分的视频数据(即客户端用户发布的视频数据)属于同一主题类型的作者历史数据作为目标作者历史数据。
S2012,识别目标作者历史数据中的反馈图标区域。
其中,反馈图标是与粉丝观看视频后的反馈操作相关的图标,其可以包括:转发图标、播放图标、收藏图标和评分图标中的至少一个。在一实施例中,本子步骤可以采用图像识别技术,从目标作者历史数据中识别反馈图标,如转发图标、播放图标、收藏图标和评分图标,并将反馈图标周围预设范围内作为一个反馈图标区域。例如,如图2B所示,若从目标作者历史数据中识别到评分图标,则将评分图标周围预设大小的范围,即方框20所在范围作为一个反馈图标区域。可选的,若识别到的多个反馈图标位置之间的间距小于预设的距离阈值,还可以是将多个反馈图标作为一个整体,将其周围预设范围作为一个反馈图标区域。例如,如图2B所示,若识别到的播放图标、转发图标和收藏图标之间的间距小于距离阈值1cm,则可以将这三个图标作为一个状体,将其周围预设大小的范围,即方框21所在的范围作为一个反馈图标区域。
S2013,在反馈图标区域进行文字识别,得到目标作者历史数据中反馈图标对应的数值信息,作为作者历史数据中主题类型的反馈数据。
在一实施例中,在识别出反馈图标区域后,对于反馈图标区域采用文字识别技术,识别该反馈图标周围数字和计数量词(如千、万、亿等),作为目标作者历史数据中反馈图标对应的数值信息,该数值信息代表该反馈图标被操作的次数,属于作者历史数据中主题类型的一部分反馈数据。例如,如图2B所示,对反馈图标区域20进行文字识别,将识别到的7.2作为反馈数据中的评分数据。
可选的,本申请实施例中,作者历史数据中主题类型的反馈数据还包括评论数据,对于评论数据,确定方式可以是先从目标作者历史数据中定位评论页面,然后对该页面的内容进行行文字识别,将识别到的文字作为反馈数据中的评论数据。
S202,根据反馈数据,对视频数据所属的主题类型进行评分。
可选的,本步骤根据反馈数据,对视频数据所属的主题类型进行评分时,若反馈数据为反馈图标对应的数值信息,即作者历史数据中对应S201确定的主题类型的视频播放次数、转发次数、收藏次数,则数值信息对应的数值越高,说明客户端用户发布的该主题类型的视频越受粉丝喜欢,此时对视频数据所属的主题类型的评分就越高。若反馈数据为评论数据,则可以是对评论数据进行语义分析,统计评论数据中好评数据在总评论数据中的占比,占比越高,说明客户端用户发布的该主题类型的视频越受粉丝喜欢,此时对视频数据所属的主 题类型的评分就越高。
S203,将评分结果发送给客户端用户,以使客户端用户根据评分结果优化发布视频的质量。
可选的,如图2C所示,当评分参数为粉丝画像时,本实施例的方法可以包括如下步骤:
S204,根据客户端用户发布的视频数据所属的主题类型,确定客户端用户的粉丝画像中该主题类型的粉丝占比。
可选的,本步骤中,可以采用与S201类似的方式,先确定客户端用户发布的视频数据所属的主题类型,然后再根据该客户端用户的粉丝画像,分析每个粉丝喜欢的主题类型,最后确定喜欢客户端用户发布的视频数据所属的主题类型的粉丝占总粉丝数量的百分比,得到该客户端用户的粉丝画像中该主题类型的粉丝占比。可选的,本实施例中,还可以是服务平台已统计并记录各客户端用户的粉丝画像中各主题类型对应的粉丝占比,在确定客户端用户发布的视频数据所属的主题类型后,电子设备可以直接与服务平台交互,获取客户端用户的粉丝画像中该主题类型的粉丝占比。
S205,根据粉丝占比,对视频数据所属的主题类型进行评分。
可选的,在S204确定出客户端用户发布的视频数据所属的主题类型的粉丝占比之后,可以根据预先设置的粉丝占比与对应主题类型的视频数据评分之间的关联关系,来对视频数据所属的主题类型进行评分,其中,粉丝占比的高低与视频数据评分的高低成正比。例如,若预先设置主题类型的视频数据的评分=该主题类型的粉丝占比×100,则当S204确定的粉丝占比为80%时,本步骤对应视频数据所属主题类型评分为80分。
S206,将评分结果发送给客户端用户,以使客户端用户根据评分结果优化发布视频的质量。
需要说明的是,本实施例在根据粉丝画像,对客户端用户发布的视频数据进行评分时,还可以根据粉丝画像中的粉丝性别或年龄进行评分,若视频数据的主题类型符合粉丝性别或年龄所喜好的类型,则对该视频数据的评分就为高分,否则评分就为低分。例如,若客户端用户发布的视频数据为极限运动的视频数据,若该客户端用户粉丝年龄段在20-30岁之间,则该视频数据的评分为高评分,若该客户端用户粉丝年龄段在50岁以上,则该视频数据的评分为低评分。
可选的,如图2D所示,当评分参数为站内内容分布时,本实施例的方法可以包括如下步骤:
S207,根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比。
可选的,本步骤中,可以采用与S201类似的方式,先确定客户端用户发布的视频数据所属的主题类型,然后再对服务平台站内拥有的所有视频数据进行主题类型的分类统计,确定站内各主题类型视频数据的数量占总视频数量的百分比,得到站内该客户端用户发布的视频数据所属主题类型的视频占比。可选的。本实施例中,还可以是服务平台已统计并记录站内所拥有的视频数据对应的各主题类型的视频占比,在确定客户端用户发布的视频数据所属的主题类型后,电子设备可以直接与服务平台交互,获取站内该主题类型的视频占比。
S208,根据视频占比,对视频数据所属的主题类型进行评分。
