Interaction method for video and processing method and device for video

Abstract

The present invention provides an interactive method for video and a processing method, device, equipment, medium, and program product for video, which relate to the field of artificial intelligence technology, especially to the technical fields of human-computer interaction, natural language processing, and large models, and can be used in application scenarios such as generative search, document intelligent editing, intelligent assistants, and intelligent e-commerce. The specific implementation scheme of the interactive method for video is: in response to the video playing to a predetermined time, the interactive recommendation information corresponding to the predetermined time is displayed on the video playback page; the interactive recommendation information and the predetermined time are predetermined by the large language model based on the video content; and in response to the selection operation on the interactive recommendation information, the interactive content corresponding to the interactive recommendation information is displayed on the playback page.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to technical fields such as human-computer interaction, natural language processing and large models, and can be used in application scenarios such as generative search, intelligent document editing, intelligent assistants, and intelligent e-commerce. Background Art

[0002] With the development of computer technology and network technology, the application of artificial intelligence technology is becoming more and more extensive, and artificial intelligence technology has made breakthrough progress in various fields. Among them, artificial intelligence generated content (AI generated content, AIGC) is an important direction of deep learning.

[0003] With the rapid development of AIGC technology, for example, intelligent dialogue can be conducted based on AIGC technology to provide intelligent services. Summary of the invention

[0004] The present invention aims to provide an interactive method for video and a processing method, device, equipment, medium and program product for video, which can improve the immersion and participation of users in watching videos, so as to solve the technical problem of low immersion and participation of users when watching videos due to a single interactive method in the related art.

[0005] According to a first aspect of the present invention, there is provided an interactive method for a video, comprising: in response to the video being played to a predetermined time, displaying interactive recommendation information corresponding to the predetermined time in a playback page of the video; the interactive recommendation information and the predetermined time are predetermined by a large language model based on the video content of the video; and in response to a selection operation on the interactive recommendation information, displaying interactive content corresponding to the interactive recommendation information in the playback page.

[0006] According to a second aspect of the present invention, a method for processing a video is provided, comprising: using a large language model to determine first interactive recommendation information for a video and a first playback time corresponding to the first interactive recommendation information based on the video content of the video; and in response to a request to obtain the video, sending the video, the first interactive recommendation information, and the correspondence between the first interactive recommendation information and the first playback time to a terminal device requesting to obtain the video.

[0007] According to a third aspect of the present invention, there is provided an interactive device for videos, comprising: a first display module, for displaying interactive recommendation information corresponding to the predetermined time in a playback page of the video in response to the video being played to a predetermined time; the interactive recommendation information and the predetermined time are predetermined by a large language model based on the video content of the video; and a second display module, for displaying interactive content corresponding to the interactive recommendation information in the playback page in response to a selection operation on the interactive recommendation information.

[0008] According to a fourth aspect of the present invention, there is provided a processing device for a video, comprising: an information determination module for determining first interactive recommendation information for a video and a first playback time corresponding to the first interactive recommendation information based on the video content of the video using a large language model; and an information sending module for sending the video, the first interactive recommendation information, and the correspondence between the first interactive recommendation information and the first playback time to a terminal device requesting to obtain the video in response to a request to obtain the video.

[0009] According to a fifth aspect of the present invention, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the interactive method for video or the processing method for video provided by the present invention.

[0010] According to a sixth aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the interactive method for video or the processing method for video provided by the present invention.

[0011] According to a seventh aspect of the present invention, there is provided a computer program product, comprising a computer program / instruction, wherein the computer program / instruction is stored on at least one of a readable storage medium and an electronic device, and wherein the computer program / instruction, when executed by a processor, implements the interactive method for video or the processing method for video provided by the present invention.

