Video search method, device, server and terminal equipment

Abstract

The embodiment of the present invention relates to a video search method, device, server and terminal device, the method comprising: obtaining search information; parsing the search information to obtain at least one field; when it is determined based on at least one field that there is a first video matching the search information in a pre-constructed database, obtaining the first video; when a second video having an association with the search information is screened out from the database based on the first video, the first video and the second video are sent to the terminal device as search results, the first video being a reply video generated by the object based on the comment content under any main video; the second video includes the main video, and / or a video of the same category as the first video. The server recalls the reply video and the video associated with the reply video based on the search information and feeds it back to the terminal device. The object can obtain the video of interest through the terminal device. Furthermore, the video click rate and video viewing rate can also be improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a video search method, apparatus, server, and terminal device. Background Art

[0002] With the rise of short videos, more and more people are beginning to pay attention to and participate in the production of short videos, as well as the sharing of short videos, in order to experience the fun of short videos. Based on this background, more and more short video anchors share their videos for other users to watch and comment on.

[0003] There are also more and more people searching for videos they are interested in on corresponding applications or websites. However, during the search process, the videos found may not be particularly relevant to the videos you expect to get, or even if they are related, they are not the videos the user wants. The videos found may differ from the user's expectations in terms of accuracy and quality, resulting in low search efficiency. Summary of the invention

[0004] The present disclosure provides a video search method, device, server and terminal device to solve some or all technical problems in the prior art.

[0005] In a first aspect, the present disclosure provides a video search method, the method comprising:

[0006] Get search information;

[0007] Parse the search information and obtain at least one field;

[0008] When it is determined according to the at least one field that there is a first video matching the search information in the pre-constructed database, acquiring the first video;

[0009] When a second video associated with the search information is screened out from the database based on the first video, the first video and the second video are sent to the terminal device as search results, wherein the first video is a reply video generated by the object based on the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video.

[0010] The method provided by the embodiment of the present disclosure obtains search information, then parses the search information, obtains at least one field, and when it is determined that there is a first video matching the search information in the pre-constructed database according to the at least one field, obtains the first video. When a second video having an association relationship with the search information is screened out from the database according to the first video, the first video and the second video are fed back to the terminal device as search results. Among them, the first video is a reply video generated by the object according to the comment content under any main video, and the second video includes the main video, or a video of the same category as the first video. During the above operation, the server can recall the reply video according to the search information, that is, a video that a certain object (such as an object making comments under the main video) is more interested in, and in the present disclosure, not only can the reply video be provided to the object, but also more videos related to the search information can be provided to the object. That is, the matching degree between the searched video and the search information is relatively high, which greatly improves the application experience of the object for video search. It is precisely because the searched videos are all videos with a high matching degree with the search information, so it can also promote the improvement of video click-through rate and video viewing rate. Related videos usually have more learning value, and they are promoted to more objects, which can facilitate object learning.

[0011] Optionally, based on the first video, selecting a second video associated with the search information from a database specifically includes:

[0012] According to the first video, key information corresponding to the first video is obtained;

[0013] According to the key information, extracting at least one video corresponding to the key information from a database;

[0014] A second video associated with the search information is filtered out from the at least one video.

[0015] In one case, the key information corresponding to the first video is first extracted. The key information may be, for example, fields in the subject name of the first video, the author of the first video, the category of the first video, and so on. Then, at least one video corresponding to the key information is extracted from the database, and a second video having a correlation with the search information is screened from the at least one video. In this process, when at least one video corresponding to the key information is extracted from the database using the key information of the first video, it is equivalent to accurately narrowing the search scope from a large number of videos. Within the narrowed search scope, the second video having a correlation with the search information is searched. This operation will improve the accuracy and efficiency of the video search. The searched videos will not only be richer, but also more in line with the videos that the object wants to search.

[0016] Optionally, when the second video is a main video, and the database includes reply videos generated respectively for a plurality of comment contents of the same main video, the method further includes:

[0017] Classify multiple response videos according to key information of each response video;

[0018] An association relationship is established between the main video and the reply videos of the same category, and the reply videos of the same category are stored in a preset storage location.

[0019] When the reply video is a reply video generated for multiple comments on the same main video, the multiple reply videos are classified according to the key information of each reply video, and the association relationship between the main video and the reply videos of the same category is established, and the reply videos of the same category are stored in the same storage location. When the object searches for a reply video, for example, after searching the main video through any of the aforementioned embodiments, the reply video of the same category can also be directly searched and fed back to the terminal device based on the association relationship between the main video and a certain type of reply video. Of course, the reply video of the same category can also be found based on the category relationship between a reply video in the same category and other reply videos, and then fed back to the terminal device. Regardless of which of the above methods is used, the number of videos fed back to the terminal device can be increased, successfully helping the object to obtain more useful videos, and also improving the click-through rate and viewing rate of the video.

[0020] In a second aspect, the present disclosure provides a video search method, the method comprising:

[0021] Receive search information;

[0022] Determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, the first video being a reply video generated by the subject according to the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video;

[0023] Generate preview information corresponding to the video set according to the first video and / or the second video;

[0024] Display preview information on the search results page, and display video collections based on the preview information.

