Video recommendation method and device

Abstract

The present application discloses a video recommendation method and device. The present application belongs to the field of data processing, and the video recommendation method comprises: collecting target monitoring data; determining target state information of a first user of an electronic device according to the target monitoring data; performing video retrieval according to the target state information of the first user to determine a target video; and recommending the target video to the first user.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and specifically relates to a video recommendation method and device. Background Art

[0002] With the continuous development of multimedia technology, short videos, live broadcasts, online movies, variety shows, online courses and other audio-visual programs have occupied our time. However, among the numerous videos, the recommendation algorithms of major video software or the videos pushed to users by advertisers occupy the main part. How to recommend videos suitable for the current user from the numerous videos affects the user experience.

[0003] At present, mainstream applications are based on user portrait recommendations. When a user frequently plays a certain type of video, such videos will be continuously recommended in the future. Although such methods can judge user preferences to a certain extent and push videos that users may be interested in, the current recommendation methods are relatively simple and have shortcomings. For example, in a scenario where a device is used by multiple people, different users have different preferences, so videos that the current user is not interested in may be recommended. Moreover, this method can only recommend videos based on videos watched by users in the past, but not based on the current user's mood and needs, which is not smart enough.

[0004] Application Contents

[0005] The purpose of the embodiments of the present application is to provide a video recommendation method and device, which can solve the problem that the existing video push method is not intelligent enough.

[0006] In order to solve the above technical problems, this application is implemented as follows:

[0007] In a first aspect, an embodiment of the present application provides a method, comprising: collecting target monitoring data; determining target state information of a first user of an electronic device based on the target monitoring data; performing video retrieval based on the target state information of the first user to determine a target video; and recommending the target video to the first user.

[0008] In a second aspect, an embodiment of the present application provides a device, which includes: a data acquisition module for collecting target monitoring data; a data processing module for determining target state information of a first user of an electronic device based on the target monitoring data; a video retrieval module for performing video retrieval based on the target state information of the first user to determine a target video; and a recommendation module for recommending the target video to the first user.

[0009] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0010] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0011] In an embodiment of the present application, the target state information of the first user of the electronic device can be determined based on the collected target monitoring data, and video retrieval can be performed based on the target state information of the first user. Videos can be pushed more intelligently based on the user's current emotional state, which can greatly improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flowchart of the steps of a video recommendation method provided by this embodiment;

[0013] Figure 2 is a schematic diagram of a desktop component provided in this embodiment;

[0014] Figure 3 is a schematic diagram of determining a target video provided by this embodiment;

[0015] Figure 4 is another step flow chart of the video recommendation method provided by this embodiment;

[0016] Figure 5 is a schematic diagram of the structure of the video recommendation device provided in this embodiment;

[0017] Figure 6 is a structural schematic diagram of an electronic device provided by this embodiment;

[0018] Figure 7 It is a schematic diagram of the hardware structure of another electronic device provided in this embodiment. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0021] The video recommendation method and device provided by the embodiments of the present application are described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0022] refer to Figure 1 , which is a flow chart of a video recommendation method provided in an embodiment of the present application. The method can be applied to an electronic device, which can be a mobile phone, a tablet computer, a laptop computer, etc. The method can also be applied to a server, which includes multiple modules for executing the video recommendation method provided in this embodiment.

[0023] like Figure 1 As shown, a video recommendation method provided by this embodiment may include steps S1100-S1400, which are described in detail below.

[0024] S1100, collecting target monitoring data.

[0025] In this embodiment, the device for collecting target monitoring data may be a camera, a fingerprint recognition device, a microphone, a vibration sensor, or other device installed on an electronic device for collecting data.

[0026] The target monitoring data may be video data collected by a camera, fingerprint information recognized by an electronic device, search information or chat information input by a user, etc.

[0027] When a user uses the electronic device for the first time, the detection data can be used to establish a user portrait. When the user does not use the electronic device for the first time, the target monitoring data can be used to update the user portrait. In addition, the target monitoring data is used to recommend videos to the user according to the method provided in this embodiment.

[0028] Therefore, the target monitoring data of this embodiment includes at least the user's facial image data and / or the user's voice data.

[0029] In a feasible example, when a user uses an electronic device for the first time, the electronic device generates an initial user portrait by collecting the user's facial image, voice information, or fingerprint information collected when the user unlocks the electronic device or interacts with the electronic device, and creates and stores a corresponding user portrait for each user who uses the electronic device. When the user uses the electronic device again, the electronic device identifies the user's identity through the facial image, voice, or fingerprint information collected in the target monitoring data to obtain the user's identity.

