CN111277859B - Method and device for acquiring score, computer equipment and storage medium - Google Patents

Method and device for acquiring score, computer equipment and storage medium Download PDF

Info

Publication number
CN111277859B
CN111277859B CN202010042060.5A CN202010042060A CN111277859B CN 111277859 B CN111277859 B CN 111277859B CN 202010042060 A CN202010042060 A CN 202010042060A CN 111277859 B CN111277859 B CN 111277859B
Authority
CN
China
Prior art keywords
video
processed
music
target
data
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
Application number
CN202010042060.5A
Other languages
Chinese (zh)
Other versions
CN111277859A (en
Inventor
李达
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
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 Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202010042060.5A priority Critical patent/CN111277859B/en
Publication of CN111277859A publication Critical patent/CN111277859A/en
Application granted granted Critical
Publication of CN111277859B publication Critical patent/CN111277859B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/439—Processing of audio elementary streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/8106—Monomedia components thereof involving special audio data, e.g. different tracks for different languages
    • H04N21/8113—Monomedia components thereof involving special audio data, e.g. different tracks for different languages comprising music, e.g. song in MP3 format

Abstract

The application relates to a score obtaining method, a score obtaining device, computer equipment and a storage medium, wherein the method comprises the following steps: responding to a music matching request of a video to be processed, and performing frame extraction on the video to be processed to obtain a key frame picture of the video to be processed; identifying the key frame picture, and determining the video content characteristics of the video to be processed; and obtaining the recommended score of the video to be processed according to the video content characteristics. The scheme provided by the application can improve the relevance between the recommended score and the video content to be processed, and is beneficial to a user to find out a proper score more quickly.

