TW201901492A - Video search method and device - Google Patents

Abstract

A method and apparatus for searching for a video. The method comprises: where a request to search for a video is received, acquiring a preliminary search result corresponding to the request to search for a video; calculating a score of each type of video data in the preliminary search result; sorting each type of video data according to the score of each type of video data to obtain a sorting result; and according to the sorting result, responding to the request to search for a video. The method can improve the accuracy and diversity of search results.

Description

Video search method and device

The present disclosure relates to the field of video technology, and in particular, to a video search method and device.

In the related art, when a server receives a video search request from a client, the server determines a search result according to a search term in the video search request, and responds to the client with the search result. This video search method usually only considers the similarity between the search term and the video title, resulting in lower accuracy and diversity of search results.

In view of this, the present disclosure proposes a video search method and device to improve the accuracy and diversity of search results.

According to an aspect of the present disclosure, a video search method is provided, including:

If a video search request is received, obtaining a preliminary search result corresponding to the video search request;

Calculating a score of each type of video data in the preliminary search result;

Sort each type of video data according to the score of each type of video data to get the sorted result;

Responding to the video search request according to the ranking result.

In a possible implementation manner, each type of video data includes at least one of the following: video, program, self-channel, and playlist.

In a possible implementation manner, calculating a score of each type of video data in the preliminary search result includes:

In the case where each type of video data includes a video, the score of the video is calculated according to at least one of the following: the correlation between the video and the video search request, the uploader of the video, and the video search request Relevance, user feedback information of the search user corresponding to the video search request, playback volume of the video, completion ratio of viewing of the video, release time of the video, number of times the video has been favorited, the The number of comments on the video, the number of barrage of the video, and the subscription status of the search user for the video.

In a possible implementation manner, calculating a score of each type of video data in the preliminary search result includes:

In the case where a program is included in each type of video data, the score of the program is calculated according to at least one of the following: the real-time search volume of the program, the playback volume of the program, the program and the video search request. Relevance, feedback information corresponding to the program, release time of the program, copyright status of the program, and site information of the program.

In a possible implementation manner, responding to the video search request according to the ranking result includes:

Adjusting the ranking of the programs in the ranking result according to the ranking of the programs in the ranking result and the total number of the programs;

Responding to the video search request according to the adjusted ranking result.

In a possible implementation manner, calculating a score of each type of video data in the preliminary search result includes:

In the case where each type of video data includes a self-channel, the score of the self-channel is calculated according to at least one of the following: the attribute of the channel master of the self-channel, the score of each video in the self-channel, the preliminary The number of videos belonging to the self-channel in the search results, the total number of videos of the self-channel, and the correlation between the video search request and the self-channel.

In a possible implementation manner, calculating a score of each type of video data in the preliminary search result includes:

In the case where each type of video data includes an order, the score of the order is calculated according to at least one of the following: the type of the order, the generation time of the order, and the feedback information corresponding to the order And the score of each video in the playlist.

According to another aspect of the present disclosure, a video search apparatus is provided, including:

An obtaining module, configured to obtain a preliminary search result corresponding to the video search request when a video search request is received;

A calculation module for calculating a score of each type of video data in the preliminary search result;

A sorting module is used to sort each type of video data according to the score of each type of video data to obtain a sorting result;

The response module is configured to respond to the video search request according to the ranking result.

In a possible implementation manner, each type of video data includes at least one of the following: video, program, self-channel, and playlist.

In a possible implementation manner, the computing module includes:

A first calculation sub-module, configured to calculate a score of the video according to at least one of the following when video is included in each type of video data: the correlation between the video and the video search request, the video Relevance of the uploader to the video search request, user feedback information of the search user corresponding to the video search request, playback volume of the video, completion ratio of the viewing of the video, release time of the video, The number of times the video has been favorited, the number of comments on the video, the number of barrage of the video, and the subscription status of the search user for the video.

In a possible implementation manner, the computing module includes:

The second calculation submodule is configured to calculate a score of the program according to at least one of the following when a program is included in each type of video data: a real-time search amount of the program, a play amount of the program, a The relevance of the program to the video search request, feedback information corresponding to the program, release time of the program, copyright status of the program, and site information of the program.

In a possible implementation manner, the response module includes:

An adjustment sub-module, configured to adjust the ranking of the programs in the ranking result according to the ranking of the programs in the ranking result and the total number of the programs;

The response sub-module is configured to respond to the video search request according to the adjusted ranking result.