[0012] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0014] Figure 1 It is a schematic diagram of an application scenario of an interactive method for a video and a processing method and device for a video according to an embodiment of the present invention;

[0015] Figure 2 is a flow chart of a video interaction method according to an embodiment of the present invention;

[0016] Figure 3 is a schematic diagram of interaction with a video according to a first embodiment of the present invention;

[0017] Figure 4 is a schematic diagram of interaction with a video according to a second embodiment of the present invention;

[0018] Figure 5 is a flow chart of a method for processing a video according to an embodiment of the present invention;

[0019] Figure 6 is a structural block diagram of a video interaction device according to an embodiment of the present invention;

[0020] Figure 7 is a structural block diagram of a video processing device according to an embodiment of the present invention; and

[0021] Figure 8 It is a block diagram of an electronic device for implementing the video interaction method or the video processing method according to the embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0023] The current interactive mode of video is single, and users can only passively accept content, lacking personalization and interactivity. The one-way interactive mode will not only reduce the user's immersion and participation, but may also cause users to lose interest in the video playback platform, thereby reducing the activity and user stickiness of the video playback platform.

[0024] For example, in existing interactive methods, users can like their favorite videos to express their preference for the video content, but this interactive method is one-sided, and the user's immersion and participation are low. Users can also send real-time comments during video playback, but this interactive process requires users to provide real-time comment content, and users often give up due to the high discussion cost, resulting in low user immersion and participation.

[0025] In order to solve the problems existing in the related art, the present invention provides an interactive method for video and a processing method, device, equipment, medium and program product for video. Figure 1 The application scenarios of the method and device provided by the present invention are described.

[0026] Figure 1 The present invention is a schematic diagram of an application scenario of a video interaction method and a video processing method and device according to an embodiment of the present invention.

[0027] like Figure 1 As shown, the application scenario 100 of this embodiment may include a terminal device 110, which may be various electronic devices with display functions and interactive functions, including but not limited to smart phones, tablet computers, portable computers, desktop computers, servers, etc.

[0028] For example, a client application or search engine for playing videos may be installed in the terminal device 110, and the video may be any video such as an advertisement video, a TV series, a movie, or a short video, which is not limited in the present invention. For example, in an application scenario, a short video platform may be installed in the terminal device 110, and the video is a video played on the short video platform.

[0029] In one embodiment, the terminal device 110 may, for example, display the interactive recommendation information in the video playback page in response to the predetermined time when playing the video. Then, in response to the user 120's interactive operation with the interactive recommendation information, the interactive content is displayed in the video playback page. The interactive recommendation information may include recommended comment information, recommended item links, recommended gifts, etc., which are not limited in the present invention. The predetermined time may be a pre-set playback time, such as the playback time of a key frame, etc., which are not limited in the present invention.

[0030] like Figure 1 As shown, the application scenario 100 may also include a server 130. The terminal device 110 may be connected to the server 130 through a network. For example, the server 130 may be a background management server for providing support for the operation of the client application installed in the terminal device. The server 130 may also be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server 130 may also be a server of a distributed system, or a server combined with a blockchain.

[0031] For example, the server 130 can use a large language model to decide the interactive recommendation information that can be displayed and the display timing of the interactive recommendation information based on the video content of the video, and when the terminal device 110 requests a video, the server 130 sends the decided information and the video to the terminal device 110, so that the terminal device 110 displays the interactive recommendation information when the video is played to a predetermined time.

[0032] It should be noted that the interactive method for video provided by the present invention can be executed by the terminal device 110. Accordingly, the interactive device for video provided by the present invention can be set in the terminal device 110. The processing method for video provided by the present invention can be executed by the server 130. Accordingly, the processing device for video provided by the present invention can be set in the server 130.

[0033] It should be understood that Figure 1 The number and type of the terminal devices 110 and the server 130 in the embodiment are only for illustration. According to the implementation requirements, there may be any number and type of the terminal devices 110 and the server 130.

[0034] The following will be combined Figure 2~Figure 4 The interactive method for videos provided by the present invention is described in detail.

[0035] Figure 2 It is a flowchart of a video interaction method according to an embodiment of the present invention.

[0036] like Figure 2 As shown, the video interaction method 200 of this embodiment may include operations S210 to S220.

[0037] In operation S210, in response to the video being played to a predetermined time, interactive recommendation information corresponding to the predetermined time is displayed in a playback page of the video.

[0038] According to an embodiment of the present invention, a large language model can be used to generate interactive recommendation information based on the video content of a video. The interactive recommendation information may include, for example, recommended commentary information, recommended item links, recommended gifts, recommended knowledge links (such as introduction information of role players in the video), and any other recommendation information that can guide users to interact. The video content may include one or more of a video synopsis, a video script, and a plot summary.

