Information display method and device based on large model, equipment and medium

Abstract

The invention provides an information display method and device based on a large model, equipment and a medium, relates to the technical field of artificial intelligence, in particular to the technical fields of natural language processing, deep learning and the like, and can be used for application scenes such as generative search, document intelligent editing, intelligent assistants, virtual assistants, intelligent e-commerce and the like. The method comprises the following steps: displaying a video playing page, wherein the video playing page comprises a video playing area for playing a first target video and a dialogue interaction object; in response to the detected 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 by using first user input to obtain a first reply result; and displaying the first reply result in the dialogue area.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to technical fields such as 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. It specifically 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 Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include natural language processing technology, computer vision technology, speech recognition technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

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

[0005] According to one aspect of the present disclosure, a large model-based information display method is provided, including: 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; 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.

[0006] According to another aspect of the present disclosure, there is provided an information display device based on a big model, comprising: a first display unit, configured to display a video playback page, the video playback page comprising a video playback area and a dialogue interaction object for playing a first target video; 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 a first user input from the dialogue area; a big model generation module calling unit, configured to call the big model generation module using the first user input to obtain a first reply result; and a third display unit, configured to display the first reply result in the dialogue area.

[0007] According to another aspect of the present 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, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0008] According to another aspect of the present disclosure, 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 above method.

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

[0010] According to one or more embodiments of the present disclosure, the present disclosure embeds a conversation area in a video playback page and utilizes the conversation capability of a large model to effectively help users conduct in-depth exploration and understanding of the video 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 content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

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

[0014] Figure 2 A flow chart 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 flow chart 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 flow chart 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] Fig. 9 An interactive diagram showing an information display method according to an embodiment of the present disclosure;

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

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

[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure 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 of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0025] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0026] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0027] In the related art, when a user has doubts about the content in a video or wants to learn more, he needs to leave the current video and go to other search pages to search for answers.

[0028] To solve the above problems, the present invention embeds a conversation area in the video playback page and utilizes the conversation capability of the large model to effectively help users conduct in-depth exploration and understanding of the video without leaving the video playback page, thereby enhancing the user experience of watching and chatting while watching the video.

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

[0030] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. 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 may be configured to execute one or more applications.

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

[0032] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided 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, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

[0034] The user can use client devices 101, 102, 103, 104, 105 and / or 106 to perform human-computer interaction. The client device can provide an interface that enables the user of the client device to interact with the client device. The client device can also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may 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 laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may 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, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0036] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, 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, dedicated 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 virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0038] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier 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 consolidate 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 embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may 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 a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0041] The 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. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

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

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

[0044] According to one aspect of the present disclosure, a method for displaying information based on a large model is provided. 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 and a dialogue interaction object for playing a first target video; 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, calling a large model generation module using the first user input to obtain a first reply result; and step S205, displaying the first reply result in the dialogue area.

[0045] Therefore, by embedding a conversation area in the video playback page and utilizing the conversation capabilities of the large model, users can effectively 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.

[0046] In the present disclosure, the big model (i.e., the deep learning big model) has an end-to-end feature, and can directly generate reply data based on the user's input data without the help of functional components or other inputs outside the deep learning big model. In other words, the deep learning big model itself has a generation function. The deep learning big model can be a big language model. A big language model generally refers to a deep learning big model with billions or even hundreds of billions of parameters, which are usually trained on large-scale text data or data of other modalities. The big language model can be used for various natural language processing tasks, such as text generation, language translation, and question-answering systems. In addition, the big model can also be a recommendation model for completing video recommendation tasks, prompt word recommendation tasks, and other tasks.

[0047] The deep learning large model can, for example, adopt an N-layer Transformer network structure with an encoder (Encoder) and a decoder (Decoder), or a unified pre-trained language model (Unified pre-trained LanguageModel, UniLM) network structure. It is understandable that the deep learning large model can also be other neural network models based on the Transformer network structure, which is not limited here. The input and output of the deep learning large model are both composed of identifiers (token). Each identifier can correspond to a single word, character, word, special symbol, or correspond to an external component, as will be described below. The deep learning large model can be trained using pre-training tasks and generation tasks to have the above-mentioned generation function.

[0048] In step S201, the display of the video playback page can be triggered in various ways, which are not limited here. In an exemplary embodiment, the video playback page can be displayed in response to detecting the user's operation on other pages (for example, a click operation on the first target video). In the present disclosure, the video playback page can also be referred to as a video immersive state page.