可选的,S207在确定出客户端用户发布的视频数据所属的主题类型的视频占比之后,可以根据预先设置的视频占比与对应主题类型的视频数据评分之间的关联关系,来对视频数据所属的主题类型进行评分,其中,视频占比的高低与视频数据评分的高低成反比。例如,若预先设置主题类型的视频数据的评分=(1-该主题类型的视频占比)×100,则当S207确定的视频占比为60%时,本步骤对应视频数据所属主题类型评分为40分。
S209,将评分结果发送给客户端用户,以使客户端用户根据评分结果优化发布视频的质量。
需要说明的是,本申请实施例在执行视频处理方法时,可以通过上述一种评分参数执行对客户端用户发布的视频数据进行评分。为了进一步提高对视频数据评分的准确性,还可以是将上述通过三种评分参数和视频清晰度参数结合对客户端用户发布的视频数据进行评分,在得到各评分参数对应的视频评分结果后,如何根据多个评分结果得到最终的评分结果的方法上述实施例已经进行了详细介绍,在此不进行赘述。
本申请实施例提供了基于三种不同的评分参数,即作者历史数据、粉丝画像和站内内容分布,对客户端用户发布的视频数据进行评分,进而向客户端用户发送评分结果的方法,针对每一种评分参数,都对应设置有不同的视频评分方法,在对客户端用户发布的视频数据进行评分时,选择三种评分参数中的一个或多个,对客户端用户发布的视频数据进行评分,与相关技术中的人工进行视频评分相比,极大的降低了人工成本,而且考虑的因素全面,得到评分更为准确,发送给客户端用户后,能够更好的辅助客户端用户根据该评分结果优化后续发布视频的质量,吸引更多粉丝的同时提高服务平台站内视频资源的质量。
图3为本申请实施例提供的另一种视频处理方法的流程图,本实施例在上述实施例提供的各可选方案的基础上进行了改动,给出了将评分结果发送给客户端用户的详细介绍。
可选的,如图3所示,本实施例中的方法可以包括如下步骤:
S301,按照评分参数,对客户端用户发布的视频数据进行评分,得到视频数据的评分结果。
其中,评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个。
S302,若评分结果未达到高质量标准,则确定视频数据的待改进方向。
其中,高质量标准可以是评价一个视频数据的评分是否符合高质量视频的评价标准,其可以是一个高质量分数阈值(如85分);高质量标准还可以是由各评分参数(即作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个)对应的多个评分阈值构成的评分阈值集合;高质量标准还可以是由上述高质量分数阈值和评分阈值集合构成的综合阈值集合。
需要说明的是,S301得到的视频数据的评分结果可以是各评分参数对应的总评分;还可以是各评分参数对应的子评分的集合;还可以是各评分参数对应的子评分以及总评分的集合。本步骤可以根据S301得到的评分结果的形式,选择上述对应的高质量标准的形式进行比较。在可实施方式一中,若S301得到的视频数据评分结果为各评分参数对应的总评分,则高质量标准也是一个高质量评分阈值,此时若S301得到的总评分大于或等于该高质量评分阈值,则说明评分结果达到高质量标准,否则评分结果未达到高质量标准。在可实施方式二中,若S301得到的视频数据评分结果为各评分参数对应的子评分的集合,则高质量标准也是由各评分参数对应的多个评分阈值构成的评分阈值集合,此时若S301得到的分数集合中每一个子评分都大于或等于评分阈值集合中对应的评分阈值,则说明评分结果达到高质量标准,否则评分结果未达到高质量标准。在可实施方式三中,若S301得到的视频数据评分结果为各评分参数对应的子评分以及总评分的集合,则高质量标准为高质量分数阈值和评分阈值集合构成的综合阈值集合,比较方式可与上述可实施方式二类似,在此不进行赘述。
可选的,若S301得到的评分结果未达到高质量标准,为了更好的辅助客户端用户优化后续发布视频的质量,本步骤中,可以根据评分结果未达到高质量标准的原因,确定视频数据的待改进方向。由于本实施例S301按照评分参数,对客户端用户发布的视频数据评分时,是通过主题类型和/或清晰度两个方面进行评分的,所以若评分结果未达到高质量标准,原因应该是视频数据的主题类型选择不合适和/或清晰度不高,所以对应的数据的待改进方向是:调整发布视频的主题类型和/或提高视频的清晰度。可选的,若评分结果中包括各评分参数对应的评分结果,还可以更精确的缩小待改进方向。在一实施例中,若评分参数中的视频清晰度对应的评分未达到高质量标准,则说明未达到高质量标准的原因是视频的清晰度不高,对应的待改进方向是提高视频的清晰度;若评分参 数中的作者历史数据、粉丝画像或站内内容分布中的至少一个对应的评分未达到高质量标准,则说明未达到高质量标准的原因是主题类型选择不合适,对应的待改进方向是调整发布视频的主题类型。
可选的,若S301得到的评分结果达到高质量标准,则可以是直接将该评分结果和达到高质量标准的判断结果发送给客户端用户。
S303,针对待改进方向确定改进建议。
可选的,本实施例可以预先建立改进方向与改进建议之间的关联关系,此时可以直接通过查找改进方向与改进建议之间的关联关系确定针对当前待改进的方向对应的改进建议。例如,针对改进方向提高视频的清晰度,可以预先关联一些提高视频清晰度的建议,如拍摄视频时手不要晃动、调整聚焦位置以及提高拍摄的分辨率等。还可以是根据当前场景下的实际情况,来确定改进建议,在一实施例中,对于调整发布视频的主题类型的改进方向,可以结合该客户端用户的粉丝喜好,将粉丝喜好的主题类型作为建议改进的主题类型;在一实施例中,还可以结合当前场景下服务平台站内所拥有的视频数据,将站内稀缺的视频主题类型作为建议改进的主题类型。