Description

Method and device for acquiring score, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for acquiring a score, a computer device, and a storage medium.
Background
With the development of the internet, short video application platforms are developed at the same time, users can upload and share own video works through the short video application platforms, and meanwhile, the users can also match corresponding music backgrounds for videos so as to enhance the interestingness and attraction of the videos.
In the related art, background music recommended for a user usually comes from a manually operated music library, manpower is consumed to collect current popular music and configure the current popular music to the music library, and for different videos uploaded by the user, the current popular music in the music library is recommended to the user, however, the current popular music is not necessarily matched with the videos uploaded by the user, and the recommended music and the videos lack correlation, so that the user needs to spend more time to select proper music.
Disclosure of Invention
Based on this, it is necessary to provide a score obtaining method, apparatus, computer device and storage medium for solving the technical problem in the related art that the lack of association between the recommended score and the video leads to the need for the user to spend more time selecting a suitable score.
A score acquisition method, the method comprising:
responding to a music matching request of a video to be processed, and performing frame extraction on the video to be processed to obtain a key frame picture of the video to be processed;
identifying the key frame picture, and determining the video content characteristics of the video to be processed;
and obtaining the recommended score of the video to be processed according to the video content characteristics.
A score acquisition apparatus, the apparatus comprising:
the frame extracting module is used for responding to a music matching request of a video to be processed and extracting frames of the video to be processed to obtain a key frame picture of the video to be processed;
the identification module is used for identifying the key frame picture and determining the video content characteristics of the video to be processed;
and the acquisition module is used for acquiring the recommended score of the video to be processed according to the video content characteristics.
A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of:
responding to a music matching request of a video to be processed, and performing frame extraction on the video to be processed to obtain a key frame picture of the video to be processed;
identifying the key frame picture, and determining the video content characteristics of the video to be processed;
and obtaining the recommended score of the video to be processed according to the video content characteristics.
A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
responding to a music matching request for acquiring a video to be processed;
according to the music matching request, performing frame extraction on the video to be processed to obtain a key frame picture of the video to be processed;
identifying the key frame picture, and determining the video content characteristics of the video to be processed; an associated music tag;
and obtaining the recommended score of the video to be processed according to the content characteristics of the music label video.
According to the method, the device, the computer equipment and the computer readable storage medium for acquiring the score, the key frame picture capable of reflecting the content of the video to be processed is obtained by extracting the frame of the video to be processed, the key frame picture is identified, the video content characteristic of the video to be processed is determined, and then the recommended score is acquired according to the video content characteristic. The video content characteristics obtained by identifying the key frame pictures are associated with the content of the video to be processed, so that the recommended score obtained according to the video content characteristics has a certain degree of association with the video to be processed, the fitness of the recommended score and the video to be processed is improved, and a user can find a proper score more quickly.
Drawings
FIG. 1 is a diagram of an application environment of a score acquisition method in one embodiment;
FIG. 2 is a schematic flow chart diagram illustrating a method for score acquisition in one embodiment;
FIG. 3 is a flowchart illustrating a step of performing frame extraction on a video to be processed to obtain a key frame picture of the video to be processed in one embodiment;
FIG. 4 is a flowchart illustrating a method for score acquisition in one embodiment;
FIG. 5 is a block diagram showing the structure of a score acquisition device according to an embodiment;
FIG. 6 is a block diagram of a computer device in one embodiment;
FIG. 7 is a block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Fig. 1 is an application environment diagram of the score acquisition method in one embodiment. As shown in fig. 1, the application environment relates to a terminal 110 and a server 120, and the terminal 110 and the server 120 are connected through a network. The user may access the video sharing platform through the terminal 110, and the server 120 may be a server where the video sharing platform is located. The terminal 110 or the server 120 may provide a recommended score for the video in response to a score request for the video. The terminal 110 may specifically be a desktop terminal or a mobile terminal, and the mobile terminal may specifically be at least one of a mobile phone, a tablet computer, a notebook computer, and the like. The server 120 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a score acquisition method is provided. The embodiment is mainly illustrated by applying the method to the terminal 110 or the server 120 in fig. 1. Referring to fig. 2, the score obtaining method specifically includes the following steps S202 to S206.
S202, responding to the music matching request of the video to be processed, and performing frame extraction on the video to be processed to obtain a key frame picture of the video to be processed.
The key frame picture refers to a picture captured from a video to be processed, and can reflect the related content of the video to be processed. The number of key frame pictures may be one or more.
In one embodiment, the pending video is obtained prior to responding to the soundtrack request for the pending video. Specifically, the terminal may obtain the video to be processed by shooting the video or selecting the local video, where the video to be processed may be an original complete video or a complete video synthesized from multiple videos, and the server may obtain the video to be processed from the terminal.
And S204, identifying the key frame picture, and determining the video content characteristics of the video to be processed.