[0039] For example, the large language model can determine the interactive recommendation information and the display time of the interactive recommendation information (i.e., the scheduled time when the video is played) based on the video content. Then, the terminal device can display the interactive recommendation information when it is determined that the video is played to the display time. It is understandable that the display time of the interactive recommendation information is based on the playback time of the starting video frame in the video.

[0040] In operation S220 , in response to a selection operation on the interactive recommendation information, interactive content corresponding to the interactive recommendation information is displayed in a play page.

[0041] For example, when the interactive recommendation information is comment information, in response to a selection operation on the interactive recommendation information, the comment information can be used as interactive content and displayed in the form of a bullet screen on the video playback page.

[0042] For example, when the interactive recommendation information is an item link, in response to a selection operation on the interactive recommendation information, the transaction page or the detail page of the item can be used as interactive content and displayed on the video playback page.

[0043] For example, when the interactive recommendation information is a gift that can be given, in response to a selection operation on the interactive recommendation information, the payment page for the gift that can be given or the giving animation corresponding to the gift that can be given can be used as interactive content and displayed in the video playback page.

[0044] The technical solution of the embodiment of the present invention can increase the scenarios where users actively select interactive content by displaying interactive recommendation information when the video is played to a predetermined time, and displaying interactive content based on the interaction with the interactive recommendation information. Compared with the scenarios where users need to actively provide interactive content and users can only passively accept content, two-way interaction between videos and users can be achieved, increasing the interactivity between users and videos, and thus improving the user stickiness of the video playback platform.

[0045] In one embodiment, the interactive recommendation information displayed when the video is played to a predetermined time may include the guidance content and the identification information of the target virtual object displayed in association with the guidance content. The target virtual object is one of a plurality of predetermined virtual objects corresponding to a plurality of key characters in the video. The identification information may be, for example, an image of the virtual object, or the name of the key character corresponding to the virtual object, a still of the corresponding key character, etc., and the present invention does not limit this.

[0046] For example, the target virtual object and the guide content can both be determined by the large language model based on the video content and the role information of multiple key roles. The role information may include the introduction information of the role and / or the personality of the role, etc. For example, the role information and video content of multiple key roles can be input into the large language model, and the large language model generates the indication information, guide content, and the display time of the guide content of the selected key role, etc., and then the target virtual object can be determined based on the indication information of the selected key role.

[0047] For example, the virtual object can be a digital person corresponding to the character in the video, which is constructed by the large language model based on the video content and character information. Specifically, the server can use the character information and video content of the character in the video to train the base model, so that the model learns the characteristics of the character in the video, thereby obtaining the large language model corresponding to the virtual object. By using the large language model to analyze the video content, it is possible to generate instruction information, guide content, and the display time of the guide content of the selected key role. Among them, the base model can be an arbitrary, open source pre-trained large language model, and the present invention does not limit this.

[0048] This embodiment can achieve the effect of information recommendation by the characters in the video by using the identification information of the target virtual object as part of the interactive recommendation information and displaying it in association with the text content in the interactive recommendation information, thereby improving the user's immersion in interacting with the characters in the video during the video viewing process and improving the user activity and user stickiness of the video playback platform.

[0049] According to an embodiment of the present invention, a large language model may be obtained by fine-tuning an existing pre-trained large model. The pre-trained large model may be any large model such as Wenxin Yiyan, and the video content may be used as a sample to fine-tune the pre-trained large model with the goal of generating pre-set interactive recommendation information. In one embodiment, the large language model obtained by fine-tuning may be a model capable of performing multiple tasks. The multiple tasks may include, for example, decision-making tasks, content generation tasks, and tool / model calling tasks, etc., which are not limited by the present invention.

[0050] In one embodiment, the interactive recommendation information may be generated offline by the server to reduce the cost of information generation and the delay of information display. Specifically, the interactive recommendation information may be generated by the server before the terminal device requests to obtain the video.

[0051] In one embodiment, the interactive recommendation information may also be generated online by the server and pushed to the terminal device after being generated, so that the terminal device can display it when the video is played to the predetermined time. It is understandable that the timing of the server generating the interactive recommendation information online should be slightly earlier than the timing of the video playing to the predetermined time. For example, the server can generate the interactive recommendation information in a timely manner after the terminal device obtains the video.