S304,将评分结果、待改进方向和改进建议发送给客户端用户,以使客户端用户根据评分结果、待改进方向和改进建议优化发布视频的质量。
本申请实施例提供了一种视频处理方法,通过评分参数自动对客户端用户发布的视频数据进行评分,若评分结果未达到高质量标准,确定视频数据的待改进方向和改进建议,并将评分结果、待改进方向和改进建议一并发送给客户端用户。本申请实施例的方案可以在视频数据的质量不高的情况下,将评分结果、待改进方向和改进建议一并反馈给客户端用户,以更好的协助客户端优化其后续的视频质量。即使客户端用户是没有经验的新用户,也可以根据接收到的评分结果、待改进方向和改进建议快速提高发布视频的质量,吸引更多粉丝,同时也提高了服务平台站内的视频资源质量。
图4为本申请实施例提供的一种视频处理装置的结构示意图,本申请实施例可适用于对用户发布的视频进行评分,并向用户反馈评分结果的情况。该装置可以通过软件和/或硬件来实现,并集成在执行本方法的电子设备中,如图4所示,该装置可以包括:
评分模块401,被设置为按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
发送模块402,被设置为将所述评分结果发送给客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
本申请实施例提供了一种视频处理装置,通过按照作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个评分参数自动对客户端用户发布的视频数据进行评分,并将评分结果发送给客户端用户。本申请实施例的方案可以实现实时对客户端发布的视频数据进行评分,并向客户端用户反馈评分结果,以辅助客户端用户根据本次发布视频的评分对后续发布视频进行优化,提高后续发布视频的质量,吸引更多粉丝的同时从整体上提高了服务平台站内的视频资源质量。
在一实施例中,所述评分模块401可被设置为:
按照评分参数中作者历史数据、粉丝画像和站内内容分布中的至少一种,对客户端用户发布的视频数据进行主题类型评分,得到第一评分结果;
按照评分参数中的视频清晰度对客户端用户发布的视频数据进行整体效果评分,得到第二评分结果;
根据所述第一评分结果和所述第二评分结果,得到所述视频数据最终的评分结果。
在一实施例中,所述评分模块401按照评分参数中的作者历史数据,对客户端用户发布的视频数据进行评分时,可被设置为:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据;所述反馈数据包括:视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中的至少一个;
根据所述反馈数据,对所述视频数据所属的主题类型进行评分。
在一实施例中,所述评分模块401执行确定所述客户端用户的作者历史数据中所述主题类型的反馈数据时,可被设置为:
从所述客户端用户的作者历史数据中,查找属于所述主题类型的目标作者历史数据;
识别所述目标作者历史数据中的反馈图标区域,所述反馈图标区域为反馈图标周围的预设范围,所述反馈图标包括:转发图标、播放图标、收藏图标和评分图标中的至少一个;
在所述反馈图标区域进行文字识别,得到所述目标作者历史数据中反馈图标对应的数值信息,作为所述作者历史数据中所述主题类型的反馈数据。
在一实施例中,所述评分模块401按照评分参数中的粉丝画像,对客户端用户发布的视频数据进行评分时,可被设置为:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的粉丝画像中所述主题类型的粉丝占比;
根据所述粉丝占比,对所述视频数据所属的主题类型进行评分;其中,粉 丝占比的高低与视频数据评分的高低成正比。
在一实施例中,所述评分模块401按照评分参数中的站内内容分布,对客户端用户发布的视频数据进行评分,可被设置为:
根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比;
根据所述视频占比,对所述视频数据所属的主题类型进行评分;其中,视频占比的高低与评分结果的高低成反比。
在一实施例中,所述发送模块402可被设置为:
若所述评分结果未达到高质量标准,则确定所述视频数据的待改进方向;
针对所述待改进方向确定改进建议;
将所述评分结果、所述待改进方向和所述改进建议发送给客户端用户。
在一实施例中,所述装置还包括:粉丝画像确定模块,该模块可被设置为:
获取客户端用户的粉丝数据;
将所述粉丝数据输入神经网络模型,得到所述粉丝数据的粉丝画像。
本申请实施例提供的视频处理装置,与上述各实施例提供的视频处理方法属于同一发明构思,未在本申请实施例中详尽描述的技术细节可参见上述各实施例,并且本申请实施例与上述各实施例具有相同的有益效果。
下面参考图5,图5为适于用来实现本申请实施例的电子设备500的结构示意图。本申请实施例中的电子设备可以是应用程序的后端服务平台对应的设备,还可以是安装有应用程序客户端的移动终端设备。在一实施例中,该电子设备可以包括诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图5示出的电子设备500仅仅是一个示例。
如图5所示,电子设备500可以包括处理装置(例如中央处理器、图形处理器等)501,其可以根据存储在只读存储器(ROM)502中的程序或者从存储装置508加载到随机访问存储器(RAM)503中的程序而执行各种适当的动作和处理。在RAM 503中,还存储有电子设备500操作所需的各种程序和数据。处理装置501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(I/O)接口505也连接至总线504。
