Large model-based information display method, device, equipment and medium

Abstract

The present disclosure provides a large model-based information display method, device, equipment and medium, relating to the technical field of artificial intelligence, especially relating to the technical field of natural language processing and deep learning, which can be used in generative search, document intelligent editing, intelligent assistant, virtual assistant, intelligent e-commerce and other application scenarios. The method comprises: displaying a video playing page, the video playing page comprising a video playing area playing a first target video and a dialogue interaction object; in response to detecting a first operation on the dialogue interaction object, displaying a dialogue area in the video playing page; obtaining a first user input from the dialogue area; calling a large model generation module using the first user input to obtain a first reply result; and displaying the first reply result in the dialogue area.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the fields of natural language processing and deep learning, and can be used in application scenarios such as generative search, intelligent document editing, intelligent assistants, virtual assistants, and intelligent e-commerce. Specifically, it relates to an information display method based on a large model, an information display device based on a large model, an electronic device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include natural language processing, computer vision, speech recognition, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0003] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0004] This disclosure provides a method for displaying information based on a large model, an information display device based on a large model, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to one aspect of this disclosure, a method for displaying information based on a large model is provided, comprising: displaying a video playback page, the video playback page including a video playback area for playing a first target video and a dialogue interaction object; in response to detecting a first operation on the dialogue interaction object, displaying a dialogue area in the video playback page; obtaining a first user input from the dialogue area; using the first user input to call a large model generation module to obtain a first response result; and displaying the first response result in the dialogue area.

[0006] According to another aspect of this disclosure, a large-model-based information display device is provided, comprising: a first display unit configured to display a video playback page, the video playback page including a video playback area for playing a first target video and a dialogue interaction object; a second display unit configured to display a dialogue area in the video playback page in response to detecting a first operation on the dialogue interaction object; an acquisition unit configured to acquire first user input from the dialogue area; a large-model generation module invocation unit configured to invoke a large-model generation module using the first user input to obtain a first response result; and a third display unit configured to display the first response result in the dialogue area.

[0007] According to another aspect of this disclosure, an electronic device is provided, 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 to enable the at least one processor to perform the methods described above.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the above-described method.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-described method when executed by a processor.

[0010] According to one or more embodiments of this disclosure, by embedding a dialogue area on the video playback page, this disclosure effectively helps users to explore and understand the video in depth without leaving the video playback page, thereby enhancing the user experience of watching and chatting while watching the video.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0013] Figure 1 A schematic diagram of an exemplary system in which the various methods described herein may be implemented according to embodiments of the present disclosure is shown;

[0014] Figure 2 A flowchart of an information display method according to an embodiment of the present disclosure is shown;

[0015] Figure 3 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown;

[0016] Figure 4 A flowchart of an information display method according to an embodiment of the present disclosure is shown;

[0017] Figure 5 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown;

[0018] Figure 6 A flowchart of an information display method according to an embodiment of the present disclosure is shown;

[0019] Figure 7 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown;

[0020] Figure 8 A schematic diagram of an information display system according to an embodiment of the present disclosure is shown;

[0021] Figure 9 An interactive diagram of an information display method according to an embodiment of the present disclosure is shown;

[0022] Figure 10 A structural block diagram of an information display device according to an embodiment of the present disclosure is shown; and

[0023] Figure 11 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0026] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0027] In related technologies, when users have questions about the content of a video or want to learn more, they need to leave the current video and go to another search page to search for answers.

[0028] To address the aforementioned issues, this disclosure embeds a dialogue area within the video playback page, leveraging the large model's dialogue capabilities to effectively help users explore and understand the video in depth without leaving the playback page, thus enhancing the user experience of watching and chatting simultaneously.

[0029] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1 The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0031] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of the methods of this disclosure.

[0032] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105, and / or 106 under a Software as a Service (SaaS) model.