[0052] For example, when generating interactive recommendation information, the portrait information of the video viewers can also be considered. Specifically, the big language model can generate interactive recommendation information based on the video content and the portrait information of the video viewers. This makes the generated interactive recommendation information different for each person, and the big language model is used as the voice of the viewers to help the viewers express their emotions, thereby increasing the viewers' participation and immersion in the video they are watching.

[0053] For example, the large language model can learn the role information of the characters in the video offline. During the online reasoning process, the input of the large language model may include the video content and the portrait information of the viewing object of the video, and the output of the large language model may include the indication information of the target virtual object, the guide content and the display time of the guide content. Alternatively, during the online reasoning process, the input of the large language model may include the role information of multiple key characters in the video in addition to the video content and the portrait information of the viewing object. The input information and output information of the large language model can be set according to actual needs by fine-tuning the large language model, and the present invention is not limited to this.

[0054] In one embodiment, the predetermined time may include the playback time of a key video frame in the video. The key video frame may be, for example, a video frame in which a protagonist appears in the video, or a video frame reflecting a plot with a conflict, or a video frame reflecting a climax plot, etc., which is not limited in the present invention. The strategy for determining the predetermined time is obtained by the large language model through the samples used in learning fine-tuning.

[0055] The video interaction method provided by the present invention will be described in detail below in combination with two scenarios.

[0056] Figure 3 FIG. 4 is a schematic diagram of interaction with a video according to the first embodiment of the present invention.

[0057] like Figure 3 As shown, in the embodiment 300, when the video is played to the predetermined moment, the display interface of the terminal device is the first interface 310. Among them, the interactive recommendation information displayed may include comment information 311, and the comment information 311 may include one or more pieces of information, which is not limited by the present invention. The comment information 311 may be a comment on the plot described in the video. After responding to the selection operation of the comment information 311, the display interface is updated from the first interface 310 to the second interface 320, in which the selected comment information 311 is displayed in a predetermined area in the video playback area, which may be, for example, the top area, etc., and the comment information 311 is displayed in a scrolling manner. That is, the selected comment information 311 is displayed as a bullet screen. It can be understood that when the comment information includes multiple pieces of information, the selected comment information may be one or at least two of the multiple pieces of information, which is not limited by the present invention.

[0058] In one embodiment, the interactive recommendation information may also include comment topic information 312 and identification information 313 of the target virtual object displayed in association with the comment topic information 312. The comment topic information 312 and the comment information 311 may constitute the aforementioned guide content. By displaying the comment topic information 312 in association with the identification information 313, the effect of the comment topic being brought out by the character in the video may be achieved, thereby increasing the user's interest in selecting comment information and improving the user's immersion and participation in watching the video.

[0059] Figure 4 FIG. 4 is a schematic diagram of interaction with a video according to a second embodiment of the present invention.

[0060] like Figure 4 As shown, in embodiment 400, when the video is played to the predetermined moment, the display interface of the terminal device is the first interface 410. Among them, the interactive recommendation information displayed includes the preview information 411 of the subsequent video and the unlock link 412 for the subsequent video. For example, the preview information 411 can be, for example, "High energy warning ahead, will I choose..." etc. It can be understood that the preview information 411 can be, for example, information expressed from the perspective of the viewing object, such as "Will character A...", or information expressed from the key characters in the video, such as "Will I go to a certain city to find XX", etc. The unlock link 412 can be displayed through the unlock theme "Unlock subsequent episodes immediately", etc., and the present invention is not limited to this. In this embodiment, the preview information 411 and the unlock link 412 constitute the aforementioned guide content.

[0061] For example, in response to the selection operation of the unlock link 412 in the interactive recommendation information, the display interface is updated from the first interface 410 to the second interface 420, and the interactive content displayed in the second interface 420 is a transaction page 421 related to unlocking. For example, the transaction page 421 may provide options for selecting the viewing range of videos after unlocking, such as an option to watch the entire video after unlocking, an option to watch the current video after unlocking, etc. The transaction page 421 may also include a control for confirming the unlocking and / or a payment option and a payment control for paying for the unlocked video, etc., which are not limited in the present invention.