通常,以下装置可以连接至I/O接口505:包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置506;包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置507;包括例如磁带、硬盘等的存储装置508;以及通信装置509。通信装置509可以允许电子设备500与其他设 备进行无线或有线通信以交换数据。虽然图5示出了具有各种装置的电子设备500,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
根据本申请的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本申请的实施例包括一种计算机程序产品,其包括承载在非暂态计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置509从网络上被下载和安装,或者从存储装置508被安装,或者从ROM 502被安装。在该计算机程序被处理装置501执行时,执行本申请实施例的方法中限定的上述功能。
需要说明的是,本申请上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的例子可以包括:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,可以包括电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,可以包括:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
在一些实施方式中,电子设备可以利用诸如HTTP(HyperText Transfer Protocol,超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信,并且可以与任意形式或介质的数字数据通信(例如,通信网络)互连。通信网络的示例包括局域网(“LAN”),广域网(“WAN”),网际网(例如,互联网)以及端对端网络(例如,ad hoc端对端网络),以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备内部进程执行:按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;将所述评分结果发送给客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码,上述程序设计语言可以包括面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图,图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如,非限制性地,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本申请的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地 使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的示例可以包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本申请的一个或多个实施例提供的一种视频处理方法,该方法包括:
按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
将所述评分结果发送给客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
根据本申请的一个或多个实施例,上述方法中,按照评分参数,对客户端用户发布的视频数据进行评分,包括:
按照评分参数中作者历史数据、粉丝画像和站内内容分布中的至少一种,对客户端用户发布的视频数据进行主题类型评分,得到第一评分结果;
按照评分参数中的视频清晰度对客户端用户发布的视频数据进行整体效果评分,得到第二评分结果;
根据所述第一评分结果和所述第二评分结果,得到所述视频数据最终的评分结果。
根据本申请的一个或多个实施例,上述方法中,按照评分参数中的作者历史数据,对客户端用户发布的视频数据进行评分,包括:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据;所述反馈数据包括:视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中的至少一个;
根据所述反馈数据,对所述视频数据所属的主题类型进行评分。
根据本申请的一个或多个实施例,上述方法中,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据,包括:
从所述客户端用户的作者历史数据中,查找属于所述主题类型的目标作者历史数据;
识别所述目标作者历史数据中的反馈图标区域,所述反馈图标区域为反馈图标周围的预设范围,所述反馈图标包括:转发图标、播放图标、收藏图标和评分图标中的至少一个;
在所述反馈图标区域进行文字识别,得到所述目标作者历史数据中反馈图标对应的数值信息,作为所述作者历史数据中所述主题类型的反馈数据。