The video content features are used for representing the related content of the video to be processed. For example, the video to be processed is a video about travel, and the video content features may include landscape features such as mountains, water, trees, flowers and the like or landmark features such as featured buildings and the like.
And S206, obtaining the recommended score of the video to be processed according to the video content characteristics.
According to the method for acquiring the score, the key frame picture capable of reflecting the content of the video to be processed is obtained by frame extraction of the video to be processed, the key frame picture is identified, the video content characteristic of the video to be processed is determined, and then the recommended score is acquired according to the video content characteristic. The video content characteristics obtained by identifying the key frame pictures are associated with the content of the video to be processed, so that the recommended score obtained according to the video content characteristics has a certain degree of association with the video to be processed, the fitness of the recommended score and the video to be processed is improved, and a user can find a proper score more quickly.
In an embodiment, as shown in fig. 3, the step of performing frame extraction on the video to be processed to obtain the key frame picture of the video to be processed may specifically include the following steps S302 to S306.
S302, determining the number of key frames to be extracted of the video to be processed based on the time length of the video to be processed.
In one embodiment, the corresponding relationship between the duration range of the video and the number of the key frames to be extracted can be preset. For example, the following correspondence may be set: the video duration is within 15s (less than or equal to 15s), represented by (0, 15), the corresponding number of key frames to be extracted is 3, the video duration is between 15s and 30s (greater than 15s and less than or equal to 30s), represented by (15, 30), the corresponding number of key frames to be extracted is 5, and when the video duration is between 30s and 60s (greater than 30s and less than or equal to 60s), represented by (30, 60), the corresponding number of key frames to be extracted is 8.
After the video to be processed is obtained, the preset duration range where the duration is located can be determined according to the duration of the video to be processed, and then the number of the key frames to be extracted, which is the number of the key frames to be extracted of the video to be processed and corresponds to the preset duration range where the duration of the video to be processed is located, is obtained according to the preset duration range where the duration of the video to be processed is located and the corresponding relation. For example, if the duration of the video to be processed is 14s, and the duration is within the preset duration range (0, 15), the corresponding number of keyframes to be extracted is 3.
S304, extracting frames of the video to be processed according to the time length of the video to be processed and the number of the key frames to be extracted.
Specifically, the extraction time interval may be determined according to the duration of the video to be processed and the number of the key frames to be extracted, and then the frame extraction may be performed on the video to be processed once every extraction time interval to obtain the corresponding number of key frames.
In one embodiment, the decimation time interval may be determined by the ratio of the duration of the video to be processed to the number of key frames to be decimated.
For example, if the duration of the video to be processed is 15s, and the number of corresponding key frames to be extracted is 3, the extraction time interval obtained by calculation is 5s, so that the frames of the video to be processed are extracted once every 5s, that is, the extracted three key frames respectively correspond to the pictures of the 5s, the 10s and the 15s in the video to be processed.
It can be understood that if the extracted key frames are too close to each other (for example, pictures of 5s, 6 s and 7 s are extracted), the three frames contain the content of the same local time segment in the video, and the content of the video cannot be fully reflected; if the extracted key frames are too far apart (for example, pictures of 1s, 8s and 15s are extracted), the missing video content between two adjacent frames in the three frames is too much, and the video content cannot be fully reflected. Based on this, in this embodiment, the extraction time interval is determined according to the ratio of the duration of the video to be processed to the number of the key frames to be extracted, and then the frames of the video to be processed are extracted at equal time intervals, so that omission of important content of the video is effectively reduced, the extracted key frame pictures can contain richer video information, and the video content can be reflected more comprehensively.
In an embodiment, before the extraction time interval is determined, the leader or the trailer of the video to be processed may be cut to obtain the cut video to be processed, and then the extraction time interval is determined by calculating the ratio of the duration of the cut video to be processed to the number of the key frames to be extracted.
For example, if the duration of the video to be processed is 15s, and the number of the corresponding key frames to be extracted is 3, the header and the trailer of the video to be processed are cut first, for convenience of subsequent calculation, it is assumed that 1s of the header and 2s of the trailer are cut, the duration of the cut video to be processed is 12s, and the extraction time interval obtained by calculation is 4s, so that the cut video to be processed is subjected to frame extraction once every 4s, that is, the extracted three key frames respectively correspond to the pictures of the 4 th s, the 8 th s and the 12 th s in the cut video to be processed, that is, the pictures respectively correspond to the 5 th s, the 9 th s and the 13 th s in the original video to be processed.
Based on the fact that the leader or the trailer of the video may contain some information unrelated to the video content itself, in this embodiment, before the extraction time interval is determined, the leader or the trailer of the video to be processed is cut first, and then the cut video is subjected to frame extraction, so that the extracted key frame picture can contain information more related to the video content, and thus the video content can be reflected more accurately.
And S306, carrying out image processing on the extracted key frame according to the configuration parameters to obtain a key frame picture of the video to be processed.
The configuration parameters may include, among other things, picture size, resolution, and compression rate of the key frames. And after the original key frame picture is obtained by frame extraction, the original key frame picture is adjusted according to the configured size and resolution, and then the adjusted key frame picture is compressed according to the configured compression rate, so that the final key frame picture used for being identified is obtained.