In a possible implementation manner, the computing module includes:

A third calculation sub-module is used to calculate a score of the self-channel according to at least one of the following cases when the self-channel is included in each type of video data: the self-channel's attribute of the self-channel The score of each video in the video, the number of videos belonging to the self-channel in the preliminary search result, the total number of videos of the self-channel, and the correlation between the video search request and the self-channel.

In a possible implementation manner, the computing module includes:

The fourth calculation submodule is used to calculate the score of the playlist according to at least one of the following: if the playlist is included in each type of video data: the type of the playlist and the generation time of the playlist 2. The feedback information corresponding to the playlist and the score of each video in the playlist.

According to another aspect of the present disclosure, there is provided a video search apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the above method.

According to another aspect of the present disclosure, there is provided a non-volatile computer-readable storage medium having computer program instructions stored therein, wherein the computer program instructions implement the above method when executed by a processor.

By receiving the preliminary search result corresponding to the video search request when the video search request is received, calculating the score of each type of video data in the preliminary search result, and performing the analysis on each type of video data according to the score of each type of video data Sorting to obtain a sorting result and responding to a video search request according to the sorting result. The video search method and device according to various aspects of the present disclosure can improve the accuracy and diversity of search results.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Various exemplary embodiments, features, and aspects of the disclosure will be described in detail below with reference to the drawings. The same reference numerals in the drawings represent the same or similar elements. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless specifically noted.

The word "exemplary" as used herein means "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior to or better than other embodiments.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the detailed description below. Those skilled in the art should understand that the present disclosure can be implemented without certain specific details. In some examples, methods, means, components, and circuits that are well known to those skilled in the art have not been described in detail in order to highlight the gist of the present disclosure.

Example 1

FIG. 1 shows a flowchart of a video search method according to an embodiment of the present disclosure. This method can be applied to a server, which is not limited herein. As shown in FIG. 1, the method includes steps S11 to S14.

In step S11, when a video search request is received, a preliminary search result corresponding to the video search request is obtained.

In this embodiment, when the server receives a video search request from a client, the server may use a video search method in the related art to obtain a preliminary search result corresponding to the video search request. The video search request may carry a search term.

In step S12, the score of each type of video data in the preliminary search result is calculated.

In a possible implementation manner, each type of video data includes at least one of the following: video, program, self-channel, and playlist. Among them, video, program, self-channel and playbill can be obtained through different engines respectively.

It should be noted that although various types of video data are described above using videos, programs, self-channels, and broadcasts as examples, those skilled in the art can understand that the present disclosure should not be limited to this. Those skilled in the art can flexibly set various types of video data according to actual application scenarios.

In a possible implementation manner, in a case where each type of video data includes a video, a program, a self-channel, and a playlist, a score of each video may be calculated first, and then a score of each program, self-channel, and playlist is calculated. This can be used to calculate scores for individual shows, self-channels, and broadcasts based on the video's score.

In a possible implementation manner, the pre-sorted Q video data can be filtered from the preliminary search results according to the pre-sorting of each video data in the preliminary search results to obtain the screening results, and only the The score of each type of video data, and the sorting results are further sorted according to the score of each type of video data in the filtering result to reduce the calculation amount.

In a possible implementation manner, various models may be trained in advance, and these models may be used to calculate scores of various types of video data in the preliminary search results. For example, a method such as LambdaMART (Lambda Multiple Additive Regression Tree, Lambda Multiple Cumulative Regression Tree) or GBDT (Gradient Boosting Decision Tree) can be used to train a model for calculating the scores of various types of video data.

In step S13, the video data of each type is sorted according to the score of the video data of each type to obtain a sorting result.

As an example of this embodiment, the video data of each type can be sorted in order of high scores to obtain a sorting result.

In step S14, a video search request is responded according to the ranking result.

In a possible implementation manner, the final search result may be determined according to the first L video data ranked in the ranking result, and the final search result is responded to the video search request.

As an example of this implementation manner, different types of video data in the final search result can be displayed on the client in different display manners, thereby being able to reflect the diversity of video data in the final search result.

As an example of this implementation manner, the video data with high correlation with the video search request among the video data mined offline can be added to the final search result.

As an example of this implementation manner, in a case where there are consecutive P videos of the same type in the previous L video data sorted in the ranking result, other types of videos may be inserted into the consecutive P videos of the same type. To further increase the diversity of the final search results. The other types of videos inserted may also be videos sorted in the previous L video data to ensure a strong correlation between the final search result and the video search request. For example, if P is 10, and there are 12 consecutive types of movies in the previous L video data in the ranking result, you can insert other types (such as TV series, animation, or Games, etc.).