[0033] exist Figure 1In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0034] Users can use client devices 101, 102, 103, 104, 105, and / or 106 for human-computer interaction. The client devices provide interfaces that enable users to interact with them. The client devices can also output information to the user through these interfaces. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0035] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices are capable of executing various applications, such as various internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and can use various communication protocols.

[0036] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0037] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0038] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0039] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105 and / or 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105 and / or 106.

[0040] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0041] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0042] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be of different types, such as key-value stores, object stores, or regular stores supported by a file system.

[0043] Figure 1 The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0044] According to one aspect of this disclosure, a method for displaying information based on a large model is provided. For example... Figure 2 As shown, the information display method 200 includes: step S201, displaying a video playback page, the video playback page including a video playback area for playing a first target video and a dialogue interaction object; step S202, in response to detecting a first operation on the dialogue interaction object, displaying a dialogue area in the video playback page; step S203, obtaining a first user input from the dialogue area; step S204, using the first user input to call a large model generation module to obtain a first response result; and step S205, displaying the first response result in the dialogue area.

[0045] Therefore, by embedding a dialogue area on the video playback page, the large model's dialogue capabilities can effectively help users explore and understand the video in depth without leaving the video playback page, thus enhancing the user experience of watching and chatting while watching the video.

[0046] In this disclosure, the large model (i.e., the deep learning large model) has end-to-end characteristics, enabling it to directly generate response data based on user input data without relying on functional components or other inputs outside the deep learning large model. In other words, the deep learning large model itself has generative capabilities. The deep learning large model can be a large language model. Large language models typically refer to deep learning large models with billions or even hundreds of billions of parameters, which are usually trained on large-scale text data or other modal data. Large language models can be used for various natural language processing tasks, such as text generation, language translation, and question answering systems. In addition, the large model can also be a recommendation model, used to complete video recommendation tasks, prompt word recommendation tasks, and other tasks.

[0047] Large-scale deep learning models can employ, for example, an N-layer Transformer network structure with an encoder and decoder, or a Unified pre-trained Language Model (UniLM) network structure. It is understood that large-scale deep learning models can also be other neural network models based on Transformer network structures, which are not limited here. The input and output of large-scale deep learning models consist of tokens. Each token can correspond to a single word, character, phrase, special symbol, or an external component, as described below. Large-scale deep learning models can be trained using pre-training and generation tasks to acquire the aforementioned generation capabilities.

[0048] In step S201, the display of the video playback page can be triggered in various ways, without limitation herein. In an exemplary embodiment, the video playback page can be displayed in response to detecting user actions on other pages (e.g., clicking on a first target video). In this disclosure, the video playback page may also be referred to as an immersive video page.

[0049] In step S202, in response to detecting a first operation on the dialogue interaction object, the dialogue area is displayed on the video playback page.

[0050] This disclosure does not limit the specific style, triggering method (i.e., the first operation) of the dialogue interaction object, the specific style of the dialogue area, or the display method. In an exemplary embodiment, the dialogue interaction object may be a button, text, pattern, etc., and the first operation may be a single click, double click, long press, or other operation. The dialogue area may be a floating window, pop-up window, etc., and may appear in a pop-up, fade-in, or other manner.

[0051] According to some embodiments, the dialogue area may be embedded in the video playback page.

[0052] By embedding the display, users can have a seamless user experience and avoid a disconnect from video viewing.

[0053] In some embodiments, the dialogue area can be displayed by popping up from the bottom of the video playback page.

[0054] According to some embodiments, the information display method may further include: compressing a video playback area in response to detecting a first operation on a dialogue interaction object. The dialogue area and the compressed video playback area may not overlap.

[0055] By compressing the video playback area and ensuring that the dialogue area does not overlap with the compressed video playback area, it is possible to allow users to engage in large-scale model dialogues while watching videos, and to conduct in-depth question-and-answer sessions based on the video content.

[0056] Figure 3 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown. Figure 3 As shown, the video playback page 300 includes a video playback area 310 and a dialogue interaction object 320. After detecting a first operation on the dialogue interaction object 320, the dialogue area 330 pops up from the bottom of the video playback page 300 and is displayed. The video playback area 310 is compressed and displayed above the pop-up dialogue area 330, and the two do not overlap.