[0030] In a feasible example, the target monitoring data may also include web page information browsed by the user while using the electronic device, or interaction information such as through the voice assistant of the electronic device.

[0031] S1200: Determine target state information of a first user of the electronic device according to target monitoring data.

[0032] In this embodiment, the first user is a user who is currently using the electronic device. The target state information reflects the current mood of the first user, for example, whether the first user is happy, angry, peaceful, etc. Specifically, the facial expression or tone of the first user can be obtained through the target monitoring data, and then the current mood of the first user can be inferred.

[0033] In this embodiment, the target monitoring data at least includes the facial image data of the first user and / or the voice data of the first user, so as to match the facial image or fingerprint information with the first user in the initial user portrait, thereby verifying the identity of the first user.

[0034] S1300: Perform video retrieval according to the target state information of the first user to determine a target video.

[0035] Video retrieval is performed according to the target state information of the first user to determine the target video, that is, the video is pushed to the first user according to the mood of the first user.

[0036] For example, when the first user is depressed, some healing videos are recommended to help the user improve his mood; when the first user is tired, some relaxing and funny videos are recommended.

[0037] S1400: Recommend a target video to a first user.

[0038] In this embodiment, reference Figure 2 , Figure 2 In order to display the desktop component on the mobile phone screen, a desktop component is provided. The desktop component can be suspended above the desktop background. The recommended target video is played through the desktop component, so that the user can quickly browse the videos of interest without opening the mobile phone application.

[0039] This embodiment can push videos more intelligently according to the user's current emotional state, which can greatly improve the user experience.

[0040] In an optional example, in order to make the target video more in line with the preferences of the first user, when determining the target video in step S1300, this embodiment also includes: obtaining the identity information of the first user based on the target monitoring data; searching for the user portrait of the first user from the portraits of multiple users stored in the electronic device based on the identity information of the first user; and / or, in response to the first input of the first user based on the electronic device, extracting the video retrieval information of the first user.

[0041] The identity information of the first user refers to the identity corresponding to the first user in the initial user portrait. The user portrait of the first user can be extracted through the identity information. The user portrait is obtained based on the historical data of the first user, that is, the initial user portrait of the first user is obtained based on the historical browsing of videos or actively input data of the first user on the electronic device.

[0042] The target video of this embodiment may be a video recommended simply based on the emotional state of the first user, or may be a video recommended based on both the emotional state of the first user and the user profile of the first user in the initial user portrait.

[0043] For example, the first user is currently in a tired state, and the initial user portrait of the first user indicates that the first user likes dogs, so the target video is a "funny dog" video.

[0044] In this embodiment, the first input of the first user based on the electronic device may be that the user actively clicks on a link while browsing the web page. For example, the first user clicks on a promotional article of a film or TV work, and the system will record the name of the corresponding film or TV work.

[0045] The first input of the first user based on the electronic device may be the chat content between the user and friends in the chat application. For example, the first user talks about a certain film or TV program in the chat, and then collects the film or TV program.

[0046] The first user may input a first thing into the electronic device, or the user may learn certain knowledge online, and the recommendation system may record the keywords of the corresponding knowledge.

[0047] The first input of the first user based on the electronic device may also be an operation of the user in the interface of any application to share the information in the application interface to the desktop component.

[0048] In this embodiment, the extracted video search information may be any one of text, picture or a combination of text and picture.

[0049] In a feasible embodiment, the video retrieval information may also be hot keywords on a video website.

[0050] The target video of this embodiment can be a video recommended simply based on the emotional state of the first user; it can be a video recommended based on the emotional state of the first user and the user portrait of the first user in the initial user portrait; it can also be a video recommended based on the emotional state of the first user, the user portrait of the first user, and video retrieval information.

[0051] For example, the first user is currently in a tired state, the initial user portrait of the first user indicates that the first user likes dogs, and the video retrieval information indicates that the first user is learning popular science knowledge, then the target video may be a "funny animal science" video.

[0052] In an optional example, since the retrieved target videos may have different video lengths, if the user finds that they are not interested in watching a long video, but has already spent time, the user experience is affected. Therefore, in order to further improve the user experience, reference Figure 3 , step S1300 of this embodiment further includes the following steps S1301 and S1302:

[0053] S1301, performing video retrieval according to the target state information, user portrait and / or video retrieval information of the first user to obtain at least one candidate video;

[0054] In this embodiment, video retrieval can be performed based on any one of the first user's target state information, user portrait, and video retrieval information; video retrieval can be performed based on any two of the first user's target state information, user portrait, and video retrieval information; or video retrieval can be performed based on all three of the first user's target state information, user portrait, and video retrieval information to obtain at least one candidate video.