[0062] In one embodiment, the interactive recommendation information may further include identification information 413 of the target virtual object displayed in association with the preview information 411. By displaying the preview information 411 in association with the identification information 413, the preview information may be introduced by the character in the video, thereby increasing the probability of the user unlocking the subsequent video, thereby increasing the revenue of the video conversion as much as possible while improving the immersion and participation of the user when watching the video.

[0063] It is understandable that the above-mentioned preview information and unlocking links are only used as examples to facilitate understanding of the present invention. According to actual needs, the interactive recommendation information may include any consumption guidance information and corresponding consumption links. In response to the selection operation of the consumption link in the interactive recommendation information, the consumption transaction page may be displayed in the playback page. In one embodiment, the interactive recommendation information may also include identification information of the target virtual object displayed in association with the consumption guidance information, so as to achieve the effect that the consumption guidance information is provided by the key characters in the video, so as to promote consumption conversion.

[0064] For example, the interactive recommendation information may include recommendation information of a specified item and an item link of the specified item. In response to a selection operation on the item link, the interactive content displayed in the play page may be a transaction page of the specified item.

[0065] In one embodiment, the designated item may be, for example, an item associated with a character in a video frame played at a predetermined time. For example, the designated item may be an item worn or used by a character in a video frame played at a predetermined time, and the present invention is not limited thereto.

[0066] According to an embodiment of the present invention, when the interactive recommendation information is determined by online reasoning of a large language model, since the large language model takes into account the portrait information of the viewing object when determining the interactive recommendation information, the determined target virtual object is the virtual object corresponding to the character that the viewing object is interested in, thereby further improving the consumption conversion rate. Among them, the portrait information can, for example, reflect the static attributes and dynamic attributes of the viewing object. The dynamic attributes can, for example, reflect the actors that the viewing object likes, the plot types that the viewing object likes, the types of items that the viewing object likes, etc., and the present invention does not limit this.

[0067] In order to facilitate the implementation of the interactive method for video provided by the present invention, the present invention also provides a processing method for video. Figure 5 The video processing method provided by the present invention is described in detail.

[0068] Figure 5 It is a flowchart of a method for processing a video according to an embodiment of the present invention.

[0069] like Figure 5 As shown, the video processing method 500 of this embodiment includes operations S510 to S520.

[0070] In operation S510, a large language model is used to determine first interactive recommendation information for a video and a first play time corresponding to the first interactive recommendation information based on the video content of the video.

[0071] According to an embodiment of the present invention, the server can generate interactive recommendation information for each newly stored video in the database. Specifically, the server can use the video content of each video as the input of the fine-tuned large language model, and the large language model outputs the interactive recommendation information and the playback time corresponding to the interactive recommendation information. In order to facilitate the large language model to output the interactive recommendation information and the playback time, for example, prompt information can also be input into the large language model. The prompt information can be, for example, an example of generating interactive recommendation information and the corresponding playback time, or a guide phrase such as "Based on the video content XXX, determine the timing of the recommendation information and the recommended information", etc. The present invention does not limit this.

[0072] According to an embodiment of the present invention, after generating interactive recommendation information and the corresponding playback time for a video, the interactive recommendation information and the corresponding playback time may be stored in association, and the identification information of the video may be used as an index of the stored association information, so as to facilitate the acquisition of the stored association information.

[0073] In operation S520, in response to the acquisition request for the video, the video, the first interactive recommendation information, and the corresponding relationship between the first interactive recommendation information and the first play time are sent to the terminal device that requests to acquire the video.

[0074] When receiving a request for obtaining a video from a terminal device, the server can send the video and associated information indexed by the identification information of the video (i.e., the first interactive recommendation information associated with the first playback time) to the terminal device, so that the terminal device can execute the interactive method for the video.

[0075] In one embodiment, the information generated by the large language model based on the input video content may include guide content and indication information of the target role associated with the guide content. This embodiment can use the identification information of the target virtual object corresponding to the target role and the guide content as interactive recommendation information. Accordingly, the guide words input into the large language model can be, for example, "Based on the video content XXX, determine the timing of recommending information and the recommended information and the role of the recommended information", etc., and the present invention does not limit this.