[0025] The method provided by the embodiment of the present disclosure, after receiving the search information, determines at least one video set matching the search information, the video set including a first video and a second video corresponding to the first video. Preview information corresponding to the video set is generated according to the first video and / or the second video. The preview information is displayed on the search result display page, and the video set is displayed according to the preview information. Among them, the first video is a reply video generated according to the comment content under any main video, and the second video includes the main video and / or a video of the same category as the first video. In this way, some key information is extracted from the searched video as preview information, which can facilitate the object to understand the content of the currently displayed video at a glance when viewing the preview information. On the one hand, it can also prompt the object to open the video and improve the click-through rate and viewing rate of the video. Moreover, the searched video has a higher matching degree with the search information, and the types and quantities of videos displayed to the object are relatively richer.

[0026] Optionally, determining at least one video set matching the search information specifically includes:

[0027] Matching the first video according to the search information;

[0028] The second video is obtained according to the key information and search information in the first video, where the key information is a video theme in the first video or a key field in the video content.

[0029] After the first video is matched according to the information, the second video can be obtained according to the key information and search information in the first video. The key information here can be the video theme in the first video or the key field in the video content. Through the video theme in the first video, or the key field in the video content, you can search for videos that are highly relevant to the first video, and then filter the second video related to the search information from these videos according to the search information. In the whole process, using the key information of the first video to search for at least one video is equivalent to accurately narrowing the search scope from a large number of videos. In the narrowed search range, look for the second video that has a correlation with the search information. This operation will improve the accuracy and efficiency of the video search. The searched videos are not only rich, but also more in line with the videos that the object wants to search.

[0030] Optionally, generating preview information corresponding to the video set according to the first video and / or the second video specifically includes:

[0031] Extracting preset content from the first video and / or the second video, wherein the preset content is used to respond to the search information;

[0032] Generate preview information based on preset content.

[0033] Preset content is extracted from the first video and / or the second video, and the preset content can respond to the search information. Then, the preset content is used as preview information, which will play a more eye-catching role, so that after the object sees the preview information, it can be known that the currently searched video is a video that matches the search information entered by the object.

[0034] Optionally, the preset content includes preset key frames in the first video and / or the second video displayed in a dynamic form; or, the preset content includes preset image content in the first video and / or the second video.

[0035] Optionally, display a collection of videos on the search results page, along with preview information, including:

[0036] When it is detected that the preview information is triggered, the next video is displayed in sequence after the current video in the video collection is played, in accordance with the preset sorting order, wherein the first video displayed is the video that generates the preview information, and the videos in the video collection are pre-sorted according to their relevance to the search information;

[0037] or,

[0038] When it is detected that the preview information is triggered, the first video is dynamically displayed;

[0039] When it is determined that the display of the first video is completed, a recommended video is selected from the video collection and displayed according to a preset recommendation method.

[0040] When it is detected that the preview information is triggered, the videos in the video collection can be displayed in a variety of ways, such as displaying the next video in a preset sorting order after the current video is played. Of course, the first video to be displayed should be the video that can respond to the search information, that is, the video that generates the preview information. The specific sorting order can be sorted in advance according to the relevance to the search information. In another case, after it is detected that the preview information is triggered, the first video can be dynamically displayed, and after the first video is displayed, a recommended video can be selected from the video collection for display according to a preset recommendation method. A rich and diverse video display method can further enhance the viewing experience of the object.

[0041] Optionally, when displaying the first video, first identification information is displayed at a preset position of the first video, and the first identification information is used to indicate that the first video is a reply video;

[0042] Alternatively, when the second video is displayed, second identification information is displayed at a preset position of the second video, and the second identification information is used to indicate that the second video is any reference video other than the reply video.

[0043] When displaying a video, the highlighted identification information is used to indicate the attributes of the video, such as whether it is a response video or any reference video other than the response video.

[0044] In a third aspect, the present disclosure provides a video search device, the device comprising:

[0045] An acquisition module, used to acquire search information;

[0046] A parsing module, used to parse the search information and obtain at least one field;

[0047] A processing module, configured to obtain the first video when it is determined that there is a first video matching the search information in the pre-built database according to at least one field; and to filter out videos having an association relationship with the search information from the database according to the first video;

[0048] A sending module is used to send the first video and the second video as search results to a terminal device when the processing module screens out a second video associated with the search information from a database based on the first video, wherein the first video is a reply video generated by the object based on the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video.

[0049] The video search device provided by the embodiment of the present disclosure obtains search information, then parses the search information, obtains at least one field, and when it is determined that there is a first video matching the search information in the pre-constructed database according to the at least one field, the first video is obtained. When a second video having an association relationship with the search information is screened out from the database according to the first video, the first video and the second video are fed back to the terminal device as search results. Among them, the first video is a reply video generated by the object according to the comment content under any main video, and the second video includes the main video, or a video of the same category as the first video. During the above operation, the server can recall the reply video according to the search information, that is, a video that a certain object (for example, an object making comments under the main video) is more interested in, and in the present disclosure, not only can the reply video be provided to the object, but also more videos related to the search information can be provided to the object. That is, the matching degree between the searched video and the search information is relatively high, which greatly improves the application experience of the object for video search. It is precisely because the searched videos are all videos with a high matching degree with the search information, so it can also promote the improvement of video click-through rate and video viewing rate. Related videos usually have more learning value, and they are promoted to more objects, which can facilitate object learning.

[0050] In a fourth aspect, the present disclosure provides a video search device, the device comprising:

[0051] A receiving module, used for receiving search information;

[0052] A matching module, used to determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, the first video being a reply video generated by the subject according to the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video;

[0053] A generating module, used to generate preview information corresponding to the video set according to the first video and / or the second video;

[0054] The display module is used to display preview information on the search results page and display video collections based on the preview information.