[0055] S1302: Determine, based on the video durations of the candidate videos, a candidate video whose video duration is within a preset range as a target video.

[0056] Considering that the user cannot accurately determine whether the video is worth watching, or is attracted by the preview image and watches a video that he is not interested in. Therefore, the target video in this embodiment is a short video, and the preset range of the short video can be 1 minute, 2 minutes or 3 minutes. After obtaining the candidate videos, the candidate videos are further screened according to the preset range to obtain the target video. This allows the user to browse the short video on the desktop audio and video component.

[0057] S1303: When the video duration of all candidate videos exceeds a preset range, the candidate videos are edited to obtain edited videos whose video duration is within the preset range as target videos.

[0058] Among them, if the video length of all candidate videos exceeds the preset range, that is, all the retrieved candidate videos are long videos, then in order to obtain a short video, this embodiment also edits the candidate videos to obtain an edited video with a video length within the preset range as the target video.

[0059] In this embodiment, the candidate videos can be edited automatically by the platform, or they can be edited according to the time period when the video is played most frequently on the video website, or according to the time period when the background music or picture elements in the video change, to obtain the target video.

[0060] It should be noted that in this embodiment, when performing video retrieval, it is not limited to the name of the video, but also includes the video section label of the video on various websites and applications, such as "social science", "education", "funny", "creation", "variety show", etc. Use the keywords in "topic" and "introduction" and combine "label" to perform similar retrieval. If no retrieval is found, the label classification conditions will be reduced for retrieval until similar videos are found.

[0061] It is understandable that after obtaining multiple target videos, the target videos need to be recommended to the first user in sequence, that is, the target videos need to be sorted. Then S1400, recommending the target videos to the first user, also includes: sorting the target videos according to preset priority playback information, and recommending the target videos in sequence according to the sorting.

[0062] In this embodiment, the priority playback information includes preset weights of target state information, video retrieval information, and user portrait, and the matching degree of the target video with the target state information, video retrieval information, and user portrait.

[0063] In this embodiment, the preset weights of the target state information, video retrieval information, and user portrait can be user-defined weights or system default weights, for example, the weight of the target state information is greater than the weight of the video retrieval information, and the weight of the video retrieval information is greater than the weight of the user portrait. For example, if the target video contains three target videos related to the target state information, the video retrieval information, and the user portrait at the same time, then the target video related to the target state information is recommended first. Finally, the target video related to the user portrait is recommended.

[0064] It is understandable that the number of retrieved target videos may be large, so each type of target video needs to be sorted. At this time, the sorting is performed based on the matching degree between the target video and the target state information, the video retrieval information, and the user portrait. For example, the target state information of the first user is depression, and the retrieved target video contains 5 healing videos. Then, the 5 healing videos can be sorted according to the healing degree of these 5 healing videos, and the video with the highest healing degree is played first. Among them, the healing degree can be obtained based on the content of the video or the comments of other users.

[0065] This embodiment can prioritize and recommend videos that best meet the needs of users by sorting the target videos, thereby further improving the user experience.

[0066] Taking into account that when a user is watching a short video through a desktop component, if he is interested in the video, he will want to watch the long video corresponding to the short video. Therefore, after determining the target video, this embodiment also includes: in the process of displaying the target video through the desktop component of the electronic device, in response to the second input of the first user based on the desktop component, a candidate video of a first length corresponding to the target video is obtained, and the first length is greater than the video length of the target video.

[0067] refer to Figure 2 The second input of the first user based on the desktop component can be double-clicking the desktop component, or the first user clicking a full-screen button in the desktop component, so that the target video can be played in full screen. After the electronic device receives the second input of the first user, it can retrieve a candidate video of the first duration corresponding to the short video.

[0068] Next, this embodiment is further described by taking the target monitoring data of the electronic device as a scenario in which the first user shares the target monitoring data to the desktop component through a video application. Figure 4 , including the following steps S410 to S480:

[0069] S410, entering the video application.

[0070] The first user can choose to open any video application.

[0071] S420, play the video.

[0072] Select a video you are interested in in the video app and play it.

[0073] S430, sharing the current video to the desktop component.