As an example of this implementation, in the case where there are consecutive G videos uploaded by the same uploader in the previous L video data sorted in the ranking result, other videos uploaded by the same G uploader may be inserted into other Videos uploaded by uploaders to further increase the diversity of the final search results. The videos uploaded by other uploaders may also be videos sorted in the previous L video data to ensure a strong correlation between the final search result and the video search request. For example, G is 6, and there are 8 videos uploaded by uploader A consecutively in the previous L video data in the sorting result. Then you can insert other uploaders (such as upload B) Uploaded videos.

As an example of this implementation manner, the final search results may also be adjusted according to the video playback rights of different regions and different platforms, which is not limited here.

The video search method provided in this embodiment can improve the accuracy and diversity of search results.

In a possible implementation manner, for different types of video data, different calculation methods may be used to calculate the scores of the video data of this type, thereby making the calculated scores of each type of video data more reasonable, and then making The sorted results obtained by the scores of video data of the type are more reasonable, can improve the accuracy and diversity of search results, and can better meet the search needs of search users, which can further improve the user experience.

In a possible implementation manner, calculating the scores of each type of video data in the preliminary search results may include: in the case where each type of video data includes a video, calculating the score of the video according to at least one of the following: video and video Relevance of search request, Relevance of video uploader and video search request, User feedback of search user corresponding to video search request, Video playback volume, Video completion ratio, Video release time, Video favorited Number of times, number of video comments, number of video barrage, and search user subscription status for the video.

The video in this implementation manner may include UGC (User Generated Content, user generated content, etc.), which is not limited herein.

As an example of this implementation, the score of the video may be determined at least based on the relevance of the video to the video search request. The correlation between the video and the video search request may be determined according to the similarity between the feature words of the video and the search words in the video search request. The feature words of the video may be determined according to at least one of a title, a subtitle, a type, a tag, and a keyword of the video. For example, the title and subtitle of the video may be segmented, and each word in the segmentation result and the type, label, and keyword of the video are used as feature words of the video, respectively. The similarity between the feature words of the video and the search terms can be determined according to the word vector of the feature words of the video, TF-IDF (Term Frequency-Inverse Document Frequency), and the word vector of search words, TF-IDF. This is not limited.

As an example of this implementation, the score of the video may be determined at least according to the relevance of the uploader of the video to the video search request. The relevance between the uploader of the video and the video search request may be determined according to the type of the uploader of the video and the search term in the video search request. The type of the uploader of the video may be determined according to the video uploaded by the uploader of the video. For example, if 98% of the videos uploaded by the uploader of a video are of a game-related type, it can be determined that the type of the uploader of the video is a game. If the type of the uploader of the video is a game, and the search term of the video search request includes a game, or the search term includes the name of a certain game, it can be determined that the uploader of the video has a high correlation with the video search request.

As an example of this implementation manner, the score of a video may be determined at least according to user feedback information of a search user corresponding to a video search request. The user feedback information of the search user may include search video information watched by the user in the first time range, completion ratio of each video, commented video information, posted video information of the barrage, favorite video information, and reposted At least one of video information, like video information, and the like. The first time range may be one week, one month, or six months, which is not limited herein. The search completion ratio of a search user for a video may be equal to the ratio of the length of time that the search user watches the video to the total length of the video. Based on the user feedback information of the search users, the search users' preferences for watching videos can be determined. For example, if it is determined that the search user likes watching a movie according to the user feedback information of the search user, and the video is a movie, the score of the video may be higher.

As an example of this implementation manner, the score of the video may be determined at least according to the playback volume of the video. For example, the score of a video may be determined according to the playback volume of the video in the second time range, and the score of the video may be positively related to the playback volume of the video in the second time range. The second time range may be one day, one week, or one month, which is not limited herein.

As an example of this implementation manner, the score of the video may be determined at least according to the viewing completion ratio of the video. The viewing completion ratio of a video may be equal to the average of the viewing completion ratios of all users for the video. The score of the video may be directly related to the completion ratio of the video.

As an example of this implementation, the score of the video may be determined at least according to the release time of the video. The score of the video may be negatively correlated with the first difference, where the first difference may be equal to the time difference between the current time and the publishing time of the video.

As an example of this implementation manner, the score of the video may be determined at least according to the number of times the video has been favorited. The score of the video can be positively related to the number of times the video has been favorited.

As an example of this implementation, the score of a video may be determined at least based on the number of comments on the video. The video's score can be positively related to the number of comments on the video.

As an example of this implementation, the score of the video may be determined at least according to the number of barrage of the video. The score of the video can be positively related to the number of barrage of the video.