[0055] The video search device provided by the embodiment of the present disclosure determines at least one video set matching the search information after receiving the search information, and the video set includes a first video and a second video corresponding to the first video. Preview information corresponding to the video set is generated based on the first video and / or the second video. The preview information is displayed on the search result display page, and the video set is displayed based on the preview information. Among them, the first video is a reply video generated based on the comment content under any main video, and the second video includes the main video and / or a video of the same category as the first video. In this way, certain key information is extracted from the searched video as preview information, which can facilitate the object to understand the content of the currently displayed video at a glance when viewing the preview information. On the one hand, it can also prompt the object to open the video and improve the click-through rate and viewing rate of the video. Moreover, the searched video has a higher matching degree with the search information, and the types and quantities of videos displayed to the object are relatively richer.

[0056] In a fifth aspect, a server is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0057] Memory, used to store computer programs;

[0058] The processor is used to implement the steps of the video search method of any embodiment of the first aspect when executing the program stored in the memory.

[0059] In a sixth aspect, a terminal device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0060] Memory, used to store computer programs;

[0061] The processor is used to implement the steps of the video search method of any embodiment of the second aspect when executing the program stored in the memory.

[0062] In the seventh aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the video search method as in any embodiment of the first aspect are implemented; or, the steps of the video search method as in any embodiment of the second aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of a video search method flow provided by an embodiment of the present disclosure;

[0064] Figure 2 A schematic diagram of another video search method flow chart provided by an embodiment of the present disclosure;

[0065] Figure 3 A schematic diagram of another video search method flow chart provided by an embodiment of the present disclosure;

[0066] Figure 4 A schematic diagram of another video search method flow chart provided by an embodiment of the present disclosure;

[0067] Figure 5 A schematic diagram of another video search method flow chart provided by an embodiment of the present disclosure;

[0068] Figure 6 A schematic diagram of another video search method flow chart provided by an embodiment of the present disclosure;

[0069] Figure 7 A schematic diagram of a specific form of displaying a reply video provided by the present disclosure;

[0070] Figure 8 A schematic diagram of the structure of a video search device provided by an embodiment of the present disclosure;

[0071] Fig. 9 A schematic diagram of the structure of another video search device provided by an embodiment of the present disclosure;

[0072] Fig.10 A schematic diagram of the structure of a server provided in an embodiment of the present disclosure;

[0073] Fig.11 A schematic diagram of the structure of a terminal device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0075] To facilitate understanding of the embodiments of the present disclosure, further explanation will be given below with reference to specific embodiments in conjunction with the accompanying drawings, and the embodiments do not constitute a limitation on the embodiments of the present disclosure.

[0076] In response to the technical problems mentioned in the background technology, the present disclosure provides a video search method, apparatus, server and terminal device.

[0077] See Figure 1 As shown, Figure 1 A schematic flow chart of a video search method provided by an embodiment of the present disclosure. In an optional example, the method is executed by a server, and the method steps include:

[0078] Step 110, obtaining search information.

[0079] Step 120: parse the search information to obtain at least one field.

[0080] Specifically, the method of parsing the search information to obtain at least one field may adopt existing relatively mature technical means, which will not be elaborated here.

[0081] Step 130: When it is determined based on at least one field that a first video matching the search information exists in the pre-constructed database, the first video is acquired.

[0082] Specifically, after parsing the search information, at least one field can be obtained. Then, each field in the at least one field can be matched with videos in the database to determine whether there is a video in the database that matches one or more fields in the at least one field.

[0083] If there are videos matching one or more fields in the at least one field in the database, it is further determined whether the first video exists.

[0084] In an optional example, the first video is a reply video generated by the object according to the comment content under any main video.

[0085] Step 140: When a second video associated with the search information is screened out from the database based on the first video, the first video and the second video are sent to the terminal device as search results.

[0086] When there is a reply video, a second video associated with the search information is further screened out from the database based on the first video.

[0087] In an optional example, the second video may include the main video mentioned above, that is, the original video for generating the reply video. Of course, it may also be a video of the same category as the first video. In a specific example, the video of the same category as the first video is, for example, different reply videos generated based on the comments under the same main video, and these reply videos are all reply videos generated for the same category of questions.

[0088] The correlation between multiple videos, such as the main video, reply video, and videos belonging to the same category as the reply video, will be very high. Moreover, the screened videos are all videos that are related to the search information. Then, these videos are fed back to the terminal device for the terminal device to display to the object that generated the search information. Then, the object that generated the search information will be able to obtain a wider variety of richer videos based on the search information. And these videos are all recalled videos using the reply video as a "bridge". Relatively speaking, all recalled videos are videos that the object (the object that generated the search information) is more interested in, so this method can improve the object's application experience for video search.

[0089] A video search method provided by an embodiment of the present disclosure obtains search information, then parses the search information, obtains at least one field, and when it is determined that there is a first video matching the search information in a pre-constructed database according to at least one field, obtains the first video. When a second video having an association relationship with the search information is screened out from the database according to the first video, the first video and the second video are fed back to the terminal device as search results. Among them, the first video is a reply video generated by the object according to the comment content under any main video, and the second video includes the main video, or a video of the same category as the first video. During the above operation, the server can recall the reply video according to the search information, that is, a video that a certain object (such as an object making comments under the main video) is more interested in, and in the present disclosure, not only can the reply video be provided to the object, but also more videos related to the search information can be provided to the object. That is, the matching degree between the searched video and the search information is relatively high, which greatly improves the application experience of the object for video search. It is precisely because the searched videos are all videos with a high matching degree with the search information, so it can also promote the improvement of video click-through rate and video viewing rate. Related videos usually have more learning value, and they are promoted to more objects, which can facilitate object learning.