[0076] According to an embodiment of the present invention, a request for obtaining a video may, for example, include identification information of a viewing object corresponding to a terminal device. For example, the server may obtain portrait information of the viewing object based on the identification information of the viewing object. After the server receives the acquisition request, a large language model may be used to generate second interactive recommendation information and a second playback time corresponding to the second interactive recommendation information based on the acquired portrait information and the video content of the requested video. In this way, the generated interactive recommendation information can be made more in line with the preferences of the viewing object of the video, which is conducive to improving the recommendation effect of the interactive recommendation information and improving the sense of participation and immersion of the viewing object of the video in watching the video. After generating the second interactive recommendation information and the second playback time corresponding to the second interactive recommendation information, the server may send the second interactive recommendation information and the corresponding relationship between the second interactive recommendation information and the second playback time to the terminal device requesting the video, so that the terminal device displays the second interactive recommendation information at the second playback time.

[0077] It is understandable that the generation principle of the second interactive recommendation information and the second playback time is similar to the generation principle of the aforementioned first interactive recommendation information and the first playback time, and will not be repeated here.

[0078] When the terminal device plays a video, both the first interactive recommendation information and the second interactive recommendation information may be used as interactive recommendation information to be displayed, so that the interactive recommendation information is displayed when the video is played to the playback time corresponding to the interactive recommendation information.

[0079] It is understandable that the aforementioned video may be an advertising video. Through the aforementioned embodiments, the effect of real interaction between the characters in the advertising video and the advertising viewers can be achieved, thereby improving the advertising conversion rate to a certain extent.

[0080] Based on the interactive method for video provided by the present invention, the present invention also provides an interactive device for video. Figure 6 The device is described in detail.

[0081] Figure 6 4 is a structural block diagram of a video interaction device according to an embodiment of the present invention.

[0082] like Figure 6 As shown, the interactive device 600 for video in this embodiment includes a first display module 610 and a second display module 620 .

[0083] The first display module 610 is used to display the interactive recommendation information corresponding to the predetermined time in the video playback page in response to the video playing to the predetermined time. The interactive recommendation information and the predetermined time are predetermined by the large language model based on the video content of the video. In one embodiment, the first display module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0084] The second display module 620 is used to display the interactive content corresponding to the interactive recommendation information in the play page in response to the selection operation on the interactive recommendation information. In one embodiment, the second display module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0085] According to an embodiment of the present invention, the interactive recommendation information includes the guiding content and the identification information of the target virtual object displayed in association with the guiding content. The target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond one to one with a plurality of key characters in the video. The target virtual object and the guiding content are determined by the large language model based on the video content and the role information of the plurality of key characters.

[0086] According to an embodiment of the present invention, the interactive recommendation information and the scheduled time are generated by a large language model based on the video content and the portrait information of the viewing object of the video.

[0087] According to an embodiment of the present invention, the interactive recommendation information includes comment information. The second display module 620 may be specifically configured to display the comment information in a scrolling manner in a predetermined area of ​​the video playback area in response to a selection operation on the comment information.

[0088] According to an embodiment of the present invention, the predetermined time includes the playback time of the key video frame in the video. The above-mentioned interactive recommendation information may also include: comment topic information and identification information of the target virtual object displayed in association with the comment topic information; the comment topic information corresponds to the comment information. Among them, the target virtual object is one of multiple predetermined virtual objects, and the multiple predetermined virtual objects correspond one-to-one to multiple key characters in the video.

[0089] According to an embodiment of the present invention, the interactive recommendation information includes a consumption link. The second display module 620 may be specifically configured to display a transaction page associated with the consumption link in the playback page in response to a selection operation on the consumption link.

[0090] According to an embodiment of the present invention, the interactive recommendation information may further include consumption guidance information and identification information of a target virtual object displayed in association with the consumption guidance information, wherein the target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond one-to-one to a plurality of key characters in the video.

[0091] According to an embodiment of the present invention, the consumption link includes an unlocking link for a subsequent video; the consumption guidance information includes preview information of the subsequent video; or the consumption link includes an item link of a specified item; the consumption guidance information includes recommendation information of the specified item; wherein the specified item is associated with a character in a video frame played at a predetermined time.