As an example of this implementation, the score of the video may be determined at least according to the subscription status of the search user for the video. If the search user has subscribed to the video, the video's score can be higher.

As an example of this implementation, the score of the video can be calculated using Equation 1. :

Formula 1.

among them, Can represent the base score for all videos, It may be greater than 0, may be equal to 0 or less than 0, and is not limited herein. Those skilled in the art can flexibly set according to the actual application scenario . Represents the first Item score, The first Weighting of items, The total number of items representing the score of the video. For example, based on the relevance of the video to the video search request , Based on the relevance of the video uploader to the video search request , Determined according to the user feedback information of the search user corresponding to the video search request , Determined based on the video ’s playback volume and completion ratio , Based on when the video was posted , Based on the number of times the video has been favorited , Based on the number of comments on the video , Based on the number of video barrage , Based on search user ’s subscription status for the video It is not limited here.

It should be noted that despite the correlation between the video and the video search request, the correlation between the uploader of the video and the video search request, the user feedback information of the search user corresponding to the video search request, the video playback volume, and the video completion ratio , Video release time, number of videos favorited, number of video comments, number of video barrage, and search user ’s subscription status for the video. As an example, the method of calculating the video ’s score is described above, but those skilled in the art can understand that The present disclosure should not be limited to this. A person skilled in the art may flexibly set a method for calculating a score of a video according to an actual application scenario, as long as it is related to at least one of a video search request, a video, a video uploader, and a search user. For example, the score of a video can also be determined based on whether the video is a broadcast control video or a cheat video, etc., which is not limited here.

As an example of this implementation method, Equation 2 can be used to calculate :

Formula 2;

among them, Indicates the current time, Indicates when the video was posted, with Respective adjustment coefficients.

It should be noted that although the calculation is described using Equation 2 as an example The manner is as above, but those skilled in the art can understand that the present disclosure should not be limited to this. Those skilled in the art can flexibly set according to the actual application scenario , As long as it is related to the time of release of the video.

As an example of this implementation, Equation 3 can be used to calculate :

Formula 3;

among them, Indicates the completion ratio of the video, Represents the amount of video playback. Can represent the average play volume of all videos in the preliminary search results. Alternatively, you can , , , , , , And its corresponding weights, first calculate the M videos with the highest score in the preliminary search results, and then use the average playback volume of these M videos as . Among them, M may be 20, which is not limited herein.

It should be noted that although Equation 3 is introduced as an example, The calculation method is as above, but those skilled in the art can understand that the disclosure should not be limited to this. Those skilled in the art can flexibly set according to the actual application scenario , As long as it is related to the amount of video played and the completion ratio.

In a possible implementation manner, calculating the score of each type of video data in the preliminary search result may include: in the case where each type of video data includes a program, calculating the score of the program according to at least one of the following: the real-time of the program Search volume, program playback volume, correlation between the program and video search request, feedback information corresponding to the program, program release time, program copyright status, and program site information.

As an example of this implementation manner, the score of a program may be determined based on at least the real-time search volume of the program. The real-time search volume of the program may be the search volume of the program within the third time range. For example, the third time range may be one hour or one day, and the like is not limited herein. The program's score can be positively correlated with the program's real-time search volume.

As an example of this implementation manner, the score of the program may be determined at least according to the play volume of the program. The score of the program can be positively related to the volume of the program. For example, the score of the program may be positively related to the total play volume of the program. Alternatively, the score of the program may be positively related to the playback volume of the program in the fourth time range. The fourth time range may be one day, one week, or one month, and is not limited herein.

As an example of this implementation manner, the score of the program may be determined based at least on the relevance of the program to the video search request. The correlation between the program and the video search request may be determined according to the similarity between the feature words of the program and the search words in the video search request. The feature word of the program may be determined according to at least one of a name, a type, a tag, and a keyword of the program. For example, the name of the program may be segmented, and each word in the segmentation result and the type, label, and keyword of the program are used as feature words of the program, respectively. The similarity between the feature word of the program and the search word can be determined according to the word vector and TF-IDF of the feature word of the program and the word vector and TF-IDF of the search word, which is not limited herein.

As an example of this implementation manner, a score of a program may be determined at least according to feedback information corresponding to the program. For example, the feedback information corresponding to the program may include the average score of all users ’ratings of the program, and may also include the total number of comments on the program by all users, which is not limited herein.