[0090] Based on the above embodiment, the present disclosure also provides another video search method, which is the same or similar to the above embodiment and will not be repeated here. In this embodiment, the focus will be on how to select a second video that is associated with the search information from a database based on the first video. Figure 2 As shown, the method steps include:

[0091] Step 210: Acquire key information corresponding to the first video based on the first video.

[0092] Specifically, the key information may include, for example, the subject name of the first video, some fields in the subject name, information about the author who generated the first video, the category of the first video, etc. The category information of the first video mentioned here can refer to the introduction of the previous embodiment, that is, the category information of the reply videos belonging to the same category.

[0093] Step 220: extract at least one video corresponding to the key information from a database according to the key information.

[0094] Specifically, for example, if the key information is the author information that generated the first video, then based on the author information, all videos published by the author can be extracted from the pre-built database. Alternatively, when the key information is the theme name of the first video, for example, the theme name of the first video is how to raise a husky. Then, based on the theme name of the first video, how to raise a husky, you can match videos that match the theme name from the pre-built database. Alternatively, based on some fields in the theme name such as raising huskies or huskies, etc., one or more videos can be searched from the pre-built database, for example, how to raise a female husky, how to play with a husky, etc. Among these videos, there may be a main video corresponding to the reply video, and there may also be videos that belong to the same category as the reply video.

[0095] Step 230: Filter a second video that is associated with the search information from the at least one video.

[0096] Specifically, from the above searched videos, find videos related to the search information. For example, if the search information is how to raise a five-month-old husky, and the above searched videos include the main video how to raise a husky, then the video can be obtained by screening. Of course, you can also search for videos that belong to the same category as how to raise a five-month-old husky, such as how to raise an eight-month-old husky, how to raise a male husky, etc. The above screening process is based on the fact that the second video has a certain association with the reply video, and the second video is obtained based on the association and the search information.

[0097] In this method, the key information corresponding to the first video is first extracted. The key information may be, for example, fields in the subject name of the first video, the author of the first video, the category of the first video, and so on. Then, at least one video corresponding to the key information is extracted from the database, and a second video having a correlation with the search information is screened from the at least one video. In this process, when at least one video corresponding to the key information is extracted from the database using the key information of the first video, it is equivalent to accurately narrowing the search scope from a large number of videos. Within the narrowed search scope, the second video having a correlation with the search information is searched. This operation will improve the accuracy and efficiency of the video search. The searched videos will not only be richer, but also more in line with the videos that the object wants to search.

[0098] Based on any of the above embodiments, the present disclosure also provides another video search method. The content that is the same or similar to any of the above embodiments will not be repeated here. This embodiment will detail some preparations that can be done in advance when the second video is the main video and the database includes reply videos generated for multiple comments on the same main video, so as to assist in searching for the second video related to the reply video when the reply video is searched later.

[0099] In an optional example, the specific preparation work may include performing a clustering operation on multiple reply videos and establishing an association relationship between each type of reply video and the main video. Figure 3 As shown, the method steps include:

[0100] Step 310, classifying the multiple reply videos according to the key information of each reply video.

[0101] Step 320, establishing an association relationship between the main video and the reply videos of the same category, and storing the reply videos of the same category in a preset storage location.

[0102] Specifically, the key information in the reply video has been explained in the previous embodiment and will not be repeated here.

[0103] According to the key information, the reply videos are classified. For example, videos such as how to raise a husky, how to raise a 7-month-old husky, and how to raise a one-year-old husky can be grouped into one category. When implementing this operation specifically, for example, if the key information is a topic name, then the clustering operation can be completed by the topic names of multiple reply videos, and the reply videos with high similarity in multiple topic names can be grouped into one category. In another case, for example, if the key information is video content, then the clustering operation can also be completed based on the video content in multiple reply videos. A specific clustering algorithm, for example, can be a k-means clustering algorithm. Of course, other algorithms that can determine the correlation between different videos can also be used, and there are no excessive restrictions here.

[0104] Through the above method, it can be ensured that when the object searches for a certain reply video, for example, after searching for the main video through any of the aforementioned embodiments, the reply video of the same category can be directly searched and fed back to the terminal device based on the association between the main video and a certain type of reply video. Of course, it is also possible to find the same category of reply videos based on the category relationship between a reply video in the same category and other reply videos, and then feed them back to the terminal device. Regardless of which of the above methods is used, the number of videos fed back to the terminal device can be increased, successfully helping the object to obtain more useful videos, and also improving the click-through rate and viewing rate of the video.

[0105] Corresponding to any of the above embodiments, the present disclosure also provides another video search method, which is executed by a terminal device and includes the following method steps, see Figure 4 As shown, including:

[0106] Step 410, receiving search information.

[0107] Specifically, the search information is the search information input by a certain object through the information input interface of the terminal device. In this embodiment, the search information generally refers to the video content to be searched by the object.

[0108] Step 420: Determine at least one video set matching the search information.

[0109] After obtaining the search information, the terminal device may search for a video collection matching the search information through a search engine.

[0110] Among them, the first video is, for example, a reply video generated based on the comment content under any main video. The second video can be the main video, or a video of the same category as the first video. The videos of the same category mentioned here are, for example, reply videos generated based on the comment content under the main video. In the reply videos of the same category, for example, the first reply video is how to raise a husky, and the second reply video is how to raise a female husky. Multiple videos in the same category of videos can usually be videos with logical associations, such as the first reply video and the second reply video listed above.