[0092] Based on the method for processing a video provided by the present invention, the present invention also provides a device for processing a video. Figure 7 The device is described in detail.

[0093] Figure 7 4 is a structural block diagram of a video processing device according to an embodiment of the present invention.

[0094] like Figure 7 As shown, the video processing device 700 of this embodiment may include an information determination module 710 and an information sending module 720 .

[0095] The information determination module 710 is used to determine the first interactive recommendation information for the video and the first play time corresponding to the first interactive recommendation information based on the video content of the video using the large language model. In one embodiment, the information determination module 710 can be used to perform the operation S510 described above, which will not be repeated here.

[0096] The information sending module 720 is used to send the video, the first interactive recommendation information, and the corresponding relationship between the first interactive recommendation information and the first playback time to the terminal device requesting to obtain the video in response to the acquisition request for the video. In one embodiment, the information sending module 720 can be used to perform the operation S520 described above, which is not repeated here.

[0097] According to an embodiment of the present invention, the information determination module 710 may include a content determination submodule and an information determination submodule. The content determination submodule is used to determine the guide content and the target role associated with the guide content based on the video content and the role information of multiple key roles in the video using a large language model. The information determination submodule is used to use the guide content and the identification information of the target virtual object corresponding to the target role as the first interactive recommendation information. The target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond one-to-one to the plurality of key roles.

[0098] According to an embodiment of the present invention, the information determination module 710 may also be used to determine the second interactive recommendation information for the video and the second playback time corresponding to the second interactive recommendation information based on the video content and the portrait information of the viewing object corresponding to the terminal device after receiving the acquisition request. The information sending module 720 may also be used to send the second interactive recommendation information and the corresponding relationship between the second interactive recommendation information and the second playback time to the terminal device.

[0099] It should be noted that the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations, necessary confidentiality measures are taken, and they do not violate public order and good morals. In the technical solution of the present invention, the user's authorization or consent is obtained before obtaining or collecting user personal information.

[0100] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0101] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an interactive method for a video or a processing method for a video of an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0102] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0103] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0104] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as an interactive method for a video or a processing method for a video. For example, in some embodiments, an interactive method for a video or a processing method for a video may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the interactive method for a video or the processing method for a video described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute an interactive method for a video or a processing method for a video in any other appropriate manner (for example, by means of firmware).

[0105] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0109] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0110] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. Among them, the server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and this document does not limit this.

[0112] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An interactive method for a video, characterized in that: The method comprises: In response to the video being played to a predetermined time, displaying interactive recommendation information corresponding to the predetermined time in the playback page of the video; the interactive recommendation information and the predetermined time are predetermined by the large language model based on the video content of the video; and In response to a selection operation on the interactive recommendation information, displaying interactive content corresponding to the interactive recommendation information in the play page, including: in response to a selection operation on comment information, scrollingly displaying the comment information in a predetermined area in the video play area; Among them, the interactive recommendation information includes guidance content, and the guidance content includes corresponding comment topic information and the comment information; the interactive recommendation information also includes: identification information of a target virtual object displayed in association with the comment topic information; the target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond one-to-one to a plurality of key characters in the video; the target virtual object and the guidance content are determined by the large language model based on the video content and the role information of the plurality of key characters.

2. The method according to claim 1, characterized in that The interactive recommendation information and the scheduled time are generated by the large language model based on the video content and the portrait information of the viewing object of the video.

3. The method according to claim 1, characterized in that: The predetermined time includes the playback time of the key video frame in the video.

4. The method according to claim 1, characterized in that The interactive recommendation information includes a consumption link; and the interactive content corresponding to the interactive recommendation information displayed on the play page includes: In response to a selection operation on the consumption link, a transaction page associated with the consumption link is displayed in the play page.

5. The method according to claim 4, characterized in that: The interactive recommendation information also includes consumption guidance information and identification information of a target virtual object displayed in association with the consumption guidance information.

6. The method according to claim 5, characterized in that: The consumption link includes an unlocking link for the subsequent video; the consumption guidance information includes preview information of the subsequent video; The consumption link includes an item link of a designated item; the consumption guidance information includes recommendation information of the designated item; wherein the designated item is associated with a character in a video frame played at the predetermined time.