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

[0050] The present disclosure does not limit the specific style, triggering method (i.e., first operation) of the dialogue interaction object, the specific style, display method, etc. of the dialogue area. 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, a pop-up window, etc., and may appear in a pop-up, fade-in, or other manner.

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

[0052] By embedding the display, users can get a consistent user experience and avoid a sense of disconnection from video viewing.

[0053] In some embodiments, the conversation area may 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: in response to detecting a first operation on the dialogue interaction object, compressing the video playback area. The dialogue area and the compressed video playback area may not overlap.

[0055] By compressing the video playback area and making the conversation area non-overlapping with the compressed video playback area, users can have large-scale conversations while watching videos and conduct in-depth questions and answers around the video content.

[0056] Figure 3 FIG. 1 shows a schematic diagram of a video playback page according to an embodiment of the present disclosure. Figure 3 As shown, the video playback page 300 includes a video playback area 310 and a dialogue interaction object 320. After detecting the first operation on the dialogue interaction object 320, the dialogue area 330 pops up and is displayed from the bottom of the video playback page 300. 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, a first user input is obtained from the dialogue area. In some embodiments, the content input by the user in the dialogue area may be taken as the first user input.

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

[0059] The large model generation module can be built based on the language large model or large model capability, and can receive input content and generate corresponding reply results. The reply results generated by the large model generation module (including the first reply result mentioned above, and also including the second reply result and the third reply result 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 the relevant video input by the user. The large model generation module can integrate the relevant video into the reply result to display it to the user. The user can trigger the display of the video playback page and the playback of the relevant video by performing a specific operation on the relevant video (actually the first target video and the second target video in the following text).

[0061] In step S205, the first reply result is displayed in the conversation area.

[0062] After the large model generation module is called to obtain the first reply result, the first reply result can be displayed in the dialogue area to allow the user to obtain a coherent dialogue experience.

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

[0064] It can be understood that the operations and effects of step S401 to step S405 in method 400 can refer to step S201 to step S205 in method 200 respectively, and will not be described in detail here.

[0065] Therefore, by recommending prompt words, it is possible to assist users in exploring the video content in depth.

[0066] In some embodiments, the prompt word recommendation module may be implemented based on a large model or using the generation capability of a large model. The prompt word recommendation module may receive information related to a video, a user and / or a conversation, and generate a recommended prompt word.

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

[0068] By using the video information of the first target video to generate recommendation prompt words, it is possible to help users 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 key frames of the first target video; and text information extracted from a title, summary, and / or introduction of the first target video.

[0070] Through the above method, it is possible to use richer video information to recommend prompt words, thereby obtaining recommended prompt words that are more relevant to the video content, thereby improving user experience.

[0071] In some embodiments, the key frames in the first target video may be processed using an image macro model or a graphic macro model to obtain visual information. The visual information may include a description text of the content in the first target video, or may include a bounding box of the target in the picture, or may include other content in other forms.

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

[0073] In some embodiments, a prompt word recommendation module may be used to perform cross-modal understanding on the visual information and text information to obtain recommended prompt words whose content is closer to the theme of the video.

[0074] In some embodiments, the recommendation prompt word may be generated by the prompt word recommendation module based on the video information and the conversation context of the first target video. In addition to the video information, the conversation context may also be used to generate the recommendation prompt word to meet the user's potential intention. The conversation context may refer to the conversation context during the playback of the first target video, that is, the conversation context occurring in the conversation area during the playback of the first target video, or may refer to the conversation context of the main conversation page hereinafter, which is not limited here.

[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 time, a prompt word recommendation module may be called to obtain a recommended prompt word.

[0076] When users start watching a video, they may not understand the theme of the video. Therefore, by calling the prompt word recommendation module and displaying the recommended prompt words after the video has been played for a preset time, that is, after the user has initially understood the video content, the user experience can be further improved. In addition, after clicking on the video, the user may find that the video content is not what he needs or is not interested in it in a short time, and then leave the video playback page. Therefore, by calling the prompt word recommendation module after the video has been played for a preset time, large model resources can be saved and waste can be avoided.

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

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

[0079] According to some embodiments, the recommended prompt words may be displayed in a carousel in an adjacent area of ​​the dialog interaction object.