[0111] Step 430: Generate preview information corresponding to the video set according to the first video and / or the second video.

[0112] Step 440: display the preview information on the search result page, and display the video collection according to the preview information.

[0113] Specifically, the preset content is extracted from the first video and / or the second video as the preview information corresponding to the video set. By displaying the preview information on the search result display page, the object can be informed of the content outline of the video set to be displayed, or the video direction, such as the video used to explain what kind of content the video set is. This allows the object to have a certain understanding of the video content without seeing the specific video, and further assists in judging whether it is the video he wants to know.

[0114] A video search method provided by an embodiment of the present disclosure determines at least one video set matching the search information after receiving search information, wherein the video set includes a first video and a second video corresponding to the first video. Preview information corresponding to the video set is generated based on the first video and / or the second video. The preview information is displayed on the search result display page, and the video set is displayed based on the preview information. Among them, the first video is a reply video generated based on the comment content under any main video, and the second video includes the main video and / or a video of the same category as the first video. In this way, certain key information is extracted from the searched video as preview information, which can facilitate the object to understand the content of the currently displayed video at a glance when viewing the preview information. On the one hand, it can also prompt the object to open the video and improve the click-through rate and viewing rate of the video. Moreover, the searched video has a higher matching degree with the search information, and the types and quantities of videos displayed to the object are relatively richer.

[0115] Optionally, based on the above embodiment, the present disclosure also provides another video search method. The same or similar contents as the above embodiment are not repeated here. In this embodiment, how to determine at least one video set matching the search information will be described in detail. Figure 5 As shown, including:

[0116] Step 510: matching the first video according to the search information.

[0117] Step 520, obtaining a second video according to the key information and search information in the first video.

[0118] Specifically, the terminal device searches for the first video matching the search information through a search engine, and then extracts key information from the first video. In an optional example, the key information may include the theme name of the first video, some fields in the theme name, information about the author who generated the first video, and the category of the first video. The category information of the first video mentioned here refers to the category information of the reply videos belonging to the same category.

[0119] Subsequently, the second video is obtained based on the key information and search information in the first video.

[0120] Specifically, for example, if the key information is the author information of the first video, then all videos published by the author can be searched based on the author information. Alternatively, when the key information is the theme name of the first video, such as the theme name of the first video is how to raise a husky. Then, based on the theme name of the first video, how to raise a husky, you can search for videos that match the theme name. Alternatively, based on some fields in the theme name, such as raising a husky or husky, you can search for one or more videos, such as how to raise a female husky, how to play with a husky, etc.

[0121] Among the videos searched based on the key information of the first video, there are videos that have a certain correlation with the search information. Then, according to the search information, the second video can be screened out from these videos. For example, the search information is how to raise a five-month-old husky, and the above-searched videos include the main video how to raise a husky, then the video can be obtained through screening. Of course, you can also search for videos that belong to the same category as how to raise a five-month-old husky, such as how to raise an eight-month-old husky, how to raise a male husky, etc. The key fields in these videos are highly similar to the key fields in the search information, so they can be directly recalled.

[0122] In the above embodiment, using the key information of the first video to search for at least one video is equivalent to accurately narrowing the search range from a large number of videos. In the narrowed search range, the second video that is associated with the search information is searched. This operation will improve the accuracy and efficiency of video search, and the searched videos will not only be richer, but also more in line with the videos that the object wants to search.

[0123] In the above Figure 4 or Figure 5 Based on the corresponding embodiment, the embodiment of the present disclosure also provides another video search method, which is similar to the above Figure 4 or Figure 5 The same or similar contents of the corresponding embodiments are not repeated here. In this embodiment, how to generate preview information corresponding to the video set according to the first video and / or the second video will be described in detail. Figure 6 As shown, the method steps include:

[0124] Step 610, extracting preset content from the first video and / or the second video, wherein the preset content is used to respond to the search information.

[0125] Step 620: Generate preview information according to preset content.

[0126] Specifically, in the first video and / or the second video, there is preset content that can respond to the search information.

[0127] In a specific example, the preset content may include, for example: preset key frames in the first video and / or the second video displayed in a dynamic form; or, the preset content includes: preset image content in the first video and / or the second video.

[0128] Then, the existing mature methods can be used to extract preset key frames or preset image contents in advance in offline or online states. Then, it is used as the preview information of the video set, and after the terminal device obtains the video set, it is displayed to the object in advance in the form of preview information.

[0129] Because the preview information is used to respond to the search information, it will play a more eye-catching role, so that after the target sees the preview information, it can know that the currently searched video is a video that matches the search information entered by the target.

[0130] In another optional example, the present disclosure also provides another embodiment of a video search method, which is based on the above Figures 4 to 6 The corresponding embodiment is implemented based on any one of the embodiments, so Figures 4 to 6 The same or similar contents of any corresponding embodiment will not be described in detail here. In this embodiment, how to display a video collection on a search result page and preview information will be described in detail. The method steps include:

[0131] When it is detected that the preview information is triggered, the next video is displayed in sequence after the current video in the video collection is played, in accordance with the preset sorting order, wherein the first video displayed is the video that generates the preview information, and the videos in the video collection are pre-sorted according to their relevance to the search information;

[0132] or,

[0133] When it is detected that the preview information is triggered, the first video is dynamically displayed;

[0134] When it is determined that the display of the first video is completed, a recommended video is selected from the video collection and displayed according to a preset recommendation method.