根据本申请的一个或多个实施例,上述方法中,按照评分参数中的粉丝画像,对客户端用户发布的视频数据进行评分,包括:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的粉丝画像中所述主题类型的粉丝占比;
根据所述粉丝占比,对所述视频数据所属的主题类型进行评分;其中,粉丝占比的高低与视频数据评分的高低成正比。
根据本申请的一个或多个实施例,上述方法中,按照评分参数中的站内内容分布,对客户端用户发布的视频数据进行评分,包括:
根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比;
根据所述视频占比,对所述视频数据所属的主题类型进行评分;其中,视频占比的高低与评分结果的高低成反比。
根据本申请的一个或多个实施例,上述方法中,将所述评分结果发送给客户端用户,包括:
若所述评分结果未达到高质量标准,则确定所述视频数据的待改进方向;
针对所述待改进方向确定改进建议;
将所述评分结果、所述待改进方向和所述改进建议发送给客户端用户。
根据本申请的一个或多个实施例,上述方法中,在按照评分参数,对客户端用户发布的视频数据进行评分之前,还包括:
获取客户端用户的粉丝数据;
将所述粉丝数据输入神经网络模型,得到所述粉丝数据的粉丝画像。
根据本申请的一个或多个实施例提供的一种视频处理装置,该装置包括:
评分模块,被设置为按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
发送模块,被设置为将所述评分结果发送给客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
根据本申请的一个或多个实施例,上述装置中的评分模块可被设置为:
按照评分参数中作者历史数据、粉丝画像和站内内容分布中的至少一种,对客户端用户发布的视频数据进行主题类型评分,得到第一评分结果;
按照评分参数中的视频清晰度对客户端用户发布的视频数据进行整体效果评分,得到第二评分结果;
根据所述第一评分结果和所述第二评分结果,得到所述视频数据最终的评分结果。
根据本申请的一个或多个实施例,上述装置中的评分模块按照评分参数中的作者历史数据,对客户端用户发布的视频数据进行评分时,可被设置为:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据;所述反馈数据包括:视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中的至少一个;
根据所述反馈数据,对所述视频数据所属的主题类型进行评分。
根据本申请的一个或多个实施例,上述装置中的评分模块执行确定所述客户端用户的作者历史数据中所述主题类型的反馈数据时,可被设置为:
从所述客户端用户的作者历史数据中,查找属于所述主题类型的目标作者历史数据;
从所述客户端用户的作者历史数据中,查找属于所述主题类型的目标作者历史数据;
识别所述目标作者历史数据中的反馈图标区域,所述反馈图标区域为反馈图标周围的预设范围,所述反馈图标包括:转发图标、播放图标、收藏图标和评分图标中的至少一个;
在所述反馈图标区域进行文字识别,得到所述目标作者历史数据中反馈图标对应的数值信息,作为所述作者历史数据中所述主题类型的反馈数据。
根据本申请的一个或多个实施例,上述装置中的评分模块按照评分参数中的粉丝画像,对客户端用户发布的视频数据进行评分时,可被设置为:
根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的粉丝画像中所述主题类型的粉丝占比;
根据所述粉丝占比,对所述视频数据所属的主题类型进行评分;其中,粉丝占比的高低与视频数据评分的高低成正比。
根据本申请的一个或多个实施例,上述装置中的评分模块按照评分参数中的站内内容分布,对客户端用户发布的视频数据进行评分,可被设置为:
根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比;
根据所述视频占比,对所述视频数据所属的主题类型进行评分;其中,视频占比的高低与评分结果的高低成反比。
根据本申请的一个或多个实施例,上述装置中的发送模块可被设置为:
若所述评分结果未达到高质量标准,则确定所述视频数据的待改进方向;
针对所述待改进方向确定改进建议;
将所述评分结果、所述待改进方向和所述改进建议发送给客户端用户。
根据本申请的一个或多个实施例,上述装置还包括:粉丝画像确定模块,该模块可被设置为:
获取客户端用户的粉丝数据;
将所述粉丝数据输入神经网络模型,得到所述粉丝数据的粉丝画像。
根据本申请的一个或多个实施例提供的一种电子设备,该电子设备包括:
一个或多个处理器;
存储器,用于存储一个或多个程序;
当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如本申请任意实施例所述的视频处理方法。
根据本申请的一个或多个实施例提供的一种可读介质,其上存储有计算机程序,该程序被处理器执行时实现如本申请任意实施例所述的视频处理方法。
虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了实现细节,但是这些不应当被解释为对本申请的范围的限制。在单独的实施例的上下文中描述的一些特征还可以组合地实现在单个实施例中。相反地,在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (11)