[0057] In step S203, first user input is obtained from the dialog area. In some embodiments, the content entered by the user in the dialog area can be used as the first user input.

[0058] In step S204, the large model generation module is invoked using the first user input to obtain the first response result.

[0059] The large model generation module can be built based on a language large model or large model capabilities, and can receive input content and generate corresponding response results. The response results generated by the large model generation module (including the first response result mentioned above, as well as the second and third response results to be introduced below) can include text, images, audio and / or video.

[0060] In some embodiments, the large model generation module may include a retrieval module to retrieve relevant videos input by the user. The large model generation module can integrate these relevant videos into the response results for display to the user. The user can trigger the display of the video playback page and the playback of the relevant videos through specific actions performed on the relevant videos (which are actually the first and second target videos mentioned below).

[0061] In step S205, the first response result is displayed in the dialog area.

[0062] After obtaining the first response result by calling the large model generation module, the first response result can be displayed in the dialogue area to give users a coherent dialogue experience.

[0063] According to some embodiments, such as Figure 4 As shown, the information display method 400 includes: step S406, calling the prompt word recommendation module to obtain recommended prompt words; step S407, displaying the recommended prompt words on the video playback page; step S408, in response to detecting a second operation by the user on the recommended prompt words, calling the large model generation module using the recommended prompt words to obtain a second response result; and step S409, displaying a dialogue area on the video playback page and displaying the second response result in the dialogue display area.

[0064] It is understandable that the operations and effects of steps S401-S405 in method 400 can be referred to steps S201-S205 in method 200 respectively, and will not be repeated here.

[0065] Therefore, by providing prompts and recommendations, users can be assisted in exploring video content in greater depth.

[0066] In some embodiments, the cue word recommendation module may be based on a large model or utilize the generative capabilities of a large model. The cue word recommendation module may receive information related to videos, users, and / or conversations, and generate recommended cue words.

[0067] According to some embodiments, the recommended prompts may be generated by the prompt recommendation module based on the video information of the first target video.

[0068] By generating recommended prompts using video information from the primary target video, users can gain a more targeted and in-depth understanding of the video content.

[0069] According to some embodiments, the video information of the first target video may include: visual information extracted from keyframes of the first target video; and text information extracted from the title, summary and / or introduction of the first target video.

[0070] By employing the methods described above, we can utilize richer video information to recommend prompts, thereby obtaining more relevant prompts that are more closely related to the video content and improving the user experience.

[0071] In some embodiments, keyframes in the first target video can be processed using an image large model or a graph-text large model to obtain visual information. The visual information may include descriptive text about the content in the first target video, bounding boxes of targets in the frame, or other forms of content.

[0072] It is understandable that visual information can also be extracted from keyframes of the first target video in other ways, which are not limited here.

[0073] In some embodiments, the cue word recommendation module can be used to perform cross-modal understanding of the above visual and textual information to obtain recommended cue words that are more closely related to the video theme.

[0074] In some embodiments, the recommended prompts may be generated by a prompt recommendation module based on video information of the first target video and the dialogue context. In addition to video information, the dialogue context can also be used to generate recommended prompts to meet the user's potential intent. The dialogue context may refer to the dialogue context during the playback of the first target video, i.e., the dialogue context occurring in the dialogue area during the playback of the first target video, or it may refer to the dialogue context of the main dialogue page as described below; this is not limited to either.

[0075] According to some embodiments, in step S406, in response to determining that the first target video has been played for more than a preset duration, the prompt word recommendation module can be invoked to obtain recommended prompt words.

[0076] When users first start watching a video, they may not yet understand the video's theme or content. Therefore, by invoking the suggestion module and displaying recommended suggestions after the video has played for a preset duration—that is, after the user has gained an initial understanding of the video content—the user experience can be further improved. Furthermore, users may quickly find that the video content is not what they need or are not interested in, and then leave the video playback page. Therefore, by invoking the suggestion module after the preset playback duration, large model resources can be saved, avoiding waste.