[0135] In a specific example, when it is detected that the preview information is triggered, all videos can be sorted according to the relevance between the video and the search information. For example, the video that generates the preview information is ranked first, that is, the video with the highest relevance to the search information. Since the preview information can respond to the search information, its relevance is naturally the highest video. To determine the relevance between each video in the video set and the search information, the relevance between the video content / video theme in the video set can be determined based on the video content / video theme in the video set. The specific way to calculate the relevance, for example, can be to count the similarity between the content in the video and the search information through a clustering algorithm, or to count the similarity between the video theme name and the search information, etc. Alternatively, the relevance between different videos and the search information can be determined by other ways that can know the relevance between each video in the video set and the search information. For example, the reply video is determined to be the video with the highest relevance, the main video that generates the reply video is the video with the second highest relevance, and among the videos of the same category as the reply video, the content similarity between different videos in the same category and the reply video is counted, and then the relevance between different videos in the same category and the search information is determined. Finally, the videos in the video set are displayed according to the degree of relevance.

[0136] In another specific example, it can also be directly set to dynamically display the first video after the preview information is triggered, and then after the first video is displayed, a recommended video is selected from the video collection according to a certain recommendation method and displayed. The specific display method can refer to the video recommendation display method in the prior art, and will not be described in detail here.

[0137] In the above embodiment, when it is detected that the preview information is triggered, the videos in the video collection can be displayed in a variety of ways, such as displaying the next video in a preset sorting order after the current video is played. Of course, the first video to be displayed should be the video that can respond to the search information, that is, the video that generates the preview information. The specific sorting order can be sorted in advance according to the relevance to the search information. In another case, after it is detected that the preview information is triggered, the first video can be dynamically displayed, and after the first video is displayed, a recommended video can be selected from the video collection for display according to a preset recommendation method. A rich and diverse video display method can further enhance the viewing experience of the object.

[0138] In another optional example, the present disclosure further provides another embodiment of a video search method. Based on the above embodiment, the method may further include:

[0139] When displaying the first video, displaying first identification information at a preset position of the first video, the first identification information is used to indicate that the first video is a reply video;

[0140] Alternatively, when the second video is displayed, second identification information is displayed at a preset position of the second video, and the second identification information is used to indicate that the second video is any reference video other than the reply video.

[0141] For details, see Figure 7 As shown, Figure 7 This illustrates one of the situations described in this embodiment. That is, when the first video is displayed, the first identification information is displayed at a preset position of the first video, and the first identification information is used to indicate that the first video is a reply video. Figure 7 As shown, Figure 7 The search information displayed is how to raise a 5-monthhusky. Figure 7 It is shown that a reply video, Reply How To Rasie a Husky#husky, is searched. At the very beginning of the reply video title, Reply is bolded to highlight that the video is a reply video. In this video, the first identification information is Reply.

[0142] If the video is another reference video, you can also use similar Figure 7 In the display method, different identification information is displayed to distinguish the currently displayed video. In addition, this display method can more clearly inform the object what type of video is currently searched.

[0143] Figure 8 A schematic diagram of the structure of a video search device provided in an embodiment of the present disclosure, the device includes: an acquisition module 801, a parsing module 802, and a processing module 803.

[0144] Acquisition module 801, used to acquire search information;

[0145] A parsing module 802, used to parse the search information and obtain at least one field;

[0146] The processing module 803 is used to obtain the first video when it is determined that there is a first video matching the search information in the pre-built database according to at least one field; and screen out videos associated with the search information from the database according to the first video;

[0147] A sending module is used to send the first video and the second video as search results to a terminal device when the processing module 803 selects a second video associated with the search information from a database based on the first video, wherein the first video is a reply video generated by the object based on the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video.

[0148] Optionally, the processing module 803 is specifically configured to:

[0149] According to the first video, key information corresponding to the first video is obtained;

[0150] According to the key information, extracting at least one video corresponding to the key information from a database;

[0151] A second video associated with the search information is filtered out from the at least one video.

[0152] Optionally, the processing module 803 is further configured to classify the multiple reply videos according to key information of each reply video when the second video is a main video and the database includes reply videos generated respectively for multiple comment contents of the same main video;

[0153] An association relationship is established between the main video and the reply videos of the same category, and the reply videos of the same category are stored in a preset storage location.

[0154] The functions performed by each component in the video search device provided in the embodiment of the present disclosure are as described above. Figures 1 to 3 The corresponding method embodiments have been described in detail, so they will not be repeated here.

[0155] A video search device provided by an embodiment of the present disclosure obtains search information, then parses the search information, obtains at least one field, and when it is determined that there is a first video matching the search information in a pre-constructed database according to at least one field, obtains the first video. When a second video having an association relationship with the search information is screened out from the database according to the first video, the first video and the second video are fed back to the terminal device as search results. Among them, the first video is a reply video generated by the object according to the comment content under any main video, and the second video includes the main video, or a video of the same category as the first video. During the above operation, the server can recall the reply video according to the search information, that is, a video that a certain object (for example, an object making comments under the main video) is more interested in, and in the present disclosure, not only can the reply video be provided to the object, but also more videos related to the search information can be provided to the object. That is, the matching degree between the searched video and the search information is relatively high, which greatly improves the application experience of the object for video search. It is precisely because the searched videos are all videos with a high matching degree with the search information, so it can also promote the improvement of video click-through rate and video viewing rate. Related videos usually have more learning value, and they are promoted to more objects, which can facilitate object learning.

[0156] Fig. 9This is a schematic diagram of the structure of another video search device provided in an embodiment of the present disclosure. The device includes: a receiving module 901, a matching module 902, a generating module 903, and a display module 904.