In one embodiment, the configuration parameters are obtained prior to image processing of the extracted keyframes according to the configuration parameters. Specifically, the configuration parameters may be set by the server, the terminal may obtain the configuration parameters from the server or from the local cache, and the configuration parameters of the local cache of the terminal may be the configuration parameters obtained from the server and cached to the local, or may be a configuration parameter saved by default in the local.
In an embodiment, the step of identifying the key frame picture and determining the video content characteristics of the video to be processed may specifically include the following steps: extracting the characteristics of the key frame picture to obtain the target characteristics of the key frame picture; and determining the video content characteristics of the video to be processed according to the target characteristics of the key frame pictures.
Specifically, each key frame picture may include related information such as people, objects, scenes, and the like, and accordingly may include a plurality of target features, and the video content features of the video to be processed are determined according to all the target features of all the key frame pictures.
In one embodiment, all target features of all key frame pictures can be used as video content features of the video to be processed. For example, three key frame pictures are extracted from the video to be processed, wherein the first picture comprises four target features of mountain, water, tree and flower, the second picture comprises three target features of mountain, water and tree, and the third picture comprises three target features of mountain, flower and car, and then the five target features of mountain, water, tree, flower and car are used as the video content features of the video to be processed.
Based on the fact that the target features included in each key frame picture correspond to related content in the video to be processed, in this embodiment, all the target features of all the key frame pictures are used as video content features of the video to be processed and then used as a basis for subsequently acquiring recommended score, and therefore the association degree between the recommended score and the video content can be improved.
In an embodiment, a part of the target features may also be selected from all the target features of all the key frame pictures as video content features of the video to be processed, and the weight of the selected target features in all the target features is greater than or equal to a threshold. Wherein the threshold value may be set based on actual needs or experience. For example, three key frame pictures are extracted from the video to be processed, wherein the first picture comprises four target features of mountain, water, tree and flower, the second picture comprises three target features of mountain, water and tree, the third picture comprises three target features of mountain, flower and car, that is, the three pictures totally contain five target features of mountain, water, tree, flower and car, the weight of each target feature can be obtained by respectively calculating the ratio of the occurrence frequency of each target feature to the occurrence frequency of all target features, the weights of the five target features of mountain, water, tree, flower and car calculated according to the weight are respectively 0.3, 0.2, 0.2, 0.2 and 0.1, if the threshold value is set to be 0.1, the weights of the four target features of mountain, water, tree and flower are larger than the threshold value, therefore, the four target characteristics of the mountain, the water, the tree and the flower are used as the video content characteristics of the video to be processed.
It can be understood that when the weight of a target feature is very low, it indicates that the target feature may not be important content in the video to be processed, and based on this, in this embodiment, the target feature whose weight is smaller than the threshold is eliminated, so as to reduce interference of the unimportant target feature on subsequently acquired recommended score, and improve the fitness of the recommended score and the video.
In an embodiment, the step of obtaining the recommended score of the video to be processed according to the video content characteristics may specifically include the following steps: mapping the video content characteristics to obtain music labels corresponding to the video content characteristics; and acquiring the recommended score of the video to be processed according to the music label.
Specifically, each video content feature may be mapped to one music tag, and all music tags corresponding to all video content features may be used as music tags associated with the to-be-processed video content, so that the recommended score obtained according to the music tags associated with the to-be-processed video content has a relatively high association degree with the to-be-processed video.
In an embodiment, the step of obtaining the recommended score of the video to be processed according to the music tag may specifically include the following steps: searching in a third party music source according to the music label to obtain target music hit by the music label; and determining the recommended score of the video to be processed according to the target music.
Specifically, each music tag may be used as a keyword to search in a third-party music source, and the searched music is the target music hit by the music tag. The recommended score determined according to the target music hit by all the music labels has relatively high association with the video to be processed.
In an embodiment, the step of determining the recommended score of the video to be processed according to the target music may specifically include the following steps: sequencing the target music based on the hit times of each target music; and sequentially selecting a preset number of target music from the sequenced target music according to the sequence of the hit times from high to low to serve as the recommended score of the video to be processed.
For example, there are four music tags (denoted by a, b, c, and d, respectively) associated with the video content to be processed, where, assuming that tag a hits five pieces of music (s1, s2, s3, s4, and s5, respectively), tag b hits five pieces of music (s1, s2, s3, s6, and s7, respectively), tag c hits five pieces of music (s1, s2, s4, s8, and s9, respectively), and tag d hits five pieces of music (s1, s3, s4, s5, and s10, respectively), all pieces of music hit by the four tags, that is, target pieces of music include ten pieces (s1 to s10, respectively), and the target pieces of music are arranged in order from high to low in the number of hits, and the ordered target pieces of music are as follows: s1, s2, s3, s4, s5, s6, s7, s8, s9 and s10, if the preset number is 5, the top five target music (s1, s2, s3, s4 and s5) are selected as the recommended score of the video to be processed.