[0077] The specific value of the preset duration can be set according to requirements. In an exemplary embodiment, the preset duration can be 3 seconds.

[0078] Step S407: Display recommended keywords on the video playback page.

[0079] According to some embodiments, recommended prompts can be displayed in a carousel in the adjacent area of ​​the dialogue interaction object.

[0080] This method allows users to see the recommended keywords without any additional action while watching videos.

[0081] In some embodiments, one or more recommended prompts can be generated, and users can see more prompts by swiping the area where the recommended prompts are located.

[0082] Step S408: In response to detecting the user's second operation on the recommended prompt, the large model generation module is invoked using the recommended prompt to obtain the second response result.

[0083] In some embodiments, the second operation can be a single click, double click, long press, or other operation.

[0084] Step S409: Display the dialogue area on the video playback page, and display the second response result in the dialogue display area.

[0085] The dialogue area is not displayed before the user performs a second action on the recommended suggestion. Therefore, after the second action is detected, the dialogue area can be displayed first, and then the second response result can be displayed in it.

[0086] Figure 5 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown. Figure 5 As shown, the video playback page 500 includes a video playback area 510 and a dialogue interaction object 520. Recommended prompts can be displayed in the adjacent area 530 of the dialogue interaction object 520. Clicking a recommended prompt directly pops up the dialogue area 540 and displays the corresponding response result 550. Simultaneously, the video playback area 510 is compressed and displayed above the dialogue area 540. The response result 550 can include a direct answer to the user input 560 and further recommended inquiries 570. In some embodiments, both the answer 560 and the recommended inquiries 570 can be obtained by calling a large model generation module using user input (which may also include video information and / or dialogue context).

[0087] According to some embodiments, such as Figure 6 As shown, the information display method 600 includes: step S601, displaying the main dialogue page; step S602, obtaining the second user input from the main dialogue page; and step S603, calling the large model generation module based on the second user input to obtain a third response result, the third response result including the first target video.

[0088] It is understandable that the operations and effects of steps S604-S608 in method 600 can be referred to steps S201-S205 in method 200 respectively, and will not be repeated here.

[0089] In step S604, in response to detecting a third operation on the first target video, a video playback page is displayed and the first target video is played.

[0090] The main dialogue page can be a dedicated page for users to interact with a large model. During this dialogue, the user provides a second set of inputs, which then triggers the large model's generation module to obtain a third response. This third response includes a first target video, and upon detecting the user's third action on the first target video, the display of the video playback page and the playback of the first target video are triggered.

[0091] It is understandable that the second user input and the third response result can constitute the dialogue context of the main dialogue page.

[0092] According to some embodiments, the video playback area can be used to play video streams. A video stream is a way of presenting continuously playing video content, in which users can quickly switch between different videos through video switching operations (swiping, clicking, etc.). Each video in the video stream can be played seamlessly, providing a smooth viewing experience.

[0093] like Figure 6 As shown, method 600 may further include: step S609, based on the dialogue context of the main dialogue page, calling the video recommendation module to obtain multiple first recommended videos, and adding the multiple first recommended videos to the first video stream corresponding to the first target video; and step S610, in response to detecting a video switching operation, replacing the currently playing video with other videos in the first video stream.

[0094] Therefore, through the above method, users can browse the first video stream corresponding to the first target video. Since the videos in the first video stream are generated based on the dialogue context of the main dialogue page, these videos are more in line with the user's preferences and needs, thereby improving the user experience.

[0095] The video recommendation module can be built based on a large recommendation model or by leveraging the capabilities of such a model. In some embodiments, in addition to the dialogue context on the main dialogue page, the video recommendation module can also be invoked based on user behavior, user profiles, and / or user preference information to obtain recommendation results that better match user preferences.

