A video recommendation method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a video recommendation method and device, electronic equipment and storage medium, comprising: in response to a touch operation on a preset recommendation control, a short video currently playing in a video playing interface is intercepted to obtain an intercepted image; the intercepted image is sent to a background server, and an image link address corresponding to the intercepted image is received from the background server; the image link address is an access address of the corresponding intercepted image in the network; the image link address is sent to a preset search interface to request a search, and a plurality of types of search results returned by the preset search interface are received; and the search results are output. According to the embodiments of the present application, it is not necessary to set the mapping relationship between short video data and long video data in advance, but the video picture of the short video is intercepted in real time, the corresponding long video data is searched based on the intercepted image, and the long video data obtained by searching is different based on the different intercepted images, so that the diverted long video data is more abundant.

Description

Technical Field

[0001] This invention relates to the field of video playback technology, and in particular to a video recommendation method, a video recommendation device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Users are spending increasingly more time watching short videos, and using short videos to drive traffic to long videos is an important way to increase the number of views for long videos.

[0003] Currently, driving traffic from short videos to long videos requires establishing a connection between the short video and its corresponding long video beforehand. When a short video is played, the associated long video data is displayed in a corresponding position on the playback interface, thus driving traffic to the long video. However, this method has the following drawbacks:

[0004] First, it is necessary to set up the mapping relationship between short video data and long video data in advance, which results in high data maintenance costs and relatively simple mapping relationships between video data.

[0005] Secondly, users are passively receiving long video recommendations. Users may only want to watch short videos, but the playback interface displays related long videos, and the recommended long video content may not match the user's actual interests. Summary of the Invention

[0006] In view of the above problems, embodiments of the present invention are proposed to provide a video recommendation method and a corresponding video recommendation device, an electronic device, and a computer-readable storage medium to overcome or at least partially solve the above problems.

[0007] This invention discloses a video recommendation method, which provides a graphical user interface (GUI) on a terminal. The GUI displays a video playback interface of a first application, and the video playback interface provides preset recommendation controls. The method includes:

[0008] In response to a touch operation on the preset recommendation control, the video frame of the currently playing short video in the video playback interface is captured to obtain a captured image;

[0009] The captured image is sent to the backend server, and the image link address corresponding to the captured image is received from the backend server; the image link address is the access address of the corresponding captured image on the network.

[0010] The image link address is sent to a preset search interface to request a search, and the preset search interface returns various types of search results; wherein, the search results include long video data;

[0011] Output the search results.

[0012] This invention also discloses a video recommendation device, which provides a graphical user interface (GUI) via a terminal. The GUI displays a video playback interface of a first application, and the video playback interface provides preset recommendation controls. The device includes:

[0013] The capture module is used to capture the currently playing short video frame in the video playback interface in response to the touch operation of the preset recommendation control, and obtain the captured image.

[0014] The first sending and receiving module is used to send the captured image to the backend server and receive the image link address corresponding to the captured image from the backend server; the image link address is the access address of the corresponding captured image in the network.

[0015] The second sending and receiving module is used to send the image link address to a preset search interface to request a search, and to receive various types of search results returned by the preset search interface; wherein, the search results include long video data;

[0016] An output module is used to output the search results.

[0017] This invention also discloses an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements a video recommendation method as described above.

[0018] This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements a video recommendation method as described above.

[0019] The embodiments of the present invention have the following advantages:

[0020] In this embodiment of the invention, a preset recommendation control is provided on the video playback interface. Touching this preset recommendation control triggers a capture operation on the currently playing short video frame, obtaining a corresponding captured image. The captured image can then be sent to a backend server, and an image link address for that captured image is received from the backend server. This image link address can be sent to a preset search interface for searching, obtaining various types of search results returned by the preset search interface. The search results may include long video data. By adopting the above method, there is no need to pre-set a mapping relationship between short video data and long video data. Instead, by capturing video frames from short videos in real time, the corresponding long video data is searched based on the captured image. Different captured images result in different long video data, making the long video data for traffic acquisition richer. Furthermore, the search results obtained by this method based on the captured image include other types of data besides long video data, making the traffic acquisition content richer. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the steps of a video recommendation method according to an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of another video recommendation method according to an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the recommendation process of a video recommendation method according to an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the recommendation process of another video recommendation method according to an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the recommendation process of another video recommendation method according to an embodiment of the present invention;

[0026] Figure 6 This is a structural block diagram of a video recommendation device according to an embodiment of the present invention. Detailed Implementation

[0027] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art are within the scope of protection of the present invention.