  1. 一种视频处理方法,包括:
    按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
    将所述评分结果发送给所述客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
  2. 根据权利要求1所述的方法,其中,按照评分参数,对客户端用户发布的视频数据进行评分,包括:
    按照评分参数中作者历史数据、粉丝画像和站内内容分布中的至少一个,对客户端用户发布的视频数据进行主题类型评分,得到第一评分结果;
    按照评分参数中的视频清晰度对所述客户端用户发布的视频数据进行整体效果评分,得到第二评分结果;
    根据所述第一评分结果和所述第二评分结果,得到所述视频数据的评分结果。
  3. 根据权利要求1或2所述的方法,其中,按照评分参数,对客户端用户发布的视频数据进行评分,包括:
    按照评分参数中的作者历史数据,对客户端用户发布的视频数据进行评分;
    其中,按照评分参数中的作者历史数据,对客户端用户发布的视频数据进行评分,包括:
    根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据;所述反馈数据包括:视频播放次数、收藏次数、转发次数、视频内容评分和评论数据中的至少一个;
    根据所述反馈数据,对所述视频数据所属的主题类型进行评分。
  4. 根据权利要求3所述的方法,其中,确定所述客户端用户的作者历史数据中所述主题类型的反馈数据,包括:
    从所述客户端用户的作者历史数据中,查找属于所述主题类型的目标作者历史数据;
    识别所述目标作者历史数据中的反馈图标区域,所述反馈图标区域为反馈图标周围的预设范围,所述反馈图标包括:转发图标、播放图标、收藏图标和评分图标中的至少一个;
    在所述反馈图标区域进行文字识别,得到所述目标作者历史数据中所述反馈图标对应的数值信息,作为所述作者历史数据中所述主题类型的反馈数据。
  5. 根据权利要求1或2所述的方法,其中,按照评分参数,对客户端用户发布的视频数据进行评分,包括:
    按照评分参数中的粉丝画像,对客户端用户发布的视频数据进行评分;
    其中,按照评分参数中的粉丝画像,对客户端用户发布的视频数据进行评分,包括:
    根据客户端用户发布的视频数据所属的主题类型,确定所述客户端用户的粉丝画像中所述主题类型的粉丝占比;
    根据所述粉丝占比,对所述视频数据所属的主题类型进行评分;其中,所述粉丝占比的高低与视频数据评分的高低成正比。
  6. 根据权利要求1或2所述的方法,其中,按照评分参数,对客户端用户发布的视频数据进行评分,包括:
    按照评分参数中的站内内容分布,对客户端用户发布的视频数据进行评分;
    其中,按照评分参数中的站内内容分布,对客户端用户发布的视频数据进行评分,包括:
    根据客户端用户发布的视频数据所属的主题类型和站内内容分布,确定站内所述主题类型的视频占比;
    根据所述视频占比,对所述视频数据所属的主题类型进行评分;其中,所述视频占比的高低与评分结果的高低成反比。
  7. 根据权利要求1所述的方法,其中,将所述评分结果发送给所述客户端用户,包括:
    基于所述评分结果未达到高质量标准的判断结果,确定所述视频数据的待改进方向;
    针对所述待改进方向确定改进建议;
    将所述评分结果、所述待改进方向和所述改进建议发送给所述客户端用户。
  8. 根据权利要求1所述的方法,在按照评分参数,对客户端用户发布的视频数据进行评分之前,所述方法还包括:
    获取客户端用户的粉丝数据;
    将所述粉丝数据输入神经网络模型,得到所述粉丝数据的粉丝画像。
  9. 一种视频处理装置,包括:
    评分模块,被设置为按照评分参数,对客户端用户发布的视频数据进行评分,得到所述视频数据的评分结果;所述评分参数包括:作者历史数据、粉丝画像、站内内容分布以及视频清晰度中的至少一个;
    发送模块,被设置为将所述评分结果发送给所述客户端用户,以使所述客户端用户根据所述评分结果优化发布视频的质量。
  10. 一种电子设备,包括:
    处理器;
    存储器,用于存储程序;
    当所述程序被所述处理器执行,使得所述处理器实现如权利要求1-8中任一所述的视频处理方法。
  11. 一种可读介质,所述可读介质上存储有计算机程序,所述计算机程序被处理器执行时实现如权利要求1-8中任一所述的视频处理方法。
PCT/CN2020/108326 2019-08-20 2020-08-11 视频处理方法、装置、电子设备及可读介质 WO2021031917A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910769741.9 2019-08-20
CN201910769741.9A CN110366043B (zh) 2019-08-20 2019-08-20 视频处理方法、装置、电子设备及可读介质