[0096] It's important to note that the multiple first recommended videos added to the first video stream are obtained by calling the video recommendation module, while the first and second target videos displayed on the dialogue page or in the dialogue area are obtained by calling the large model generation module. Recommended videos are more aligned with user behavior, preferences, and personal profiles, while target videos are more relevant to the user's intent in the current dialogue.

[0097] By using two links to acquire video, we can more accurately grasp user needs and recommend the content that users need to the right place.

[0098] In some embodiments, the switching operation may include a swipe operation or other video switching operations in the video stream, which are not limited herein.

[0099] According to some embodiments, the first response result may include a second target video. For example... Figure 6 As shown, method 600 may further include: step S611, in response to detecting a fourth operation on the second target video, closing the dialogue area and playing the second target video in the video playback area; step S612, based on the dialogue context during the playback of the first target video, calling the video recommendation module to obtain multiple second recommended videos, and adding the multiple second recommended videos to the second video stream corresponding to the second target video; and step S613, in response to detecting a video switching operation, replacing the currently playing video with other videos in the second video stream.

[0100] As described above, the response results may include a video. After the user performs a fourth action (e.g., single-click, double-click, long-press, or other action) on the second target video in the first response result, the chat area can be closed, thereby displaying the video playback area and playing the second target video therein.

[0101] It is important to note that after executing step S611, the video stream switching is completed from the first video stream corresponding to the first target video to the second video stream corresponding to the second target video. After this video stream switching is complete, any subsequent video switching operation will occur in the second video stream, not the first video stream.

[0102] In this way, each time a user clicks on the target video returned by the large model generation module, the current video is automatically switched to the video the user clicked, and prompts and video stream recommendations are made based on the new video content, forming a new round of watch-and-chat experience. Therefore, the method proposed in this disclosure can support multi-turn dialogue.

[0103] Figure 7 A schematic diagram of a video playback page according to an embodiment of the present disclosure is shown. Figure 7As shown, the video playback page 700 includes a dialogue area 710. Within the dialogue area 710, the first response result 720 may include a second target video 730. After clicking the second target video 730, the dialogue area 710 is closed, and the second target video 730 is played in the video playback area 740. After closing the dialogue area 710, the video playback area 740 can be restored from its compressed state, and the dialogue interaction object 750 can be redisplayed on the video playback page 700. After entering the second target video 730, steps S612-S613 can be executed to expand the second video stream, and steps S402-S409 can be executed based on the relevant information of the second target video to achieve a simultaneous viewing and chatting experience for the second target video.

[0104] Figure 8 A schematic diagram of an information display system according to an embodiment of the present disclosure is shown. (As shown) Figure 8 As shown, the information display system 800 may include three main parts: a video immersive container 810, a dialogue container 820, and a large model capability layer 830.

[0105] In some embodiments, the video immersive container 810 may further include video playback, infinite streaming, a chat entry, and prompts. Video playback may indicate a video playback area or a video playback function; infinite streaming indicates support for video streams that can switch between videos almost "infinitely"; the chat entry indicates the dialogue interaction object; and prompts indicate recommended prompts.

[0106] In some embodiments, the dialogue container 820 may further include text chat, voice chat, text-to-speech (TTS) playback, and multi-turn dialogue. The information display methods, apparatus, and implementations of these methods and apparatuses disclosed herein are capable of supporting these functions.

[0107] In some embodiments, the large model capability layer 830 may further include prompt word recommendation capability, video stream recommendation capability, and dialogue generation capability, corresponding to the prompt word recommendation module, video recommendation module, and large model generation module described above, respectively.

[0108] Figure 9 An interactive diagram of an information display method according to an embodiment of the present disclosure is shown. Figure 9 As shown, the information display method can involve interaction between six objects, including the main dialogue page 910, the video immersive page 920 (video playback page), the chat panel 930 (dialogue area), the keyword recommendation module 940, the video recommendation module 950, and the large model generation module 960.

[0109] The main dialogue page can receive a second user input, which in turn calls the large model generation module to obtain a third response. After the third response is displayed, in response to the detection of a third operation (e.g., a click) on the first target video in the response, the video immersion page (i.e., the video playback page) is displayed and the first target video is played.