[0028] Currently, driving traffic from short videos to long videos requires establishing a connection between the short video and its corresponding long video beforehand. When a short video is played, the associated long video data is displayed in a corresponding position on the playback interface, thus driving traffic to the long video. However, this method has the following drawbacks:

[0029] First, it is necessary to set up the mapping relationship between short video data and long video data in advance, which results in high data maintenance costs and relatively simple mapping relationships between video data.

[0030] Secondly, users are passively receiving long video recommendations. Users may only want to watch short videos, but the playback interface displays related long videos, and the recommended long video content may not match the user's actual interests.

[0031] One of the core concepts of this invention is to provide a preset recommendation control on the video playback interface. Touching this control triggers a capture operation on the currently playing short video frame, obtaining a corresponding captured image. This captured image can then be sent to a backend server, which returns an image link address for that image. This image link address can be sent to a preset search interface to obtain various types of search results, including long video data. By employing this method, there is no need to pre-set a mapping relationship between short and long video data. Instead, by capturing video frames from short videos in real time, the corresponding long video data is searched based on the captured image. Different captured images result in different long video data, enriching the long video data used for traffic redirection. Furthermore, the search results obtained from the captured image search include other types of data besides long video data, further enriching the content used for traffic redirection.

[0032] Reference Figure 1 This diagram illustrates a flowchart of a video recommendation method according to an embodiment of the present invention. A graphical user interface (GUI) is provided via a terminal, displaying a video playback interface of a first application. The video playback interface provides preset recommendation controls, and the method may specifically include the following steps:

[0033] Step 101: In response to a touch operation on a preset recommended control, capture a frame of the currently playing short video in the video playback interface to obtain a captured image.

[0034] The video recommendation method provided in this invention can be applied to terminal devices, which may include various mobile terminals such as mobile phones, tablets, and PDAs. These devices can interact with users through input devices such as keyboards, virtual keyboards, touchpads, touchscreens, and voice control devices. Applications can run on the terminal device, and a graphical user interface can be rendered on the device's display screen.

[0035] In this embodiment of the invention, a video playback interface of a first application can be displayed in a graphical user interface, and preset recommendation controls can be provided on the video playback interface. The video playback interface can be the interface through which a player plays a video; the preset recommendation controls are intuitively displayed entry points for users.

[0036] Users can perform touch operations on preset recommended controls, and the touch operation will be responded to, triggering a capture operation on the currently playing short video frame in the video playback interface to obtain the captured image.

[0037] The preset recommendation control is used to implement the screenshot function in the video player. In the specific implementation, the preset recommendation control encapsulates a specified method class. By calling the specified method class, the video frame currently being played by the video player can be obtained. Then, the obtained video frame can be converted into an image format to obtain the corresponding screenshot image.

[0038] Step 102: Send the captured image to the backend server and receive the image link address corresponding to the captured image from the backend server.

[0039] After obtaining the captured image, it can be sent to the backend server, and then the backend server will return an image link address for that captured image. The image link address is the network access address for the corresponding captured image. The captured image can then be obtained over the network using this image link address.

[0040] Step 103: Send the image link address to the preset search interface to request a search, and receive various types of search results returned by the preset search interface.

[0041] The search results include long video data.

[0042] In this embodiment of the invention, the image link address of the captured image can be sent to a preset search interface. The preset search interface can obtain the captured image based on the image link address, and then perform a search based on the captured image to obtain the corresponding search results. The search results can be received from the preset search interface. The search results include various types, such as actor data and related short video data.

[0043] It should be noted that the search results may be the results at the current moment, and the search results obtained at different times may be different. That is, the traffic redirection data of this application is not static.

[0044] In some optional embodiments, the video content of the long video data in the search results can be the main content of the short video; the actor data in the search results can be the actor data in the short video, or it can be the actor data in the long video data that is being redirected; the correlation between the short video data in the search results and the currently playing short video meets a preset correlation condition, for example, the correlation between the associated short video data and the currently playing short video is greater than a preset correlation threshold. As for the specific calculation method of the correlation, this embodiment of the invention does not impose specific limitations.