[0074] When the first user wants to search for more videos related to the current video being watched, he only needs to share the currently playing video in the video application to the desktop component.

[0075] S440, the desktop component determines whether the currently shared video received is a short video.

[0076] If the currently shared video is a short video, execute step S450; if the currently shared video is a long video, execute step S460.

[0077] S450, searching for more short videos and long videos for the currently shared short video.

[0078] Retrieving more short videos here is to allow users to see more videos they want to watch, and retrieving long videos is to meet the needs of users who want to click on the desktop component to watch long videos after watching short videos.

[0079] S460, searching for short videos related to the currently shared short video, and determining whether a short video is detected.

[0080] If a short video is retrieved, execute step S480; if a short video is not retrieved, execute step S470.

[0081] S470, editing the retrieved long video to generate a short video.

[0082] S480, displays short videos through desktop components.

[0083] This embodiment can meet the user's demand for further expansion of sharing video content. At the same time, the recommendation system of the video component can also be used to understand the content displayed in the long video in advance, and preliminarily identify whether to watch it further, further improving the user experience.

[0084] It should be noted that the video recommendation method provided in the embodiment of the present application can be executed by a video recommendation device, or by a control module in the video recommendation device for executing the method for loading video recommendation. In the embodiment of the present application, the video recommendation method provided in the embodiment of the present application is described by taking the video recommendation device executing the method for loading video recommendation as an example.

[0085] refer to Figure 5 This embodiment provides a video recommendation device 500, including:

[0086] A data acquisition module 510 is used to collect target monitoring data;

[0087] A data processing module 520, configured to determine target state information of a first user of the electronic device according to the target monitoring data;

[0088] A video retrieval module 530, configured to perform video retrieval according to the target state information of the first user to determine a target video;

[0089] The recommendation module 540 is configured to recommend the target video to the first user.

[0090] In a feasible example, the data processing module is further used to: obtain the identity information of the first user according to the target monitoring data; find the user portrait of the first user from the portraits of multiple users stored in the electronic device according to the identity information of the first user; and / or,

[0091] In response to a first input of the first user based on the electronic device, video retrieval information of the first user is extracted.

[0092] In a feasible example, the video retrieval module is further used to: perform video retrieval according to the target state information, user portrait and / or video retrieval information of the first user to obtain at least one candidate video;

[0093] According to the video duration of the candidate videos, a candidate video whose video duration is within a preset range is determined as a target video.

[0094] In a feasible example, the video retrieval module is also used to: when the video duration of all the candidate videos exceeds a preset range, edit the candidate videos to obtain edited videos with a video duration within the preset range as target videos.

[0095] In a feasible example, the recommendation module is further used to sort the target videos according to preset priority playback information, wherein the priority playback information includes the weights of the target state information, the video retrieval information, and the user portrait, and the matching degree of the target video with the target state information, the video retrieval information, and the user portrait;

[0096] The recommending the target video to the first user includes: recommending the target videos in sequence according to the ranking.

[0097] In a feasible example, the recommendation module is further used to: display the target video through a desktop component of the electronic device;

[0098] During the presentation process, in response to the second input of the first user based on the desktop component, a candidate video of a first duration corresponding to the target video is obtained, and the first duration is greater than the video duration of the target video.

[0099] This embodiment can push videos more intelligently based on the user's current emotional state, user portrait and user input; it can prioritize the recommendation of videos that best suit the user's needs by sorting the target videos; it can meet the user's needs for further expansion related to sharing video content, and further improve the user experience.

[0100] The video recommendation device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0101] The video recommendation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0102] The video recommendation device provided in the embodiment of the present application can implement each process implemented by the video recommendation device in the method embodiment provided in this embodiment, and will not be described again here to avoid repetition.

[0103] Optionally, an embodiment of the present application further provides an electronic device 600, including a processor 601, a memory 602, and a program or instruction stored in the memory 602 and executable on the processor 601. When the program or instruction is executed by the processor 601, each process of the above-mentioned video recommendation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0104] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0105] Figure 7 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0106] The electronic device 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010 and other components.

[0107] Those skilled in the art will appreciate that the electronic device 1000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1010 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0108] Among them, the processor 1010 is used to collect target monitoring data; determine the target state information of the first user of the electronic device based on the target monitoring data; perform video retrieval based on the target state information of the first user to determine the target video; and recommend the target video to the first user.