[0110] The immersive video page carries video information and / or the dialogue context of the main dialogue page. It can call the video recommendation module (e.g., the video recommendation big model) to generate more recommended videos and insert them below the current video to enrich the first video stream corresponding to the first target video currently being played.

[0111] The immersive video page carries video information and / or the context of the main dialogue page, calls the prompt word recommendation module (e.g., the prompt word recommendation big model) to generate recommended prompt words, and displays them at the bottom of the page.

[0112] After a user triggers a recommended prompt, a chat panel (i.e., the dialogue area on the video playback page) can be brought up, and a large-scale model dialogue can be automatically performed using the prompt to discuss the current video. This process involves calling the large-scale model generation module.

[0113] After a user triggers a dialogue interaction, a chat panel (i.e., the dialogue area on the video playback page) can be invoked. In some embodiments, suggested prompts can be displayed in a carousel within the input box. The input box allows users to use the carousel prompts or manually enter query text to invoke the large model generation module to leverage the large model's capabilities for dialogue and question-and-answer sessions around the current video.

[0114] The chat panel supports multi-turn conversations, allowing users to ask questions in multiple rounds while watching videos without closing the chat panel. The big model then answers based on the current context.

[0115] In multi-turn dialogues, the large model may recommend new videos (i.e., the second target video; it's important to note that the second target is recommended by the large model's generation module, not the video recommendation module). After the user clicks on a video in the dialogue area, the dialogue area closes, and the immersive video page automatically switches the current video to the video the user clicked. Based on the new video content, it recommends prompts and video streams, forming a new round of watch-and-chat experience.

[0116] According to another aspect of this disclosure, an information display device based on a large model is provided. For example... Figure 10As shown, the information display device 1000 includes: a first display unit 1010 configured to display a video playback page, the video playback page including a video playback area for playing a first target video and a dialogue interaction object; a second display unit 1020 configured to display a dialogue area in the video playback page in response to detecting a first operation on the dialogue interaction object; a first acquisition unit 1030 configured to acquire a first user input from the dialogue area; a first invocation unit 1040 configured to invoke a large model generation module using the first user input to obtain a first response result; and a third display unit 1050 configured to display the first response result in the dialogue area.

[0117] It is understandable that the operations of units 1010-1050 can be referred to the descriptions of steps S201-S205 above, and will not be repeated here.

[0118] According to some embodiments, the dialogue area may be embedded in the video playback page.

[0119] According to some embodiments, the information display device may further include: a compression unit configured to compress a video playback area in response to detecting a first operation on a dialogue interaction object, wherein the dialogue area and the compressed video playback area do not overlap.

[0120] According to some embodiments, the information display device may further include: a second invocation unit configured to invoke a prompt word recommendation module to obtain recommended prompt words; a fourth display unit configured to display the recommended prompt words on a video playback page; a third invocation unit configured to, in response to detecting a second operation by a user on the recommended prompt words, invoke a large model generation module using the recommended prompt words to obtain a second response result; and a fifth display unit configured to display a dialogue area on the video playback page and display the second response result in the dialogue display area.

[0121] According to some embodiments, the recommended prompts may be generated by the prompt recommendation module based on the video information of the first target video.

[0122] According to some embodiments, the video information of the first target video may include: visual information extracted from keyframes of the first target video; and text information extracted from the title, summary and / or introduction of the first target video.

[0123] According to some embodiments, in response to determining that the first target video has been played for more than a preset duration, the prompt word recommendation module can be invoked to obtain recommended prompt words.

[0124] According to some embodiments, recommended prompts can be displayed in a carousel in the adjacent area of ​​the dialogue interaction object.

[0125] According to some embodiments, the information display device may further include: a sixth display unit configured to display a main dialogue page; a second acquisition unit configured to acquire second user input from the main dialogue page; and a fourth invocation unit configured to invoke a large model generation module based on the second user input to obtain a third response result, the third response result including a first target video. In response to detecting a third operation on the first target video, a video playback page may be displayed and the first target video may be played.