[0045] Step 104: Output the search results.

[0046] In this embodiment of the invention, multiple types of search results can be output. For example, multiple types of search results can be displayed in different areas on the search results display page.

[0047] In summary, in this embodiment of the invention, a preset recommendation control is provided on the video playback interface. Touching this preset recommendation control triggers a capture operation on the currently playing short video frame, obtaining a corresponding captured image. This captured image can then be sent to a backend server, and the server returns an image link address for that captured image. This image link address can be sent to a preset search interface for searching, obtaining various types of search results. These search results may include long video data. By employing this method, there is no need to pre-set a mapping relationship between short video data and long video data. Instead, by capturing video frames from short videos in real time, the corresponding long video data is searched based on the captured image. Different captured images result in different long video data, enriching the long video data for traffic redirection. Furthermore, the search results obtained from the captured image search include other types of data besides long video data, further enriching the content for traffic redirection.

[0048] Reference Figure 2 This diagram illustrates a flowchart of another video recommendation method according to an embodiment of the present invention. A graphical user interface (GUI) is provided via a terminal, displaying a video playback interface of a first application. The video playback interface provides preset recommendation controls, and the method may specifically include the following steps:

[0049] Step 201: In response to a touch operation on a preset recommended control, capture a frame of the currently playing short video in the video playback interface to obtain a captured image.

[0050] In practice, users can launch the first application and enter the short video feed (a continuously updated information stream presented to users). Users can select short videos of interest and click to enter the video playback interface to watch them. This playback interface provides a player for playing short videos and also offers a "short to long" function button, a preset recommendation control. Clicking this function button triggers the player to automatically capture a frame from the currently playing short video.

[0051] In an optional embodiment of the present invention, step 201, which involves capturing a frame of the currently playing short video in response to a touch operation on a preset recommendation control, to obtain a captured image, may specifically include the following sub-steps:

[0052] In response to touch operations on preset recommended controls, a specified method class is called to obtain the video frame playing at the current playback time; the video frame is then converted into an image format to obtain the corresponding cropped image.

[0053] The preset recommendation control encapsulates a specific method class. This specific method class may differ depending on the operating system. For example, in iOS, the specified method class could be `AVPlayerLayer`. When a touch operation on the preset recommendation control is detected, the `AVPlayerLayer` class can be called to retrieve the video frame playing at the current playback time. This video frame can then be converted into a `UIImage` object, and the `UIImagePNGRepresentation` or `UIImageJPEGRepresentation` functions can be used to save the `UIImage` object as a PNG or JPEG image file. Similarly, in Android, the specified method class could be `MediaPlayer`. When a touch operation on the preset recommendation control is detected, the `MediaPlayer` class can be called to retrieve the video frame playing at the current playback time. This video frame can then be converted into a `Bitmap` object, and the `Bitmap.Compress` function can be used to save the `Bitmap` object as a JPEG or PNG image file.

[0054] Step 202: Identify the copyright holder of the video content in the short video and determine the target application corresponding to the copyright holder.

[0055] Major long-form video platforms own the copyrights to their respective long-form video resources. In this embodiment of the invention, the video resource search is specifically performed within the target application corresponding to the copyright holder. Therefore, it is necessary to identify the copyright holder of the video content in the short video and determine the target application corresponding to the copyright holder.

[0056] As an example, it is possible to identify whether there is a corresponding copyright holder's logo in the video frame of a short video. There are various methods for identifying the copyright holder, and this embodiment of the invention does not impose any specific limitations on them.

[0057] Step 203: Send the captured image to the target application's backend server and receive the image link address corresponding to the captured image from the backend server.

[0058] The image link address is specifically the storage address or path of the captured image on the corresponding backend server; it is a reference link pointing to the captured image. The image link address is typically a URL (Uniform Resource Locator), consisting of the protocol, server hostname, storage path, and query parameters.

[0059] In an optional embodiment of the present invention, the background server of the target application is used to store the captured image to the background server, obtain the corresponding storage address, and then use the storage address to generate the image link address of the captured image.

[0060] In this embodiment of the invention, the captured image is sent to the background server of the target application, the captured image is stored in the background server, the corresponding storage address is obtained, and then the image link address corresponding to the captured image can be generated based on the storage address. Obtaining the image link address makes it more convenient to call the preset search interface later.