As an example of this implementation manner, a score of a program may be determined at least according to a release time of the program. The score of the program may be negatively correlated with a second difference value, where the second difference value may be equal to the time difference between the current time and a specified time of the program. The specified time of the program may be the release time of the latest video of the program or the average release time of all videos of the program, which is not limited herein.

As an example of the implementation, the score of the program may be determined at least according to the copyright status of the program. For example, if the copyright status of the program is that the site has the copyright of the program, the score of the program can be higher.

As an example of this implementation manner, a score of a program may be determined based on at least site information of the program. For example, if the site information of the program is this site, the score of the program can be higher.

As an example of this implementation, the score of the program can be calculated using Equation 4:

Equation 4.

among them, Can represent the base score for all shows, It may be greater than 0, may be equal to 0 or less than 0, and is not limited herein. Those skilled in the art can flexibly set according to the actual application scenario . Indicate the first Item score, The first Weighting of items, The total number of items representing the score of the show. For example, it can be determined based on the real-time search volume of the program , The value range of can be [0,1], which is determined according to the program's play volume , Based on the relevance of the show to the video search request , The value range can be [-1,1], which is determined according to the feedback information corresponding to the program. , Determined based on the program ’s release time, the program ’s copyright status, and the program ’s site information , The value range of can be [-1,1], which is not limited here.

It should be noted that although the real-time search volume of the program, the playback volume of the program, the correlation between the program and the video search request, the feedback information corresponding to the program, the release time of the program, the copyright status of the program, and the site information of the program are taken as examples The calculation method of the score of the program is introduced as above, but those skilled in the art can understand that the present disclosure should not be limited to this. A person skilled in the art may flexibly set a calculation method of a score of a program according to an actual application scenario, as long as it is related to at least one of a program and a video search request.

FIG. 2 illustrates an exemplary flowchart of step S14 of a video search method according to an embodiment of the present disclosure. As shown in FIG. 2, step S14 may include steps S141 and S142.

In step S141, the ranking of the programs in the ranking result is adjusted according to the ranking of the programs in the ranking result and the total number of the programs.

As an example of this embodiment, when the copyright status of the program is that the site has the copyright of the program, the ranking of the programs in the ranking result may be adjusted according to the ranking of the programs in the ranking result and the total number of the programs. Based on this example, you can protect the copyrighted programs on this site.

As an example of this embodiment, Equation 6 can be used to determine the lowest ranking of the program in the ranking result. :

Equation 7.

among them, Represents the adjustment factor, Can indicate the ranking of the show among all the shows in the ranking result, Represents the total number of shows in the preliminary search results.

E.g, Is equal to 5, Equals 3, Equal to 7, you can calculate Equals 3, Equal to 18, that is, the lowest ranking of the program in the ranking result is 18. If the current ranking of the program in the ranking result is lower than 18, the ranking of the program in the ranking result is adjusted to 18.

In step S142, a video search request is responded according to the adjusted ranking result.

In a possible implementation manner, calculating the scores of each type of video data in the preliminary search result may include: in a case where each type of video data includes a self-channel, the score of the self-channel is calculated according to at least one of the following: The attributes of the channel's channel master, the score of each video in the self-channel, the number of videos belonging to the self-channel in the preliminary search results, the total number of videos in the self-channel, and the correlation between video search requests and the self-channel.

As an example of this implementation manner, the score of the self-channel can be determined at least according to the attribute of the channel owner of the self-channel. The attribute of the channel owner of the self-channel may include the number of fans of the channel owner, etc., which is not limited herein. For example, a self-channel's score may be positively related to the number of followers of the self-channel's channel owner.

As an example of this implementation manner, the score of the self-channel may be determined at least according to the score of each video in the self-channel. For example, the score of a self-channel can be positively related to the average score of each video in the self-channel.

As an example of this implementation manner, the score of the self-channel can be determined at least according to the number of videos belonging to the self-channel and the total number of videos of the self-channel in the preliminary search result. For example, the score of the self-channel may be positively related to the ratio of the number of videos belonging to the self-channel to the total number of videos of the self-channel in the preliminary search results. For example, if the number of videos belonging to a certain self channel in the preliminary search results is 10 and the total number of videos of the self channel is 100, the score of the self channel can be compared with the number of videos belonging to the self channel in the preliminary search results and the self channel The total number of videos is 0.1.