It can be understood that, when the weight of a target music in all the target music is higher, it indicates that the association degree between the target music and the video content to be processed is higher, and correspondingly, when the weight of a target music in all the target music is lower, it indicates that the association degree between the target music and the video content to be processed is lower.
In one embodiment, after providing the recommended score to the user, the method may further include the following steps: acquiring operation behavior data aiming at the recommended score, and determining a recommendation effect index of the recommended score according to the operation behavior data; and adjusting configuration parameters according to the recommendation effect index.
The operation behavior data may include any one or more of browsing data, clicking data, listening duration data, and publishing data. The recommendation effect index is used to represent recommendation accuracy for recommending the score, and may indicate that the recommendation accuracy is high when the recommendation effect index is greater than or equal to a preset value, and indicate that the recommendation accuracy is low when the recommendation effect index is less than the preset value, so as to adjust the configuration parameters, for example, improve resolution of the key frame picture to improve picture recognition rate, and finally improve score recommendation effect.
Specifically, the recommended score can be displayed on the terminal so that the user can operate the recommended score, browsing data is obtained by monitoring exposure data of the recommended score, click data is obtained by monitoring the number of times the recommended score is clicked by the user, audition duration data is obtained by monitoring the stay duration after the user clicks the recommended score, and release data is obtained by monitoring whether the user adopts the recommended score as the score release of the video.
In one embodiment, the recommendation effectiveness index may be expressed as a ratio of post data to click data. For example, ten recommended music pieces exist, in the first case, the recommendation effect index is 0.1 assuming that each recommended music piece is clicked by the user and one of the recommended music pieces is selected as the video music distribution, and in the second case, the recommendation effect index is 0.2 assuming that five recommended music pieces are clicked by the user and one of the recommended music pieces is selected as the video music distribution. In this embodiment, the recommendation effect index obtained in the second case is higher, and it can be understood that, compared with the first case, the click operation required by the user to find a suitable score in the second case is less, that is, the time taken is less, so the recommendation effect is relatively better.
In one embodiment, the recommendation effectiveness index may be expressed as a ratio of the published data to the viewed data. For example, there are ten recommended scores, the number of scores displayable on the current page of the terminal is five, and the user browses other recommended scores not displayed on the current page by sliding the screen left and right or up and down, in the first case, it is assumed that the user does not browse the other five recommended scores not displayed on the current page, and selects one of the five currently displayed recommended scores as a video score release, the recommendation effect index is 0.2, in the second case, it is assumed that the user browses the other five recommended scores not displayed on the current page, and selects one of the five recommended scores as a video score release, the recommendation effect index is 0.1. In this embodiment, the index of the recommendation effect obtained in the first case is higher, and it can be understood that, compared with the second case, the number of recommended matches that need to be browsed when the user finds a suitable match in the first case is smaller, that is, the time taken is shorter, so the recommendation effect is relatively better.
It is understood that in other embodiments, the recommendation effectiveness index may also be represented by other relationships between user operation data, such as a ratio of click data to browsing data, or a ratio of listening duration data to click data. In addition, the above ratios can be considered comprehensively, for example, the ratios are weighted by using a certain weighting ratio, and finally obtained data is used as a recommendation effect index.
In one embodiment, the configuration parameters may further include an intelligent switch state, and if the intelligent switch state is an on state, the recommended score of the video to be processed is obtained by using the methods of the above embodiments in response to the score request of the video to be processed; and if the intelligent switch is in the closed state, responding to the music matching request of the video to be processed, and acquiring the current popular music from the music matching library as the recommended music of the video to be processed.
As shown in fig. 4, in an embodiment, a method for acquiring a score is provided, which specifically includes the following steps S401 to S412.
S401, obtaining configuration parameters, wherein the configuration parameters comprise intelligent switch states and picture sizes, resolutions and compression rates of key frames.
S402, receiving a music matching request of the video to be processed.
S403, monitoring the state of the intelligent switch, and if the state of the intelligent switch is on, going to step S404 to step S412, and if the state of the intelligent switch is off, going to step S413.
S404, determining the number of key frames to be extracted of the video to be processed based on the time length of the video to be processed.
S405, extracting frames of the video to be processed according to the time length of the video to be processed and the number of the key frames to be extracted.
And S406, performing image processing on the extracted key frame according to the configuration parameters to obtain a key frame picture of the video to be processed.
And S407, extracting the characteristics of the key frame picture to obtain the target characteristics of the key frame picture.
And S408, determining the video content characteristics of the video to be processed according to the target characteristics of the key frame picture.
And S409, mapping the video content characteristics to obtain a music label corresponding to the video content characteristics.
And S410, searching in a third-party music source according to the music labels to obtain target music hit by the music labels.
S411, the target music is sorted based on the hit frequency of each target music.
And S412, sequentially selecting a preset number of target music from the sequenced target music according to the sequence of the hit times from high to low, and taking the target music as the recommended score of the video to be processed.