[0061] Step 204: Send the image link address to the preset search interface to request a search, and receive various types of search results returned by the preset search interface.

[0062] The image link address of the captured image can be sent to the preset search interface. The preset search interface can obtain the captured image based on the image link address, and then perform a search based on the captured image to obtain the corresponding search results.

[0063] In an optional embodiment of the present invention, the search results also include actor data and short video data, wherein the video content of the long video data is the full-length content of the short video.

[0064] Search results can include various types, such as long video data, actor data, and short video data. Specifically, long video data in the search results can be the full content of the currently playing short video.

[0065] The search process for various search results can be illustrated in the following example:

[0066] In an optional embodiment of the present invention, the database of the target application stores long video data and / or short video data, which have corresponding video tag data. A preset search interface is used to access the backend server through an image link address to obtain the corresponding captured image, and to perform image analysis on the captured image using image recognition technology to obtain the corresponding image feature data. Then, the image feature data is matched with the video tag data to determine the target video tag data that matches the image feature data, and the target long video data and / or target short video data corresponding to the target video tag data are determined as the search results.

[0067] For long video data and / or short video data, the target application's database can pre-store long video data and / or short video data. The target application can pre-label the long video data and / or short video data in the database, such as labeling video frames, audio frames, image feature points, audio feature points, and text features, to obtain the corresponding video labeling data.

[0068] After the target application's preset search interface receives the image link address, it can obtain the corresponding cropped image from the corresponding backend server. It can then use image recognition technology to perform image analysis on the cropped image, such as image classification and object detection based on convolutional neural networks, to extract feature information from the cropped image, such as color, shape, and texture, and obtain the corresponding image feature data.

[0069] The video tag data and image feature data obtained in the above two steps are matched. Here, machine learning and natural language processing techniques can be used for analysis and comparison to determine the target video tag data that matches the image feature data, and the corresponding target long video data and / or target short video data are determined as the search results to be output.

[0070] In an optional embodiment of the present invention, the long video data stored in the target application database has associated actor data, and a preset search interface is used to determine the target actor data associated with the target long video data as the search result after determining the target long video data corresponding to the target video tag data.

[0071] For actor data, a relationship between long video data and actor data can be established in advance in the database of the target application. After the preset search interface determines the target long video data corresponding to the target video tag data, it can determine the target actor data associated with the target long video data based on the relationship and output the target actor data as the search result.

[0072] It should be noted that, in addition to the three types of search results mentioned above, other types of search results can also be output, and this embodiment of the invention does not impose specific limitations on them.

[0073] In an optional embodiment of the present invention, the target application includes a second application, which is different from the first application. This occurs when the target application is the second application and the terminal has the second application installed.

[0074] Step 203, which involves sending the captured image to the target application's backend server and receiving the image link address corresponding to the captured image from the backend server, may specifically include the following sub-steps:

[0075] Retrieve and call settings information;

[0076] If the settings indicate that the first application is allowed to call the second application, the second application is called, the captured image is sent to the backend server of the second application, and the image link address corresponding to the captured image is received from the backend server.

[0077] Step 204, which involves sending an image link address to a preset search interface to request a search and receiving various types of search results returned by the preset search interface, may specifically include the following sub-steps:

[0078] Send an image link address to the preset search interface of the second application to request a search, and receive various types of search results returned by the preset search interface.

[0079] In this embodiment of the invention, when the target application is a second application and the terminal has the second application installed, the second application can be invoked to store the captured image of the first application to the background server of the second application, and the preset search interface of the second application can be invoked to perform a search.

[0080] Specifically, if the target application is the second application and the terminal has the second application installed, it is necessary to obtain the calling settings information to determine the calling relationship between the first application and the second application. If the calling settings information indicates that the first application is allowed to call the second application, then the second application can be called, the captured image is sent to the backend server of the second application for storage, the corresponding image link address is received from the backend server, and the returned image link address is sent to the preset search interface of the second application to request a search.

[0081] In an optional embodiment of the present invention, the target application includes a second application, which is different from the first application. This occurs when the target application is the second application but the terminal does not have the second application installed.