As an example of this implementation, the score of the self-channel can be determined at least according to the correlation between the video search request and the self-channel. The correlation between the self-channel and the video search request may be determined according to the similarity between the feature words of the self-channel and the search words in the video search request. The feature words of the self-channel can be determined according to at least one of a title, a subtitle, a genre, a tag, and a keyword of each video in the self-channel. For example, the title and subtitle of each video in the self-channel can be segmented, and each word in the segmentation result and the type, label, and keyword of each video are used as feature words of the self-channel. The similarity between the feature word of the self-channel and the search word can be determined according to the word vector of the feature word of the self-channel, TF-IDF, and the word vector of the search word, TF-IDF, which is not limited herein.

As an example of this implementation, the score from the channel can be calculated using Equation 5. :

Equation 5.

among them, Can represent the base score for all self-channels, It may be greater than 0, may be equal to 0 or less than 0, and is not limited herein. Those skilled in the art can flexibly set according to the actual application scenario . Represents the first Item score, The first Weighting of items, The total number of items representing the score from the channel. For example, it can be determined based on the attributes of the channel owner from the channel , Based on the score of each video in the channel , Based on the ratio of the number of videos belonging to the own channel to the total number of videos from the own channel in the preliminary search results , Determined based on the relevance of the video search request to its own channel It is not limited here. among them, The value range can be , The value range can be .

In a possible implementation manner, calculating the scores of each type of video data in the preliminary search results may include: in the case where each type of video data includes a play order, calculating the score of the play order according to at least one of the following: The type of the order, the generation time of the order, the feedback information corresponding to the order, and the score of each video in the order.

As an example of this implementation manner, the score of the broadcast order may be determined at least according to the type of the broadcast order. For example, the type of the broadcast order may include the official type and the broadcast control type, and the score corresponding to the official type may be higher than the score corresponding to the broadcast control type.

As an example of this implementation manner, the score of the broadcast order may be determined at least according to the generation time of the broadcast order. The score of the broadcast order may be negatively correlated with a third difference value, where the third difference value may be equal to a time difference between a current time and a generation time of the broadcast order.

As an example of this implementation manner, the score of the broadcast order may be determined at least according to the feedback information corresponding to the broadcast order. For example, the feedback information corresponding to the broadcast order may include an average score of the ratings of all users on the broadcast order, and may also include the total number of comments of all users on the broadcast order, which is not limited herein.

As an example of this implementation manner, the score of the playlist may be determined at least according to the score of each video in the playlist. For example, the score of the playlist can be positively related to the average score of each video in the playlist.

As an example of this implementation manner, Equation 6 can be used to calculate the score of the broadcast order :

Equation 6.

among them, Can represent the base score for all orders, It may be greater than 0, may be equal to 0 or less than 0, and is not limited herein. Those skilled in the art can flexibly set according to the actual application scenario . Represents the first Item score, The first Weighting of items, The total number of items representing the score of the order. For example, depending on the type of order , Determined according to the generation time of the broadcast , Determined according to the feedback information corresponding to the broadcast , Based on the score of each video in the playlist It is not limited here.

Example 2

FIG. 3 illustrates a block diagram of a video search apparatus according to an embodiment of the present disclosure. As shown in FIG. 3, the device includes: an obtaining module 31 for obtaining a preliminary search result corresponding to the video search request when a video search request is received; and a calculation module 32 for calculating the preliminary search result The score of each type of video data in the search results; a sorting module 33 for sorting each type of video data according to the score of each type of video data to obtain a ranking result; a response module 34 for The ranking result responds to the video search request.

In a possible implementation manner, each type of video data includes at least one of the following: video, program, self-channel, and playlist.

FIG. 4 illustrates an exemplary block diagram of a video search apparatus according to an embodiment of the present disclosure. As shown in Figure 4:

In a possible implementation manner, the calculation module 32 includes: a first calculation sub-module 321, configured to calculate a score of the video according to at least one of the following when a video is included in each type of video data: : The correlation between the video and the video search request, the correlation between the uploader of the video and the video search request, the user feedback information of the search user corresponding to the video search request, and the video playback amount , The completion ratio of the video, the time when the video was published, the number of times the video was favorited, the number of comments on the video, the number of barrage of the video, and the subscription status of the search user for the video .

In a possible implementation manner, the calculation module 32 includes: a second calculation submodule 322, configured to calculate a score of the program according to at least one of the following when a program is included in each type of video data: : The real-time search volume of the program, the playback volume of the program, the relevance of the program to the video search request, the feedback information corresponding to the program, the release time of the program, and the copyright status of the program And site information for the show.

In a possible implementation manner, the response module 34 includes: an adjustment submodule 341, configured to adjust the ranking of the programs in the ranking result according to the ranking of the programs in the ranking result and the total number of programs. A response submodule 342, configured to respond to the video search request according to the adjusted ranking result.