Publications (1)

Publication Number Publication Date
WO2021031917A1 true WO2021031917A1 (zh) 2021-02-25

Family

ID=68224082

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/108326 WO2021031917A1 (zh) 2019-08-20 2020-08-11 视频处理方法、装置、电子设备及可读介质

Country Status (2)

Country Link
CN (1) CN110366043B (zh)
WO (1) WO2021031917A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115379259A (zh) * 2022-08-18 2022-11-22 百度在线网络技术(北京)有限公司 视频处理方法、装置、电子设备和存储介质
CN117119231A (zh) * 2023-10-13 2023-11-24 深圳市知酷信息技术有限公司 一种基于区块链的视频计费调控系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110366043B (zh) * 2019-08-20 2022-02-18 北京字节跳动网络技术有限公司 视频处理方法、装置、电子设备及可读介质
CN111277899B (zh) * 2020-02-18 2021-06-22 福州大学 基于短期记忆和用户期望的视频质量评价方法
CN112492297B (zh) * 2020-11-17 2022-06-14 腾讯科技(深圳)有限公司 一种对视频的处理方法以及相关设备
CN113342626B (zh) * 2021-05-28 2022-11-11 深圳市前海房极客网络科技有限公司 内容处理方法、装置、电子设备及存储介质
CN114390344A (zh) * 2022-01-11 2022-04-22 北京达佳互联信息技术有限公司 视频分发方法、装置、电子设备和计算机可读存储介质
CN114466222B (zh) * 2022-01-29 2023-09-26 北京百度网讯科技有限公司 一种视频合成方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130124653A1 (en) * 2011-11-16 2013-05-16 Loopa Llc Searching, retrieving, and scoring social media
CN109068158A (zh) * 2018-09-18 2018-12-21 苏州商信宝信息科技有限公司 一种基于网络平台的短视频价值估算推荐系统
CN109284417A (zh) * 2018-08-27 2019-01-29 广州飞磨科技有限公司 视频推送方法、装置、计算机设备和存储介质
CN109769128A (zh) * 2018-12-25 2019-05-17 北京达佳互联信息技术有限公司 视频推荐方法、视频推荐装置和计算机可读存储介质
CN110121108A (zh) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 视频价值评估方法及装置
CN110366043A (zh) * 2019-08-20 2019-10-22 北京字节跳动网络技术有限公司 视频处理方法、装置、电子设备及可读介质

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7038710B2 (en) * 2002-07-17 2006-05-02 Koninklijke Philips Electronics, N.V. Method and apparatus for measuring the quality of video data
US20100053300A1 (en) * 2007-02-02 2010-03-04 Einarsson Torbjoern Method And Arrangement For Video Telephony Quality Assessment
CN104219575B (zh) * 2013-05-29 2020-05-12 上海连尚网络科技有限公司 相关视频推荐方法及系统
CN105163106B (zh) * 2015-07-22 2017-04-12 天津科技大学 一种多重数据处理的视频质量评价系统
CN105812706A (zh) * 2016-03-17 2016-07-27 掌赢信息科技(上海)有限公司 一种视频通话质量评估方法及电子设备
CN105843876B (zh) * 2016-03-18 2020-07-14 阿里巴巴(中国)有限公司 多媒体资源的质量评估方法和装置
CN105898294A (zh) * 2016-05-27 2016-08-24 乐视控股(北京)有限公司 一种视频质量评价方法及装置
CN107451148A (zh) * 2016-05-31 2017-12-08 北京金山安全软件有限公司 一种视频分类方法、装置及电子设备
CN106060537B (zh) * 2016-08-04 2019-08-13 腾讯科技(深圳)有限公司 一种视频质量评估方法及装置
CN106454536B (zh) * 2016-09-19 2019-07-26 广州视源电子科技股份有限公司 信息推荐度的确定方法及装置
CN106682870A (zh) * 2016-12-12 2017-05-17 武汉图灵创客科技有限公司 创客教育社交平台系统
CN108243033A (zh) * 2016-12-26 2018-07-03 中国移动通信有限公司研究院 一种对视频质量进行打分的方法、云服务端和系统
CN106791579A (zh) * 2016-12-30 2017-05-31 唐常芳 一种视频会议质量的处理方法及系统
US10542298B2 (en) * 2017-03-02 2020-01-21 Cisco Technology, Inc. Autonomously generated video channels
CN108304429B (zh) * 2017-05-16 2021-12-14 腾讯科技(深圳)有限公司 信息推荐方法、装置和计算机设备
CN107249127B (zh) * 2017-05-18 2019-01-22 南京和电科技有限公司 一种评估准确的网络视频质量评估系统
CN109214634A (zh) * 2017-07-06 2019-01-15 腾讯科技(深圳)有限公司 一种信息处理方法、装置及信息处理可读介质
US10743076B2 (en) * 2017-09-05 2020-08-11 Roblox Corporation Automated content rating system and network
US20190087870A1 (en) * 2017-09-15 2019-03-21 Oneva, Inc. Personal video commercial studio system
CN110020110B (zh) * 2017-09-15 2023-04-07 腾讯科技(北京)有限公司 媒体内容推荐方法、装置及存储介质
CN109714557A (zh) * 2017-10-25 2019-05-03 中国移动通信集团公司 视频通话的质量评估方法、装置、电子设备和存储介质
CN108093274A (zh) * 2018-01-05 2018-05-29 武汉斗鱼网络科技有限公司 一种直播间排序方法、电子设备及可读存储介质
CN108280155B (zh) * 2018-01-11 2022-04-08 百度在线网络技术(北京)有限公司 基于短视频的问题检索反馈方法、装置及其设备
CN108737902B (zh) * 2018-05-22 2021-03-02 北京奇艺世纪科技有限公司 一种关联视频的更新方法、装置以及电子设备
CN108989555B (zh) * 2018-07-10 2021-06-04 Oppo广东移动通信有限公司 图像处理方法及相关产品
CN109729395B (zh) * 2018-12-14 2022-02-08 广州市百果园信息技术有限公司 视频质量评估方法、装置、存储介质和计算机设备
CN109729433B (zh) * 2019-01-22 2021-05-07 北京奇艺世纪科技有限公司 一种视频播放评估方法及装置
CN109858971A (zh) * 2019-02-03 2019-06-07 北京字节跳动网络技术有限公司 用户画像的处理方法、装置、存储介质及电子设备
CN109729348B (zh) * 2019-03-07 2020-06-02 腾讯科技(深圳)有限公司 一种确定视频质量的方法、装置及设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130124653A1 (en) * 2011-11-16 2013-05-16 Loopa Llc Searching, retrieving, and scoring social media
CN110121108A (zh) * 2018-02-06 2019-08-13 上海全土豆文化传播有限公司 视频价值评估方法及装置
CN109284417A (zh) * 2018-08-27 2019-01-29 广州飞磨科技有限公司 视频推送方法、装置、计算机设备和存储介质
CN109068158A (zh) * 2018-09-18 2018-12-21 苏州商信宝信息科技有限公司 一种基于网络平台的短视频价值估算推荐系统
CN109769128A (zh) * 2018-12-25 2019-05-17 北京达佳互联信息技术有限公司 视频推荐方法、视频推荐装置和计算机可读存储介质
CN110366043A (zh) * 2019-08-20 2019-10-22 北京字节跳动网络技术有限公司 视频处理方法、装置、电子设备及可读介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115379259A (zh) * 2022-08-18 2022-11-22 百度在线网络技术(北京)有限公司 视频处理方法、装置、电子设备和存储介质
CN115379259B (zh) * 2022-08-18 2024-04-26 百度在线网络技术(北京)有限公司 视频处理方法、装置、电子设备和存储介质
CN117119231A (zh) * 2023-10-13 2023-11-24 深圳市知酷信息技术有限公司 一种基于区块链的视频计费调控系统