[0157] Receiving module 901, used for receiving search information;

[0158] A matching module 902 is used to determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, the first video being a reply video generated by the subject according to the comment content under any main video; the second video includes the main video and / or is a video of the same category as the first video;

[0159] A generating module 903, configured to generate preview information corresponding to the video set according to the first video and / or the second video;

[0160] The display module 904 is used to display the preview information on the search result page and display the video collection according to the preview information.

[0161] Optionally, a matching module 902 is specifically configured to match the first video according to the search information;

[0162] The second video is obtained according to the key information and search information in the first video, where the key information is a video theme in the first video or a key field in the video content.

[0163] Optionally, the generating module 903 is specifically configured to extract preset content from the first video and / or the second video, wherein the preset content is used to respond to the search information;

[0164] Generate preview information based on preset content.

[0165] Optionally, the preset content includes preset key frames in the first video and / or the second video displayed in a dynamic form; or, the preset content includes preset image content in the first video and / or the second video.

[0166] Optionally, a display module 904 is specifically used to display the next video in the video set after the current video in the video set is played after it is detected that the preview information is triggered, in accordance with a preset sorting order, wherein the first video to be displayed is the video that generates the preview information, and the videos in the video set are pre-sorted according to the relevance between them and the search information;

[0167] or,

[0168] When it is detected that the preview information is triggered, the first video is dynamically displayed;

[0169] When it is determined that the display of the first video is completed, a recommended video is selected from the video collection and displayed according to a preset recommendation method.

[0170] Optionally, the display module 904 is further configured to display first identification information at a preset position of the first video when displaying the first video, wherein the first identification information is used to indicate that the first video is a reply video;

[0171] Alternatively, when the second video is displayed, second identification information is displayed at a preset position of the second video, and the second identification information is used to indicate that the second video is any reference video other than the reply video.

[0172] The functions performed by each component in the video search device provided by the embodiment of the present disclosure are all described in Figures 4 to 7 The corresponding method embodiments have been described in detail, so they will not be repeated here.

[0173] A video search device provided by an embodiment of the present disclosure determines at least one video set matching the search information after receiving search information, wherein the video set includes a first video and a second video corresponding to the first video. Preview information corresponding to the video set is generated based on the first video and / or the second video. The preview information is displayed on the search result display page, and the video set is displayed based on the preview information. Among them, the first video is a reply video generated based on the comment content under any main video, and the second video includes the main video and / or a video of the same category as the first video. In this way, certain key information is extracted from the searched video as preview information, which can facilitate the object to understand the content of the currently displayed video at a glance when viewing the preview information. On the one hand, it can also prompt the object to open the video and improve the click-through rate and viewing rate of the video. Moreover, the searched video has a higher matching degree with the search information, and the types and quantities of videos displayed to the object are relatively richer.

[0174] like Fig.10 As shown, an embodiment of the present disclosure provides a server, including a processor 111 , a communication interface 112 , a memory 113 and a communication bus 114 , wherein the processor 111 , the communication interface 112 , and the memory 113 communicate with each other through the communication bus 114 .

[0175] Memory 113, used for storing computer programs;

[0176] In one embodiment of the present disclosure, the processor 111 is configured to implement the video search method provided by any one of the aforementioned method embodiments when executing the program stored in the memory 113. The method includes:

[0177] Get search information;

[0178] Parse the search information and obtain at least one field;

[0179] When it is determined according to the at least one field that there is a first video matching the search information in the pre-constructed database, acquiring the first video;

[0180] When a second video associated with the search information is screened out from the database based on the first video, the first video and the second video are sent to the terminal device as search results, wherein the first video is a reply video generated by the object based on the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video.

[0181] Optionally, based on the first video, selecting a second video associated with the search information from a database specifically includes:

[0182] According to the first video, key information corresponding to the first video is obtained;

[0183] According to the key information, extracting at least one video corresponding to the key information from a database;

[0184] A second video associated with the search information is filtered out from the at least one video.

[0185] Optionally, when the second video is a main video, and the database includes reply videos generated respectively for a plurality of comment contents of the same main video, the method further includes:

[0186] Classify multiple response videos according to key information of each response video;

[0187] An association relationship is established between the main video and the reply videos of the same category, and the reply videos of the same category are stored in a preset storage location.

[0188] like Fig.11 As shown, an embodiment of the present disclosure provides a terminal device, including a processor 211, a communication interface 212, a memory 213 and a communication bus 214, wherein the processor 211, the communication interface 212, and the memory 213 communicate with each other through the communication bus 214.

[0189] Memory 213, used for storing computer programs;

[0190] In one embodiment of the present disclosure, the processor 211 is configured to implement the video search method provided by any one of the aforementioned method embodiments when executing the program stored in the memory 213. The method includes:

[0191] Receive search information;

[0192] Determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, the first video being a reply video generated by the subject according to the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video;

[0193] Generate preview information corresponding to the video set according to the first video and / or the second video;

[0194] Display preview information on the search results page, and display video collections based on the preview information.

[0195] Optionally, determining at least one video set matching the search information specifically includes:

[0196] Matching the first video according to the search information;

[0197] The second video is obtained according to the key information and search information in the first video, where the key information is a video theme in the first video or a key field in the video content.

[0198] Optionally, generating preview information corresponding to the video set according to the first video and / or the second video specifically includes:

[0199] Extracting preset content from the first video and / or the second video, wherein the preset content is used to respond to the search information;

[0200] Generate preview information based on preset content.

[0201] Optionally, the preset content includes preset key frames in the first video and / or the second video displayed in a dynamic form; or, the preset content includes preset image content in the first video and / or the second video.