And S413, acquiring the current popular score from the score library as the recommended score of the video to be processed.
In the embodiment, when the intelligent switch is turned on, the key frame picture of the video to be processed is obtained by frame extraction, and the video content feature associated with the content of the video to be processed is obtained by identifying the key frame picture, so that the recommended score obtained according to the video content feature has a certain degree of association with the video to be processed, the fitting degree of the recommended score and the video to be processed is improved, a user can find a proper score more quickly, and the manual operation cost of a score library can be reduced.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
As shown in fig. 5, in one embodiment, there is provided a score acquisition apparatus 500 including: a framing module 510, an identification module 520, and an acquisition module 530.
The frame extracting module 510 is configured to respond to a music matching request of a video to be processed, and perform frame extraction on the video to be processed to obtain a key frame picture of the video to be processed.
The identifying module 520 is configured to identify the key frame picture and determine a video content characteristic of the video to be processed.
An obtaining module 530, configured to obtain, according to the video content feature, a recommended score of the to-be-processed video.
In one embodiment, the frame decimation module 510 includes: the device comprises a quantity determining unit, an extracting unit and a processing unit. And the quantity determining unit is used for determining the quantity of the key frames to be extracted of the video to be processed based on the time length of the video to be processed. And the extraction unit is used for extracting frames of the video to be processed according to the time length of the video to be processed and the number of the key frames to be extracted. And the processing unit is used for carrying out image processing on the extracted key frames according to the configuration parameters to obtain key frame pictures of the video to be processed.
In one embodiment, the identification module 520 includes: a feature extraction unit and a feature determination unit. And the feature extraction unit is used for extracting features of the key frame picture to obtain target features of the key frame picture. And the characteristic determining unit is used for determining the video content characteristics of the video to be processed according to the target characteristics of the key frame picture.
In one embodiment, the obtaining module 530 includes: a mapping unit and an acquisition unit. And the mapping unit is used for mapping the video content characteristics to obtain the music labels corresponding to the video content characteristics. And the acquisition unit is used for acquiring the recommended score of the video to be processed according to the music label.
In an embodiment, the obtaining unit, when obtaining the recommended score of the video to be processed according to the music tag, is specifically configured to: searching in a third party music source according to the music label to obtain target music hit by the music label; and determining the recommended score of the video to be processed according to the target music.
In an embodiment, when determining the recommended score of the video to be processed according to the target music, the obtaining unit is specifically configured to: sequencing the target music based on the hit times of each target music; and sequentially selecting a preset number of target music from the sequenced target music according to the sequence of the hit times from high to low to serve as the recommended score of the video to be processed.
In one embodiment, the score acquisition device 500 further includes: the adjusting module is used for acquiring operation behavior data aiming at the recommended score, determining a recommendation effect index of the recommended score according to the operation behavior data, and adjusting configuration parameters according to the recommendation effect index.
For specific limitations of the score obtaining device, reference may be made to the above limitations of the score obtaining method, which are not described herein again. The modules in the score acquiring device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
FIG. 6 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be the terminal 110 in fig. 1. As shown in fig. 6, the computer apparatus includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the score acquisition method. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the soundtrack acquisition method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
FIG. 7 is a diagram illustrating an internal structure of a computer device in one embodiment. The computer device may specifically be the server 120 in fig. 1. As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the score acquisition method. The internal memory may also have a computer program stored therein, which when executed by the processor, causes the processor to perform the soundtrack acquisition method.
Those skilled in the art will appreciate that the configurations shown in fig. 6 or 7 are merely block diagrams of some configurations relevant to the present disclosure, and do not constitute a limitation on the computing devices to which the present disclosure may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the score acquiring apparatus provided in the present application may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in fig. 6 or fig. 7. The memory of the computer device may store various program modules constituting the score acquisition apparatus, such as the frame extracting module, the identifying module, and the acquiring module shown in fig. 5. The computer program constituted by the respective program modules causes the processor to execute the steps in the score acquisition method of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 6 or fig. 7 may execute step S202 by a frame extracting module in the score acquisition apparatus shown in fig. 5. The computer device may perform step S204 through the identification module. The computer device may perform step S206 through the acquisition module.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the score acquisition method described above. Here, the steps of the score acquisition method may be the steps in the score acquisition methods of the respective embodiments described above.
In one embodiment, a computer-readable storage medium is provided, in which a computer program is stored, which, when executed by a processor, causes the processor to carry out the steps of the above-mentioned score acquisition method. Here, the steps of the score acquisition method may be the steps in the score acquisition methods of the respective embodiments described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (20)