[0082] Step 203, which involves sending the captured image to the target application's backend server and receiving the image link address corresponding to the captured image from the backend server, may specifically include the following sub-steps:

[0083] The first application calls the second application's mini-program, sends the captured image to the mini-program's backend server, and receives the image link address corresponding to the captured image from the backend server;

[0084] Step 204, which involves sending an image link address to a preset search interface to request a search and receiving various types of search results returned by the preset search interface, may specifically include the following sub-steps:

[0085] Send an image link to the mini-program's preset search interface to request a search, and receive various types of search results returned by the preset search interface.

[0086] In this embodiment of the invention, when the target application is a second application but the terminal does not have the second application installed, the mini-program of the second application can be called in the first application to store the captured image of the first application to the background server of the mini-program, and the preset search interface of the mini-program can be called to perform a search.

[0087] Specifically, if the target application is a second application but the terminal does not have the second application installed, the second application's mini-program can be called in the first application. The captured image is sent to the mini-program's backend server for storage, the corresponding image link address is received from the backend server, and the returned image link address is sent to the mini-program's preset search interface to request a search.

[0088] As can be seen from the above, the video recommendation method provided in this embodiment of the invention can be executed within an application or across multiple applications.

[0089] Step 205: Output the search results.

[0090] In an optional embodiment of the present invention, step 205, which involves outputting the search results, may specifically include the following sub-steps:

[0091] The search results are displayed on the search results page of the first application; or,

[0092] The search results are displayed on the search results page of the second application; or,

[0093] The search results are displayed on the search results page of the mini-program.

[0094] In this embodiment of the invention, if the target application is a first application, the search results can be displayed to the user on the search results display page of the first application.

[0095] If the target application is a secondary application, the search results can be displayed to the user on the search results display page of the secondary application; alternatively, the search results can also be displayed to the user on the search results display page of the secondary application's mini-program.

[0096] Users can select the results they are interested in on the search results page to complete the conversion process.

[0097] In an optional embodiment of the present invention, the following steps may also be included:

[0098] Display a prompt message at the preset recommended control.

[0099] The prompt information is used to provide feedback on the functional effects of the preset recommended controls.

[0100] To enable those skilled in the art to better understand the embodiments of the present invention, three examples are provided below:

[0101] Reference Figure 3 The diagram illustrates the recommendation process of a video recommendation method according to an embodiment of the present invention. This recommendation process is performed within an application and specifically includes:

[0102] 1. Users enter the short video feed page, click to enter the short video playback interface to watch, and click the "Short to Long" function button on the video playback interface;

[0103] 2. Respond to click operations. The player in the video playback interface automatically captures a frame of the currently playing short video, obtains the captured image, and sends the captured image to the application's backend server.

[0104] 3. The backend server stores the captured image and generates an image link address based on the storage address, then sends the image link address back to the player;

[0105] 4. The player calls the application's default search interface and sends the image link address to the default search interface to request a search;

[0106] 5. The preset search interface accesses the backend server based on the image link address to obtain the corresponding cropped image, and can perform corresponding image recognition analysis on the cropped image to obtain search results;

[0107] 6. Display search results on the application's search results page. Search results can include long video data associated with short videos, actor data in short videos, and other relevant short video data. Users can click on the results they are interested in through the search results page to complete the traffic conversion.

[0108] Reference Figure 4 The diagram illustrates the recommendation process of another video recommendation method according to an embodiment of the present invention. This recommendation process is performed across applications, with APP-1 and APP-2 installed on the terminal. The specific process includes:

[0109] 1. Users enter the short video feed page of APP-1, click to enter the short video playback interface to watch, and click the "Short to Long" function button on the video playback interface.

[0110] 2. Respond to click operations. The player in the video playback interface of APP-1 automatically captures the video frame of the currently playing short video, obtains the captured image, and sends the captured image to the backend server of APP-2.

[0111] 3. The APP-2 backend server stores the captured image and generates an image link address based on the storage address, and sends the image link address back to the APP-1 player.

[0112] 4. When APP-1 is allowed to call APP-2, the APP-1 player calls the APP-2 preset search interface and sends the image link address to the APP-2 preset search interface to request a search.

[0113] 5. The APP-2 preset search interface accesses the APP-2 backend server based on the image link address to obtain the corresponding cropped image, performs corresponding image recognition analysis on the cropped image, and obtains the search results.

[0114] 6. Display search results on the APP-2 search results display page. Search results can include long video data associated with short videos, actor data in short videos, and other relevant short video data. Users can click on the results they are interested in through the search results display page to complete the traffic conversion.