Also Published As

Publication number Publication date
CN110366043B (zh) 2022-02-18
CN110366043A (zh) 2019-10-22

Similar Documents

Publication Publication Date Title
WO2021031917A1 (zh) 视频处理方法、装置、电子设备及可读介质
WO2021036876A1 (zh) 直播辅助数据的提供方法、装置、设备及可读介质
WO2021052085A1 (zh) 视频推荐方法、装置、电子设备及计算机可读介质
TWI683272B (zh) 資訊獲取方法、提供方法、裝置及系統、儲存介質
JP6730335B2 (ja) ストリーミングメディアプレゼンテーションシステム
CN110602564B (zh) 视频优化信息提供方法、装置、电子设备及可读介质
WO2020134571A1 (zh) 页面展示方法、装置、终端设备及存储介质
WO2021129157A1 (zh) 基于视频的交互实现方法、装置、设备及介质
CN111414543B (zh) 用于生成评论信息序列的方法、装置、电子设备和介质
US10733249B1 (en) Machine learning system for data selection
CN111050203A (zh) 一种视频处理方法、装置、视频处理设备及存储介质
US20210409787A1 (en) Techniques for providing interactive interfaces for live streaming events
US11388561B2 (en) Providing a summary of media content to a communication device
WO2023151589A1 (zh) 视频显示方法、装置、电子设备和存储介质
JP6781233B2 (ja) 統合インフォメーションの生成方法、統合インフォメーションのプッシュ方法及びその装置、端末、サーバ、媒体
WO2021218556A1 (zh) 信息展示方法、装置和电子设备
WO2020221121A1 (zh) 视频查询方法、装置、设备及存储介质
CN110475158B (zh) 视频学习素材的提供方法、装置、电子设备及可读介质
CN109639813B (zh) 视频文件传输处理方法及装置、电子设备和存储介质
CN112000251A (zh) 用于播放视频的方法、装置、电子设备和计算机可读介质
CN114996487B (zh) 媒体资源推荐方法、装置、电子设备以及存储介质
WO2021258972A1 (zh) 视频检索方法、装置、电子设备和计算机可读介质
WO2021031909A1 (zh) 数据内容的输出方法、装置、电子设备及计算机可读介质
CN114820060A (zh) 一种广告推荐方法、装置、设备及介质
CN112307260A (zh) 视频鉴别方法、装置、电子设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20855655

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20855655

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25/08/2022)