[0202] Optionally, display a collection of videos on the search results page, along with preview information, including:

[0203] When it is detected that the preview information is triggered, the next video is displayed in sequence after the current video in the video collection is played, in accordance with the preset sorting order, wherein the first video displayed is the video that generates the preview information, and the videos in the video collection are pre-sorted according to their relevance to the search information;

[0204] or,

[0205] When it is detected that the preview information is triggered, the first video is dynamically displayed;

[0206] When it is determined that the display of the first video is completed, a recommended video is selected from the video collection and displayed according to a preset recommendation method.

[0207] Optionally, when displaying the first video, first identification information is displayed at a preset position of the first video, and the first identification information is used to indicate that the first video is a reply video;

[0208] Alternatively, when the second video is displayed, second identification information is displayed at a preset position of the second video, and the second identification information is used to indicate that the second video is any reference video other than the reply video.

[0209] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figures 1 to 3 The steps of the video search method provided by any method embodiment;

[0210] Alternatively, when the computer program is executed by the processor, the above Figures 4 to 7 Any of the method embodiments provides the steps of the European video search method.

[0211] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0212] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A video search method, characterized in that: The method comprises: Get search information; Parsing the search information to obtain at least one field; When it is determined, based on at least one of the fields, that a first video matching the search information exists in the pre-constructed database, acquiring the first video; When a second video associated with the search information is screened out from the database based on the first video, the first video and the second video are sent to the terminal device as search results, wherein the first video is a reply video generated by the subject based on the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video; The method of selecting, according to the first video, a second video associated with the search information from the database specifically includes: According to the first video, acquiring key information corresponding to the first video; According to the key information, extracting at least one video corresponding to the key information from the database; A second video associated with the search information is filtered out from at least one of the videos.

2. The method according to claim 1, characterized in that: When the second video is a main video, and the database includes reply videos generated for a plurality of comments on the same main video, the method further includes: Classifying the plurality of reply videos according to key information of each reply video; An association relationship is established between the main video and the reply videos of the same category, and the reply videos of the same category are stored in a preset storage location.

3. A video search method, characterized in that: The method comprises: Receive search information; Determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, the first video being a reply video generated by the subject according to the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video; Generate preview information corresponding to the video set according to the first video and / or the second video; Displaying the preview information on a search result page, and displaying the video collection according to the preview information; The determining of at least one video set matching the search information specifically includes: Matching the first video according to the search information; The second video is acquired according to key information in the first video and the search information, wherein the key information is a key field in a video theme or video content in the first video.

4. The method according to claim 3, characterized in that The generating preview information corresponding to the video set according to the first video and / or the second video specifically includes: Extracting preset content from the first video and / or the second video, wherein the preset content is used to respond to the search information; The preview information is generated according to the preset content.

5. The method according to claim 4, characterized in that The preset content includes preset key frames in the first video and / or the second video displayed in a dynamic form; or, the preset content includes preset image content in the first video and / or the second video.

6. The method according to claim 3, characterized in that: The displaying of the video collection and the preview information on the search results page specifically includes: When it is detected that the preview information is triggered, the next video is displayed in sequence after the current video in the video set is played in a preset sorting order, wherein the first video displayed is the video that generates the preview information, and the videos in the video set are pre-sorted according to their relevance to the search information; or, When it is detected that the preview information is triggered, dynamically display the first video; When it is determined that the first video display is completed, a recommended video is selected from the video collection and displayed according to a preset recommendation method.

7. The method according to claim 6, characterized in that When displaying the first video, displaying first identification information at a preset position of the first video, the first identification information being used to indicate that the first video is a reply video; Alternatively, when displaying the second video, second identification information is displayed at a preset position of the second video, and the second identification information is used to indicate that the second video is any reference video other than the reply video.

8. A video search device, characterized in that: The device comprises: An acquisition module, used to acquire search information; A parsing module, used to parse the search information and obtain at least one field; A processing module, configured to obtain the first video when it is determined that there is a first video matching the search information in the pre-built database according to at least one of the fields; and to filter out videos associated with the search information from the database according to the first video; A sending module, configured to send the first video and the second video as search results to a terminal device when the processing module selects a second video associated with the search information from the database according to the first video, wherein the first video is a reply video generated by the subject according to the comment content under any main video; the second video includes the main video, and / or is a video of the same category as the first video; Among them, the processing module is specifically used to obtain key information corresponding to the first video based on the first video; extract at least one video corresponding to the key information from the database based on the key information; and filter a second video that has an association with the search information from at least one of the videos.

9. A video search device, characterized in that: The device comprises: A receiving module, used for receiving search information; A matching module, configured to determine at least one video set matching the search information; wherein the video set includes a first video and a second video corresponding to the first video, wherein the first video is a reply video generated by the subject according to the comment content under any main video; and the second video includes the main video and / or is a video of the same category as the first video; A generating module, configured to generate preview information corresponding to the video set according to the first video and / or the second video; A display module, used to display the preview information on the search result page, and to display the video collection according to the preview information; Among them, the matching module is specifically used to match the first video according to the search information; obtain the second video according to the key information in the first video and the search information, and the key information is the key field in the video theme or video content in the first video.

10. A server, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the video search method described in claim 1 or 2 when executing the program stored in the memory.

11. A terminal device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the video search method described in any one of claims 3 to 7 when executing the program stored in the memory.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the steps of the video search method according to any one of claims 1 to 2; or, implements the steps of the video search method according to any one of claims 3 to 7.

Images