[0115] Reference Figure 5 The diagram illustrates the recommendation process of another video recommendation method according to an embodiment of the present invention. In this method, APP-1 is installed on the terminal, but APP-2 is not. APP-1 can call the APP-2 mini-program. The specific process includes:

[0116] 1. Users enter the short video feed page of APP-1, click to enter the short video playback interface to watch, and click the "Short to Long" function button on the video playback interface.

[0117] 2. Respond to the click operation. The player in the video playback interface of APP-1 automatically captures the video frame of the currently playing short video and obtains the captured image. APP-1 calls the APP-2 mini program, and the APP-1 player sends the captured image to the backend server of the APP-2 mini program.

[0118] 3. The APP-2 mini-program backend server stores the captured image and generates the image link address based on the storage address, and sends the image link address back to the APP-1 player.

[0119] 4. The APP-1 player calls the preset search interface of the APP-2 mini program and sends the image link address to the preset search interface of the APP-2 mini program to request a search.

[0120] 5. The APP-2 mini-program's preset search interface accesses the APP-2 mini-program's backend server based on the image link address to obtain the corresponding cropped image, performs corresponding image recognition analysis on the cropped image, and obtains the search results.

[0121] 6. Display search results on the APP-2 mini-program search results display page. Search results can include long video data associated with short videos, actor data in short videos, and other relevant short video data. Users can click on the results data of interest through the search results display page to complete the traffic conversion.

[0122] In summary, in this embodiment of the invention, a preset recommendation control is provided on the video playback interface. Touching this preset recommendation control triggers a capture operation on the currently playing short video frame, obtaining a corresponding captured image. This captured image can then be sent to a backend server, and the server returns an image link address for that captured image. This image link address can be sent to a preset search interface for searching, obtaining various types of search results, including long video data. By employing this method, there is no need to pre-set a mapping relationship between short and long video data. Instead, by capturing video frames from short videos in real time, the corresponding long video data is searched based on the captured image. Different captured images result in different long video data, enriching the long video data for traffic redirection. Furthermore, the search results obtained based on the captured image include other types of data besides long video data, further enriching the content for traffic redirection. This method is not only applicable within an application but can also achieve cross-application traffic redirection, making it widely applicable.

[0123] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0124] Reference Figure 6 The diagram illustrates a structural block diagram of a video recommendation device according to an embodiment of the present invention. A graphical user interface (GUI) is provided via a terminal. The GUI displays a video playback interface of a first application, and the video playback interface provides preset recommendation controls. Specifically, it may include the following modules:

[0125] The capture module 601 is used to capture the currently playing short video frame in the video playback interface in response to the touch operation of the preset recommendation control, and obtain the captured image.

[0126] The first sending and receiving module 602 is used to send the captured image to the backend server and receive the image link address corresponding to the captured image from the backend server; the image link address is the access address of the corresponding captured image in the network.

[0127] The second sending and receiving module 603 is used to send the image link address to a preset search interface to request a search, and to receive various types of search results returned by the preset search interface; wherein, the search results include long video data;

[0128] Output module 604 is used to output the search results.

[0129] In this embodiment of the invention, the interception module includes:

[0130] The acquisition submodule is used to respond to the touch operation on the preset recommendation control by calling a specified method class to obtain the video frame playing at the current playback time.

[0131] The image format conversion submodule is used to convert the image format of the video frame to obtain the corresponding cropped image.

[0132] In this embodiment of the invention, the first transmitting and receiving module includes:

[0133] The identification and determination submodule is used to identify the copyright holder of the video content in the short video and determine the target application corresponding to the copyright holder;

[0134] The first sending and receiving submodule is used to send the captured image to the background server of the target application and receive the image link address corresponding to the captured image from the background server.

[0135] In this embodiment of the invention, the target application includes a second application, which is different from the first application. This occurs when the target application is the second application and the terminal has the second application installed.

[0136] The first sending and receiving submodule includes:

[0137] The retrieval unit is used to retrieve the call setting information;

[0138] The first calling, sending, and receiving unit is configured to, if the calling setting information indicates that the first application is allowed to call the second application, call the second application, send the captured image to the background server of the second application, and receive the image link address corresponding to the captured image from the background server;

[0139] The second transmitting and receiving module includes:

[0140] The second sending and receiving submodule is used to send the image link address to the preset search interface of the second application to request a search, and to receive various types of search results returned by the preset search interface.