[0126] According to some embodiments, the video playback area is used to play a video stream. The information display device may further include: a fifth invocation unit, configured to invoke a video recommendation module to obtain a plurality of first recommended videos based on the dialogue context of the main dialogue page, and add the plurality of first recommended videos to a first video stream corresponding to a first target video; and a first replacement unit, configured to replace the currently playing video with other videos in the first video stream in response to detecting a video switching operation.

[0127] According to some embodiments, the first response result includes a second target video. The information display device may further include: a playback unit configured to close the dialogue area and play the second target video in the video playback area in response to detecting a fourth operation on the second target video; a sixth invocation unit configured to invoke a video recommendation module to obtain a plurality of second recommended videos based on the dialogue context during the playback of the first target video, and add the plurality of second recommended videos to a second video stream corresponding to the second target video; and a second replacement unit configured to replace the currently playing video with other videos in the second video stream in response to detecting a video switching operation.

[0128] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0129] According to embodiments of this disclosure, an electronic device, a readable storage medium, and a computer program product are also provided.

[0130] refer to Figure 11The present invention describes a structural block diagram of an electronic device 1100 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, 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 processors, cellular phones, smartphones, 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 disclosure described and / or claimed herein.

[0131] like Figure 11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of the electronic device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0132] Multiple components in electronic device 1100 are connected to I / O interface 1105, including: input unit 1106, output unit 1107, storage unit 1108, and communication unit 1109. Input unit 1106 can be any type of device capable of inputting information to electronic device 1100. Input unit 1106 can receive input digital or character information and generate key signal inputs related to user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 1107 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 1108 may include, but is not limited to, a hard disk and an optical disk. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and / or chipsets, such as Bluetooth devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices and / or the like.

[0133] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods, processes, and / or processing described above. For example, in some embodiments, these methods, processes, and / or processing may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the methods, processes, and / or processing described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform these methods, processes, and / or handling by any other suitable means (e.g., by means of firmware).

[0134] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0139] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the management difficulties and weak business scalability inherent in traditional physical hosts and VPS (Virtual Private Server) services. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0140] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0141] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. An information display method based on a large model, comprising: Display the main dialog page; Obtain second user input from the main dialog page; The large model generation module is invoked based on the second user input to obtain a third response result, which includes the first target video; In response to detecting a third operation on the first target video, a video playback page is displayed, the video playback page including a video playback area for playing the first target video and a dialogue interaction object; Based on the dialogue context of the main dialogue page, and based on user behavior, user profile and / or user preference information, the video recommendation module is invoked to obtain multiple first recommended videos, and the multiple first recommended videos are added to the first video stream corresponding to the first target video; In response to detecting a first video switching operation in the video playback area, the currently playing video is replaced with another video from the first video stream; In response to detecting a first operation on the dialogue interaction object, a dialogue area is displayed on the video playback page; Obtain first user input from the dialogue area; The large model generation module is invoked using the first user input to obtain the first response result; The first response result is displayed in the dialogue area, and the first response result includes the second target video; In response to detecting a fourth operation on the second target video, the dialog area is closed, and the second target video is played in the video playback area; Based on the dialogue context during the playback of the first target video, the video recommendation module is invoked to obtain multiple second recommended videos, and the multiple second recommended videos are added to the second video stream corresponding to the second target video; as well as In response to the detection of a second video switching operation in the video playback area, the currently playing video is replaced with another video from the second video stream.

2. The method according to claim 1, further comprising: Call the suggestion word recommendation module to obtain recommended suggestion words; The recommended keywords are displayed on the video playback page; In response to detecting a second user action on a recommended suggestion word, the large model generation module is invoked using the recommended suggestion word to obtain a second response result; as well as The dialogue area is displayed on the video playback page, and the second response result is displayed in the dialogue area.