In a possible implementation manner, the calculation module 32 includes: a third calculation sub-module 323, configured to calculate the self-channel according to at least one of the following when a self-channel is included in each type of video data: Score: the attribute of the channel owner of the self-channel, the score of each video in the self-channel, the number of videos belonging to the self-channel in the preliminary search results, the total number of videos of the self-channel, and the video The relevance of the search request to the self-channel.

In a possible implementation manner, the calculation module 32 includes: a fourth calculation submodule 324, configured to calculate the playlist according to at least one of the following when a type of video data includes a playlist Score: the type of the playlist, the time when the playlist was generated, the feedback information corresponding to the playlist, and the score of each video in the playlist.

The video search apparatus provided in this embodiment can improve the accuracy and diversity of search results.

Example 3

Fig. 5 is a block diagram of a device 1900 for video search according to an exemplary embodiment. For example, the device 1900 may be provided as a server. Referring to FIG. 5, the device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by the memory 1932, for storing instructions executable by the processing component 1922, such as an application program. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the method described above.

The device 1900 may further include a power module 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output (I / O) interface 1958. The device 1900 can operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, and the computer program instructions may be executed by the processing component 1922 of the device 1900 to complete the above method.

The present disclosure may be a system, method, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

The computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electric storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only Memory (EPROM or Flash), Static Random Access Memory (SRAM), Portable Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disk (DVD), USB Flash Drive, Floppy Disk, Mechanical Encoding Device, such as The perforated card or raised structure in the groove is stored thereon, and any suitable combination of the above. Computer-readable storage media used herein are not to be interpreted as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, light pulses through fiber optic cables), or via electrical wires Electrical signal transmitted.

The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing / processing devices or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. . The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for computer-readable storage in the respective computing / processing device Storage media.

The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or any arbitrary one or more programming languages. Combining written source or object code, the programming languages include object-oriented programming languages—such as Smalltalk, C ++, and the like—and conventional procedural programming languages—such as the "C" language or similar programming languages. The computer-readable program instructions can be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on a remote computer, or entirely on a remote computer or server carried out. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider) To connect via the Internet). In some embodiments, the electronic circuit is personalized by utilizing the state information of computer readable program instructions, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA). Computer-readable program instructions may be executed to implement various aspects of the present disclosure.

Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer-readable program instructions.

These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing device, thereby producing a machine that when executed by a processor of a computer or other programmable data processing device, Means are generated to implement the functions / acts specified in one or more of the blocks in the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer, a programmable data processing device, and / or other devices to work in a specific manner. Thus, a computer-readable medium storing instructions includes: An article of manufacture comprising instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

Computer-readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device, so that a series of operating steps can be performed on the computer, other programmable data processing device, or other device to produce a computer-implemented process. So that the instructions executed on the computer, other programmable data processing device, or other equipment can implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a part of a module, segment, or instruction that contains one or more pieces of logic for implementing the specified logic. Functional executable instructions. In some alternative implementations, the functions marked in the blocks may also occur in a different order than those marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in the reverse order, depending on the function involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs a specified function or action. Implementation, or it can be implemented with a combination of dedicated hardware and computer instructions.

The embodiments of the present disclosure have been described above, the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the embodiments described. The terminology used herein is chosen to best explain the principles of the embodiments, practical applications or technical improvements in the market, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

S11 ~ S14‧‧‧step

S141 ~ S142‧‧‧step

31‧‧‧Get Module

32‧‧‧Computing Module

321‧‧‧first computing submodule

322‧‧‧Second Computing Submodule

323‧‧‧Third computing submodule

324‧‧‧Fourth calculation submodule

33‧‧‧Sorting Module

34‧‧‧ Response Module

341‧‧‧Adjust submodule

342‧‧‧Response submodule

1900‧‧‧ device

1922‧‧‧Processing Components

1926‧‧‧Power Module

1932‧‧‧Memory

1950‧‧‧Interface

1958‧‧‧Input and output interface

The accompanying drawings, which are incorporated in and constitute a part of the specification, together with the description, illustrate exemplary embodiments, features, and aspects of the disclosure and serve to explain the principles of the disclosure.

FIG. 1 shows a flowchart of a video search method according to an embodiment of the present disclosure.

FIG. 2 illustrates an exemplary flowchart of step S14 of a video search method according to an embodiment of the present disclosure.

FIG. 3 illustrates a block diagram of a video search apparatus according to an embodiment of the present disclosure.

FIG. 4 illustrates an exemplary block diagram of a video search apparatus according to an embodiment of the present disclosure.