[0141] In this embodiment of the invention, the target application includes a second application, which is different from the first application. This occurs when the target application is the second application but the terminal does not have the second application installed.

[0142] The first sending and receiving submodule includes:

[0143] The second calling, sending and receiving unit is used to call the mini-program of the second application in the first application, send the captured image to the background server of the mini-program, and receive the image link address corresponding to the captured image from the background server.

[0144] The second transmitting and receiving module includes:

[0145] The third sending and receiving submodule is used to send the image link address to the preset search interface of the mini-program to request a search, and to receive various types of search results returned by the preset search interface.

[0146] In this embodiment of the invention, the background server of the target application is used to store the captured image to the background server, obtain the corresponding storage address, and then use the storage address to generate the image link address of the captured image.

[0147] In this embodiment of the invention, the search results also include actor data and short video data, wherein the video content of the long video data is the main content of the short video.

[0148] In this embodiment of the invention, the database of the target application stores long video data and / or short video data, which have corresponding video tag data. The preset search interface is used to access the backend server through the image link address to obtain the corresponding captured image, and to perform image analysis on the captured image using image recognition technology to obtain corresponding image feature data. Then, the image feature data is matched with the video tag data to determine the target video tag data that matches the image feature data, and the target long video data and / or target short video data corresponding to the target video tag data are determined as the search results.

[0149] In this embodiment of the invention, the long video data stored in the target application database has associated actor data. The preset search interface is used to determine the target actor data associated with the target long video data as the search result after determining the target long video data corresponding to the target video tag data.

[0150] In this embodiment of the invention, the output module includes:

[0151] A first display submodule is configured to display the search results on the search results display page of the first application; or,

[0152] The second display submodule is used to display the search results on the search results display page of the second application; or,

[0153] The third display submodule is used to display the search results on the search results display page of the mini-program.

[0154] In this embodiment of the invention, the device further includes:

[0155] The display module is used to display prompt information at the preset recommended control; the prompt information is used to indicate the functional effects implemented by the preset recommended control.

[0156] In summary, in this embodiment of the invention, a preset recommendation control is provided on the video playback interface. Touching this preset recommendation control triggers a capture operation on the currently playing short video frame, obtaining a corresponding captured image. This captured image can then be sent to a backend server, and the server returns an image link address for that captured image. This image link address can be sent to a preset search interface for searching, obtaining various types of search results. These search results may include long video data. By employing this method, there is no need to pre-set a mapping relationship between short video data and long video data. Instead, by capturing video frames from short videos in real time, the corresponding long video data is searched based on the captured image. Different captured images result in different long video data, enriching the long video data for traffic redirection. Furthermore, the search results obtained from the captured image search include other types of data besides long video data, further enriching the content for traffic redirection.

[0157] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0158] This invention also provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described video recommendation method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0159] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described video recommendation method embodiment and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0160] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0161] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0162] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0163] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0164] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0166] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0167] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0168] The present invention has provided a detailed description of a video recommendation method, a video recommendation device, an electronic device, and a computer-readable storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A video recommendation method, characterized in that, The method includes providing a graphical user interface (GUI) via a terminal, wherein the GUI displays a video playback interface of a first application, and the video playback interface provides preset recommended controls. In response to a touch operation on the preset recommendation control, the video frame of the currently playing short video in the video playback interface is captured to obtain a captured image; The captured image is sent to the backend server of the target application, and the image link address corresponding to the captured image is received from the backend server; the image link address is the access address of the corresponding captured image on the network; the target application corresponds to the copyright holder of the video content in the short video; The image link address is sent to a preset search interface to request a search, and the preset search interface returns various types of search results; wherein, the search results include long video data and short video data, the video content of the long video data is the main content of the short video; the video content of the short video data is short video data whose relevance to the currently playing short video meets a preset relevance condition; Output the search results; The step of sending the captured image to the target application's backend server and receiving the image link address corresponding to the captured image from the backend server includes: Identify the copyright holder of the video content in the short video and determine the target application corresponding to the copyright holder; The captured image is sent to the background server of the target application, and the image link address corresponding to the captured image is received from the background server. The background server of the target application stores the captured image in the background server, obtains the corresponding storage address, and then uses the storage address to generate the image link address of the captured image, wherein the image link address is the storage address or storage path of the captured image in the background server of the target application.