7. A method for processing a video, characterized in that: The method comprises: Using a large language model to determine first interactive recommendation information for a video and a first playback time corresponding to the first interactive recommendation information based on the video content of the video, including: using the large language model to determine a guide content and a target role associated with the guide content based on the video content and role information of multiple key roles in the video, and using the guide content and identification information of a target virtual object corresponding to the target role as the first interactive recommendation information; wherein the target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond to the plurality of key roles one-to-one; and In response to a request for obtaining the video, sending the video, the first interactive recommendation information, and a corresponding relationship between the first interactive recommendation information and the first playback time to a terminal device that requests to obtain the video; After receiving the acquisition request, the large language model is used to determine the second interactive recommendation information for the video and the second playback time corresponding to the second interactive recommendation information based on the video content and the portrait information of the viewing object corresponding to the terminal device; and the second interactive recommendation information and the correspondence between the second interactive recommendation information and the second playback time are sent to the terminal device.

8. An interactive device for video, characterized in that: The device comprises: A first display module is used for displaying interactive recommendation information corresponding to the predetermined time in the playback page of the video in response to the video being played to the predetermined time; the interactive recommendation information and the predetermined time are predetermined by the large language model based on the video content of the video; and A second display module is used to display the interactive content corresponding to the interactive recommendation information in the play page in response to the selection operation on the interactive recommendation information, including: in response to the selection operation on the comment information, scrollingly displaying the comment information in a predetermined area in the video play area; Among them, the interactive recommendation information includes guidance content, and the guidance content includes corresponding comment topic information and the comment information; the interactive recommendation information also includes: identification information of a target virtual object displayed in association with the comment topic information; the target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond one-to-one to a plurality of key characters in the video; the target virtual object and the guidance content are determined by the large language model based on the video content and the role information of the plurality of key characters.

9. The device according to claim 8, characterized in that The interactive recommendation information and the scheduled time are generated by the large language model based on the video content and the portrait information of the viewing object of the video.

10. The device according to claim 8, characterized in that: The predetermined time includes the playback time of the key video frame in the video.

11. The device according to claim 8, characterized in that The interactive recommendation information includes a consumption link; and the second display module is used for: In response to a selection operation on the consumption link, a transaction page associated with the consumption link is displayed in the play page.

12. The device according to claim 11, characterized in that: The interactive recommendation information also includes consumption guidance information and identification information of a target virtual object displayed in association with the consumption guidance information.

13. The device according to claim 12, characterized in that: The consumption link includes an unlocking link for the subsequent video; the consumption guidance information includes preview information of the subsequent video; The consumption link includes an item link of a designated item; the consumption guidance information includes recommendation information of the designated item; wherein the designated item is associated with a character in a video frame played at the predetermined time.

14. A video processing device, characterized in that: The device comprises: an information determination module, configured to determine first interactive recommendation information for the video and a first playback time corresponding to the first interactive recommendation information based on the video content of the video by using a large language model; and an information sending module, configured to send, in response to a request for obtaining the video, the video, the first interactive recommendation information, and a corresponding relationship between the first interactive recommendation information and the first playback time to a terminal device that requests to obtain the video; Wherein, the information determination module includes: a content determination submodule, configured to determine, using the large language model, a guide content and a target role associated with the guide content based on the video content and role information of a plurality of key roles in the video; and an information determination submodule, configured to use the guidance content and identification information of a target virtual object corresponding to the target role as the first interactive recommendation information; wherein the target virtual object is one of a plurality of predetermined virtual objects, and the plurality of predetermined virtual objects correspond to the plurality of key roles one by one; The information determination module is further configured to: after receiving the acquisition request, determine the second interactive recommendation information for the video and the second playback time corresponding to the second interactive recommendation information based on the video content and the portrait information of the viewing object corresponding to the terminal device using the large language model; The information sending module is further used for sending the second interactive recommendation information and the corresponding relationship between the second interactive recommendation information and the second playback time to the terminal device.

15. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

17. A computer program product, characterized in that The product comprises a computer program / instruction, wherein the computer program / instruction is stored on at least one of a readable storage medium and an electronic device, and when the computer program / instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images