3. The method according to claim 2, wherein, The recommended prompts are generated by the prompt recommendation module based on the video information of the first target video.

4. The method according to claim 3, wherein, The video information of the first target video includes: Visual information extracted from keyframes of the first target video; and Text information extracted from the title, summary, and / or description of the first target video.

5. The method according to claim 2, wherein, In response to determining that the first target video has been played for more than a preset duration, the prompt word recommendation module is invoked to obtain the recommended prompt words.

6. The method according to claim 2, wherein, The recommended prompts are displayed in a rotating manner in the adjacent area of ​​the dialogue interaction object.

7. The method according to any one of claims 1-6, wherein, The dialogue area is embedded and displayed within the video playback page.

8. The method according to any one of claims 1-6, further comprising: In response to detecting the first operation on the dialogue interaction object, the video playback area is compressed, wherein the dialogue area and the compressed video playback area do not overlap.

9. An information display device based on a large model, comprising: The sixth display unit is configured to display the main dialog page; The second acquisition unit is configured to acquire second user input from the main dialogue page; The fourth calling unit is configured to call the large model generation module based on the second user input to obtain a third response result, the third response result including the first target video; The first display unit is configured to display a video playback page in response to detecting a third operation on the first target video, the video playback page including a video playback area for playing the first target video and a dialogue interaction object; The fifth calling unit is configured to call the video recommendation module to obtain multiple first recommended videos based on the dialogue context of the main dialogue page and based on user behavior, user profile and / or user preference information, and add the multiple first recommended videos to the first video stream corresponding to the first target video; The first replacement unit is configured to replace the currently playing video with another video in the first video stream in response to detecting a first video switching operation in the video playback area. The second display unit is configured to display a dialogue area on the video playback page in response to detecting a first operation on the dialogue interaction object; The first acquisition unit is configured to acquire first user input from the dialog area; The first invocation unit is configured to invoke the large model generation module using the first user input to obtain a first response result; A third display unit is configured to display the first response result in the dialogue area, the first response result including the second target video; The playback unit is configured to close the dialog area and play the second target video in the video playback area in response to detecting a fourth operation on the second target video; The sixth invocation unit is configured to invoke the video recommendation module to obtain multiple second recommended videos based on the dialogue context during the playback of the first target video, and add the multiple second recommended videos to the second video stream corresponding to the second target video; as well as The second replacement unit is configured to replace the currently playing video with another video from the second video stream in response to detecting a second video switching operation in the video playback area.

10. The apparatus according to claim 9, further comprising: The second calling unit is configured to call the suggestion word recommendation module to obtain recommended suggestion words; The fourth display unit is configured to display the recommended prompts on the video playback page; The third calling unit is configured to, in response to detecting a second operation by the user on the recommended prompt word, call the large model generation module using the recommended prompt word to obtain a second response result; as well as The fifth display unit is configured to display the dialogue area on the video playback page and to display the second response result in the dialogue area.

11. The apparatus according to claim 10, wherein, The recommended prompts are generated by the prompt recommendation module based on the video information of the first target video.

12. The apparatus according to claim 11, wherein, The video information of the first target video includes: Visual information extracted from keyframes of the first target video; and Text information extracted from the title, summary, and / or description of the first target video.

13. The apparatus according to claim 10, wherein, In response to determining that the first target video has been played for more than a preset duration, the prompt word recommendation module is invoked to obtain the recommended prompt words.

14. The apparatus according to claim 10, wherein, The recommended prompts are displayed in a rotating manner in the adjacent area of ​​the dialogue interaction object.

15. The apparatus according to any one of claims 9-14, wherein, The dialogue area is embedded and displayed within the video playback page.

16. The apparatus according to any one of claims 9-14, further comprising: A compression unit is configured to compress the video playback area in response to detecting the first operation on the dialogue interaction object, wherein the dialogue area and the compressed video playback area do not overlap.

17. An electronic device, characterized in that, The electronic device includes: 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 to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method of any one of claims 1-8.

Images