1. A score acquisition method, comprising:
responding to a music matching request of a video to be processed, extracting frames of the video to be processed, and performing image processing on the extracted key frames according to configuration parameters to obtain key frame pictures of the video to be processed;
identifying the key frame picture, and determining the video content characteristics of the video to be processed;
obtaining the recommended score of the video to be processed according to the video content characteristics;
obtaining operation behavior data aiming at the recommended score, determining a recommendation effect index of the recommended score according to the operation behavior data, and adjusting the configuration parameters according to the recommendation effect index.
2. The method of claim 1, wherein the decimating the video to be processed comprises:
determining the number of key frames to be extracted of the video to be processed based on the duration of the video to be processed;
and extracting frames of the video to be processed according to the duration of the video to be processed and the number of the key frames to be extracted.
3. The method according to claim 1, wherein identifying the key frame picture and determining the video content characteristics of the video to be processed comprises:
extracting the characteristics of the key frame picture to obtain the target characteristics of the key frame picture;
and determining the video content characteristics of the video to be processed according to the target characteristics of the key frame pictures.
4. The method according to claim 3, wherein determining the video content feature of the video to be processed according to the target feature of the key frame picture comprises:
and taking all target characteristics of all key frame pictures as video content characteristics of the video to be processed.
5. The method according to claim 3, wherein determining the video content feature of the video to be processed according to the target feature of the key frame picture comprises:
and determining the weight of each target feature in all the target features, and selecting the target features with the weight greater than or equal to a threshold value as the video content features of the video to be processed.
6. The method according to claim 1, wherein obtaining the recommended score of the video to be processed according to the video content features comprises:
mapping the video content characteristics to obtain music labels corresponding to the video content characteristics;
and acquiring the recommended score of the video to be processed according to the music label.
7. The method of claim 6, wherein obtaining the recommended score for the video to be processed according to the music tag comprises:
searching in a third-party music source according to the music label to obtain target music hit by the music label;
and determining the recommended score of the video to be processed according to the target music.
8. The method of claim 7, wherein determining the recommended score for the video to be processed based on the target music comprises:
ranking the target music based on the hit times of each target music;
and sequentially selecting a preset number of target music from the sequenced target music according to the sequence of the hit times from high to low to serve as the recommended score of the video to be processed.
9. The method according to claim 1, wherein the operation behavior data comprises any one or more of browsing data, clicking data, listening trial duration data and publishing data;
the recommendation effect index comprises one or more of a ratio of the release data to the click data, a ratio of the release data to the browsing data, a ratio of the click data to the browsing data, and a ratio of the listening trial duration data to the click data.
10. An apparatus for acquiring a score, the apparatus comprising:
the frame extracting module is used for responding to a music matching request of a video to be processed, extracting frames of the video to be processed, and performing image processing on the extracted key frames according to configuration parameters to obtain key frame pictures of the video to be processed;
the identification module is used for identifying the key frame picture and determining the video content characteristics of the video to be processed;
the acquisition module is used for acquiring the recommended score of the video to be processed according to the video content characteristics;
the adjusting module is used for acquiring operation behavior data aiming at the recommended score, determining a recommendation effect index of the recommended score according to the operation behavior data, and adjusting the configuration parameters according to the recommendation effect index.
11. The apparatus according to claim 10, wherein the frame extracting module, when extracting the frame of the video to be processed, is specifically configured to: determining the number of key frames to be extracted of the video to be processed based on the duration of the video to be processed; and extracting frames of the video to be processed according to the duration of the video to be processed and the number of the key frames to be extracted.
12. The apparatus of claim 10, wherein the identification module comprises:
the feature extraction unit is used for extracting features of the key frame pictures to obtain target features of the key frame pictures;
and the characteristic determining unit is used for determining the video content characteristics of the video to be processed according to the target characteristics of the key frame picture.
13. The apparatus according to claim 12, wherein the feature determination unit is specifically configured to: and taking all target characteristics of all key frame pictures as video content characteristics of the video to be processed.
14. The apparatus according to claim 12, wherein the feature determination unit is specifically configured to: and determining the weight of each target feature in all the target features, and selecting the target features with the weight greater than or equal to a threshold value as the video content features of the video to be processed.
15. The apparatus of claim 10, wherein the obtaining module comprises:
the mapping unit is used for mapping the video content characteristics to obtain music labels corresponding to the video content characteristics;
and the acquisition unit is used for acquiring the recommended score of the video to be processed according to the music label.
16. The apparatus according to claim 15, wherein the obtaining unit, when obtaining the recommended score of the to-be-processed video according to the music tag, is specifically configured to: searching in a third-party music source according to the music label to obtain target music hit by the music label; and determining the recommended score of the video to be processed according to the target music.
17. The apparatus according to claim 16, wherein the obtaining unit, when determining the recommended score of the video to be processed according to the target music, is specifically configured to: sequencing the target music based on the hit times of each target music; and sequentially selecting a preset number of target music from the sequenced target music according to the sequence of the hit times from high to low to serve as the recommended score of the video to be processed.
18. The device according to claim 10, wherein the operation behavior data includes any one or more of browsing data, clicking data, listening duration data and publishing data;
the recommendation effect index comprises one or more of a ratio of the release data to the click data, a ratio of the release data to the browsing data, a ratio of the click data to the browsing data, and a ratio of the listening trial duration data to the click data.
19. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 9.
20. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 9.
CN202010042060.5A 2020-01-15 2020-01-15 Method and device for acquiring score, computer equipment and storage medium Active CN111277859B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010042060.5A CN111277859B (en) 2020-01-15 2020-01-15 Method and device for acquiring score, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010042060.5A CN111277859B (en) 2020-01-15 2020-01-15 Method and device for acquiring score, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111277859A CN111277859A (en) 2020-06-12
CN111277859B true CN111277859B (en) 2021-12-14