Fig. 5 is a block diagram of a device 1900 for video search according to an exemplary embodiment.

Claims (16)

A video search method, comprising: when a video search request is received, obtaining a preliminary search result corresponding to the video search request; calculating a score of each type of video data in the preliminary search result; Scores of each type of video data, sort each type of video data to obtain a ranking result, and respond to the video search request according to the ranking result. The method according to claim 1, wherein each type of video data includes at least one of the following: video, program, self-channel, and broadcast. The method according to claim 1 or 2, wherein calculating a score of each type of video data in the preliminary search result includes: In a case where a video is included in each type of video data, according to at least one of the following Calculate the score of the video: the relevance of the video to the video search request, the relevance of the uploader of the video to the video search request, the user feedback information of the search user corresponding to the video search request, The video playback volume, the video completion ratio, the video release time, the number of times the video has been favorited, the number of comments on the video, the number of barrage of the video, and the search user The subscription status of the video. The method according to claim 1 or 2, wherein calculating a score of each type of video data in the preliminary search result includes: In a case where a program is included in each type of video data, according to at least one of the following Calculate the score of the program: the real-time search volume of the program, the playback volume of the program, the relevance of the program to the video search request, the feedback information corresponding to the program, the release time of the program, Copyright status of the program and site information of the program. The method according to claim 4, wherein responding to the video search request according to the ranking result includes: adjusting the ranking result of the program in the ranking result according to the ranking of the programs in the ranking result and the total number of programs. And a response to the video search request according to the adjusted ranking result. The method according to claim 1 or 2, wherein calculating a score of each type of video data in the preliminary search result includes: in a case where each type of video data includes a self-channel, according to at least one of the following To calculate the score of the self-channel: the attribute of the channel owner of the self-channel, the score of each video in the self-channel, the number of videos belonging to the self-channel in the preliminary search results, the The total number of videos and the relevance of the video search request to the self-channel. The method according to claim 1 or 2, wherein calculating a score of each type of video data in the preliminary search result includes: In a case where a broadcast order is included in each type of video data, according to at least one of the following The item calculates the score of the broadcast order: the type of the broadcast order, the generation time of the broadcast order, the feedback information corresponding to the broadcast order, and the score of each video in the broadcast order. A video search device is characterized by comprising: an acquisition module for acquiring a preliminary search result corresponding to the video search request when a video search request is received; a calculation module for calculating the preliminary search The score of each type of video data in the result; a sorting module for sorting each type of video data according to the score of each type of video data to obtain a sorting result; and a response module for sorting according to the sorted result Responding to the video search request. The device according to claim 8, wherein each type of video data includes at least one of the following: video, program, self-channel, and playlist. The device according to claim 8 or 9, wherein the calculation module includes: a first calculation sub-module, configured to calculate a video according to at least one of the following when a video is included in each type of video data: The score of the video: the relevance of the video to the video search request, the relevance of the uploader of the video to the video search request, the user feedback information of the search user corresponding to the video search request, the The video playback amount, the video completion ratio, the video release time, the number of times the video has been favorited, the number of comments on the video, the number of barrage of the video, and the search users The video's subscription status. The device according to claim 8 or 9, wherein the calculation module includes: a second calculation sub-module, configured to calculate a program according to at least one of the following when a program is included in each type of video data: The score of the program: the real-time search volume of the program, the playback volume of the program, the correlation between the program and the video search request, the feedback information corresponding to the program, the release time of the program, the The copyright status of the program and the site information of the program are described. The device according to claim 11, wherein the response module comprises: an adjustment sub-module configured to adjust the program in the ranking result according to the ranking of the programs in the ranking result and the total number of programs. And a response submodule for responding to the video search request according to the adjusted ranking result. The device according to claim 8 or 9, wherein the calculation module includes: a third calculation sub-module, configured to include a self-channel in each type of video data, according to at least one of the following Calculate the score of the self-channel: the attribute of the channel owner of the self-channel, the score of each video in the self-channel, the number of videos belonging to the self-channel in the preliminary search results, the video of the self-channel The total number and the relevance of the video search request to the self-channel. The device according to claim 8 or 9, wherein the calculation module includes: a fourth calculation sub-module, configured to include a playlist in each type of video data, according to at least one of the following Calculate the score of the broadcast order: the type of the broadcast order, the generation time of the broadcast order, the feedback information corresponding to the broadcast order, and the score of each video in the broadcast order. A video search device, comprising: a processor; a memory for storing processor-executable instructions; and wherein the processor is configured to execute the method according to any one of claims 1 to 7 . A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.