[0109] In a feasible example, the processor 1010 is also used to obtain the identity information of the first user based on the target monitoring data; based on the identity information of the first user, search for the user portrait of the first user from the portraits of multiple users stored in the electronic device; and / or, in response to the first input of the first user based on the electronic device, extract the video retrieval information of the first user.

[0110] In a feasible example, the processor 1010 is also used to perform video retrieval based on the target state information, user portrait and / or video retrieval information of the first user to obtain at least one candidate video; based on the video length of the candidate video, determine the candidate video with a video length within a preset range as the target video; or, when the video length of all the candidate videos exceeds the preset range, edit the candidate videos to obtain an edited video with a video length within the preset range as the target video.

[0111] In a feasible example, the processor 1010 is also used to sort the target videos according to priority playback information, the priority playback information including preset weights of the target status information, the video retrieval information and the user portrait, and the matching degree of the target video with the target status information, the video retrieval information and the user portrait; and recommend the target videos in sequence according to the sorting.

[0112] In a feasible example, the processor 1010 is also used to display the target video through the desktop component of the electronic device; during the display process, in response to the second input of the first user based on the desktop component, a candidate video of a first length corresponding to the target video is obtained, and the first length is greater than the video length of the target video.

[0113] It should be understood that in the embodiment of the present application, the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 1009 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 1010.

[0114] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned video recommendation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0115] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0116] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes 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 one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0118] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A video recommendation method, characterized in that: include: Collect target monitoring data; determining target state information of a first user of the electronic device according to the target monitoring data; Perform video retrieval according to the target state information of the first user to determine the target video; recommending the target video to the first user; Before performing video retrieval according to the target state information of the first user, the method further includes: Obtaining identity information of the first user according to the target monitoring data; searching, according to the identity information of the first user, for a user portrait of the first user from portraits of a plurality of users stored in the electronic device; In response to a first input of the first user based on the electronic device, extracting video retrieval information of the first user; The step of performing video retrieval according to the target state information of the first user to determine the target video includes: Perform video retrieval according to the target state information, user portrait and video retrieval information of the first user to obtain at least one candidate video, and determine, according to the video duration of the candidate videos, a candidate video whose video duration is within a preset range as a target video; or When the video durations of all the candidate videos exceed a preset range, the candidate videos are edited to obtain edited videos with video durations within the preset range as target videos.

2. The method according to claim 1, characterized in that When the number of the target videos is greater than 1, the method includes: Sorting the target videos according to priority playback information, the priority playback information including preset weights of the target state information, the video retrieval information, and the user portrait, and a matching degree between the target video and the target state information, the video retrieval information, and the user portrait; The recommending the target video to the first user includes: recommending the target videos in sequence according to the ranking.

3. The method according to claim 1, characterized in that After determining the target video, the method further includes: Displaying the target video through a desktop component of the electronic device; During the presentation process, in response to the second input of the first user based on the desktop component, a candidate video of a first duration corresponding to the target video is obtained, and the first duration is greater than the video duration of the target video.

4. A video recommendation device, characterized in that: include: A data acquisition module, used to collect target monitoring data; A data processing module, configured to determine target state information of a first user of the electronic device according to the target monitoring data; A video retrieval module, used to perform video retrieval according to the target state information of the first user to determine a target video; A recommendation module, configured to recommend the target video to the first user; The data processing module is further used to: obtain the identity information of the first user according to the target monitoring data; and find the user portrait of the first user from the portraits of multiple users stored in the electronic device according to the identity information of the first user; In response to a first input of the first user based on the electronic device, extracting video retrieval information of the first user; The video retrieval module is further used to: perform video retrieval according to the target state information, user portrait and video retrieval information of the first user to obtain at least one candidate video, and determine, according to the video duration of the candidate video, a candidate video whose video duration is within a preset range as a target video; or When the video durations of all the candidate videos exceed a preset range, the candidate videos are edited to obtain edited videos with video durations within the preset range as target videos.

5. The device according to claim 4, characterized in that The recommendation module is further used to sort the target videos according to priority playback information, wherein the priority playback information includes preset weights of the target state information, the video retrieval information, and the user portrait, and a matching degree between the target video and the target state information, the video retrieval information, and the user portrait; The recommending the target video to the first user includes: recommending the target videos in sequence according to the ranking.

6. The device according to claim 4, characterized in that The recommendation module is also used to: display the target video through the desktop component of the electronic device; During the presentation process, in response to the second input of the first user based on the desktop component, a candidate video of a first duration corresponding to the target video is obtained, and the first duration is greater than the video duration of the target video.

Images