2. The method according to claim 1, characterized in that, The step of responding to a touch operation on the preset recommendation control and capturing a frame of the currently playing short video in the video playback interface to obtain a captured image includes: In response to the touch operation on the preset recommended control, a specified method class is called to obtain the video frame playing at the current playback time. The video frames are converted to their image formats to obtain the corresponding cropped images.

3. The method according to claim 1, characterized in that, The target application includes a second application, which is different from the first application, provided that the target application is the second application and the terminal has the second application installed. The step of sending the captured image to the background server of the target application and receiving the image link address corresponding to the captured image from the background server includes: Retrieve and call settings information; If the call settings information indicates that the first application is allowed to call the second application, the second application is called, the captured image is sent to the background server of the second application, and the image link address corresponding to the captured image is received from the background server; The process involves sending the image link address to a preset search interface to request a search, and receiving various types of search results returned by the preset search interface, including: The image link address is sent to the preset search interface of the second application to request a search, and the various types of search results returned by the preset search interface are received.

4. The method according to claim 1, characterized in that, The target application includes a second application, which is different from the first application, in the case where the target application is the second application but the terminal does not have the second application installed. The step of sending the captured image to the background server of the target application and receiving the image link address corresponding to the captured image from the background server includes: The first application calls the mini-program of the second application, sends the captured image to the backend server of the mini-program, and receives the image link address corresponding to the captured image from the backend server; The process involves sending the image link address to a preset search interface to request a search, and receiving various types of search results returned by the preset search interface, including: Send the image link address to the preset search interface of the mini-program to request a search, and receive various types of search results returned by the preset search interface.

5. The method according to claim 1, characterized in that, The target application's database stores long video data and / or short video data, which have corresponding video tag data. The preset search interface is used to access the backend server through the image link address to obtain the corresponding captured image, and to perform image analysis on the captured image using image recognition technology to obtain corresponding image feature data. Then, the image feature data is matched with the video tag data to determine the target video tag data that matches the image feature data, and the target long video data and / or target short video data corresponding to the target video tag data are determined as the search results.

6. The method according to claim 1 or 5, characterized in that, The target application database stores long video data with associated actor data. The preset search interface is used to determine the target actor data associated with the target long video data as the search result after determining the target long video data corresponding to the target video tag data.

7. The method according to claim 4, characterized in that, The output of the search results includes: The search results are displayed on the search results display page of the first application; or, The search results are displayed on the search results display page of the second application; or, The search results are displayed on the search results page of the mini-program.

8. The method according to claim 1, characterized in that, The method further includes: A prompt message is displayed at the preset recommended control; the prompt message is used to indicate the functional effect of the preset recommended control.

9. A video recommendation device, characterized in that, The device provides a graphical user interface via a terminal, the graphical user interface displaying a video playback interface of a first application, the video playback interface providing preset recommended controls, and the device includes: The capture module is used to capture the currently playing short video frame in the video playback interface in response to the touch operation of the preset recommendation control, and obtain the captured image. The first sending and receiving module is used to send the captured image to the backend server of the target application and receive the image link address corresponding to the captured image from the backend server; the image link address is the access address of the corresponding captured image on the network; the target application corresponds to the copyright holder of the video content in the short video; The second sending and receiving module is used to send the image link address to a preset search interface to request a search, and to receive various types of search results returned by the preset search interface; wherein, the search results include long video data and short video data, the video content of the long video data is the main content of the short video; the video content of the short video data is short video data whose relevance to the currently playing short video meets a preset relevance condition; An output module is used to output the search results; The first transmitting and receiving module includes: The identification and determination submodule is used to identify the copyright holder of the video content in the short video and determine the target application corresponding to the copyright holder; The first sending and receiving submodule is used to send the captured image to the background server of the target application and receive the image link address corresponding to the captured image from the background server; the background server of the target application is used to store the captured image in the background server, obtain the corresponding storage address, and then use the storage address to generate the image link address of the captured image, wherein the image link address is the storage address or storage path of the captured image in the background server of the target application.

10. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements a video recommendation method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, which, when executed by a processor, implements a video recommendation method as described in any one of claims 1-8.

Images