Family

ID=71000305

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010042060.5A Active CN111277859B (en) 2020-01-15 2020-01-15 Method and device for acquiring score, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111277859B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114637867A (en) * 2022-05-18 2022-06-17 合肥的卢深视科技有限公司 Video special effect configuration method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4963269B2 (en) * 2007-06-29 2012-06-27 株式会社第一興商 Image-compatible music recommendation presentation system
WO2012070880A3 (en) * 2010-11-25 2012-10-04 Samsung Electronics Co., Ltd. Content-providing method and system
CN106548364A (en) * 2016-09-27 2017-03-29 腾讯科技（北京）有限公司 Method for sending information and device
CN107391692A (en) * 2017-07-26 2017-11-24 腾讯科技（北京）有限公司 The appraisal procedure and device of a kind of recommendation effect
CN108093314A (en) * 2017-12-19 2018-05-29 北京奇艺世纪科技有限公司 A kind of news-video method for splitting and device
CN109587554A (en) * 2018-10-29 2019-04-05 百度在线网络技术（北京）有限公司 Processing method, device and the readable storage medium storing program for executing of video data

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103152621B (en) * 2013-02-27 2016-03-23 四三九九网络股份有限公司 Recommend the collocation method of video, display packing and player method
CN105912650B (en) * 2016-04-07 2021-08-24 腾讯科技（深圳）有限公司 Method and device for recommending songs
US20190394511A1 (en) * 2018-06-21 2019-12-26 Wells Fargo Bank, N.A. Systems and methods for generating and presenting content-based summaries and recommendations
CN110647651A (en) * 2019-09-19 2020-01-03 曹玲 Expression recognition music recommendation system based on convolutional neural network

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4963269B2 (en) * 2007-06-29 2012-06-27 株式会社第一興商 Image-compatible music recommendation presentation system
WO2012070880A3 (en) * 2010-11-25 2012-10-04 Samsung Electronics Co., Ltd. Content-providing method and system
CN106548364A (en) * 2016-09-27 2017-03-29 腾讯科技（北京）有限公司 Method for sending information and device
CN107391692A (en) * 2017-07-26 2017-11-24 腾讯科技（北京）有限公司 The appraisal procedure and device of a kind of recommendation effect
CN108093314A (en) * 2017-12-19 2018-05-29 北京奇艺世纪科技有限公司 A kind of news-video method for splitting and device
CN109587554A (en) * 2018-10-29 2019-04-05 百度在线网络技术（北京）有限公司 Processing method, device and the readable storage medium storing program for executing of video data

Also Published As

Publication number Publication date
CN111277859A (en) 2020-06-12

Similar Documents

Publication Publication Date Title
WO2022022152A1 (en) Video clip positioning method and apparatus, and computer device and storage medium
CN111062871B (en) Image processing method and device, computer equipment and readable storage medium
CN110458107B (en) Method and device for image recognition
CN112330685B (en) Image segmentation model training method, image segmentation device and electronic equipment
CN109871490B (en) Media resource matching method and device, storage medium and computer equipment
KR102222087B1 (en) Image recognition method and apparatus based on augmented reality
CN116881501A (en) Providing relevant video scenes in response to a video search query
CN112101169B (en) Attention mechanism-based road image target detection method and related equipment
WO2008129383A1 (en) Method, apparatus and computer program product for determining relevance and/or ambiguity in a search system
CN113496208B (en) Video scene classification method and device, storage medium and terminal
CN112328823A (en) Training method and device for multi-label classification model, electronic equipment and storage medium
CN104520848A (en) Searching for events by attendants
CN112000871A (en) Method, device and equipment for determining search result list and storage medium
CN111277761A (en) Video shooting method, device and system, electronic equipment and storage medium
CN111860313A (en) Information query method and device based on face recognition, computer equipment and medium
CN111277859B (en) Method and device for acquiring score, computer equipment and storage medium
WO2021196551A1 (en) Image retrieval method and apparatus, computer device, and storage medium
CN112040273B (en) Video synthesis method and device
CN110162689A (en) Information-pushing method, device, computer equipment and storage medium
CN114595372A (en) Scene recommendation method and device, computer equipment and storage medium
US20150043833A1 (en) Image processing method and electronic device
CN110134815A (en) Image processing method, device, computer equipment and storage medium
CN111352680A (en) Information recommendation method and device
CN112765453A (en) Content recommendation method and device, computer equipment and storage medium
CN113821676A (en) Video retrieval method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40024319

Country of ref document: HK

GR01 Patent grant
GR01 Patent grant