[0080] In this way, users can fully see the content of the recommended prompt words while watching the video without any additional operations.

[0081] In some embodiments, one or more recommended prompt words may be generated, and the user may view more prompt words by sliding the area where the recommended prompt words are located.

[0082] Step S408: In response to detecting a second operation of the user on the recommendation prompt word, the large model generation module is called using the recommendation prompt word to obtain a second reply result.

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

[0084] Step S409: displaying a conversation area in the video playback page, and displaying a second reply result in the conversation display area.

[0085] Before the user performs the second operation on the recommended prompt word, the dialogue area has not been displayed. Therefore, after the second operation is detected, the dialogue area may be displayed first, and then the second reply result may be displayed therein.

[0086] Figure 5 FIG. 1 shows a schematic diagram of a video playback page according to an embodiment of the present disclosure. Figure 5 As shown, the video playback page 500 includes a video playback area 510 and a dialogue interaction object 520, and the adjacent area 530 of the dialogue interaction object 520 can display the recommended prompt word. After clicking the recommended prompt word, the dialogue area 540 can be directly popped up, and the corresponding reply result 550 can be displayed. At the same time, the video playback area 510 is compressed and displayed above the dialogue area 540. The reply result 550 may include a direct answer 560 to the user input and a further recommended query 570. In some embodiments, the answer 560 and the recommended query 570 can be obtained by calling the large model generation module using the user input (which may also include video information and / or dialogue context).

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

[0088] It can be understood that the operations and effects of step S604 to step S608 in method 600 can refer to step S201 to step S205 in method 200 respectively, and will not be described in detail here.

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

[0090] The main dialogue page can be a page dedicated to dialogue between the user and the big model. During the dialogue between the user and the big model, the user provides a second user input, and then calls the big model generation module to obtain a third reply result. The third reply result includes the first target video, and then after detecting the user's third operation on the first target video, the display of the video playback page and the playback of the first target video are triggered.

[0091] It can be understood that the second user input and the third reply result can constitute the conversation context of the main conversation page.

[0092] According to some embodiments, the video playback area can be used to play a video stream. Video streaming is a continuous video content presentation method in which a user can quickly switch between different videos through video switching operations (slide, click, etc.). Each video in the video stream can be played seamlessly to provide a smooth viewing experience.

[0093] like Figure 6 As shown, method 600 may also include: step S609, based on the conversation context of the main conversation 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, the user can browse the first video stream corresponding to the first target video, and because the videos in the first video stream are generated based on the conversation context of the main conversation 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 the recommendation big model or using the big model capability. In some embodiments, in addition to the conversation context on the main conversation page, the video recommendation module can also be called based on user behavior, user portrait and / or user preference information to obtain recommendation results that are more in line with user preferences.

[0096] It should be noted that the multiple first recommended videos added to the first video stream are obtained by calling the video recommendation module, while the first target video and the second target video displayed on the conversation page or in the conversation area are obtained by calling the large model generation module. The recommended videos are more in line with the user's behavior, preferences, and personal portrait, while the target videos are more in line with the user's intention in the current conversation.

[0097] By using two links to obtain videos, it is possible to more accurately grasp the needs of users and recommend the content they need to users at the appropriate location.

[0098] In some embodiments, the switching operation may include a sliding operation, or a video switching operation in other video streams, which is not limited here.

[0099] According to some embodiments, the first reply result may include the second target video. Figure 6 As shown, method 600 may also include: step S611, in response to detecting a fourth operation on the second target video, closing the conversation area, and playing the second target video in the video playback area; step S612, based on the conversation 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 reply result may include a video. After the user performs a fourth operation (e.g., single-click, double-click, long-press, or other operation) on the second target video in the first reply result, the user may close the conversation area, thereby displaying the video play area and playing the second target video therein.

[0101] It should be noted that after executing step S611, the video stream switching from the first video stream corresponding to the first target video to the second video stream corresponding to the second target video is completed. After completing the video stream switching, the video switching operation will be performed in the second video stream instead of the first video stream.

[0102] In this way, each time the user clicks on the target video returned by the large model generation module, the current video is automatically switched to the video clicked by the user, and prompt word recommendations and video stream recommendations are made based on the new video content, forming a new round of watching and chatting experience. Therefore, the method proposed in the present disclosure can support multiple rounds of dialogue.

[0103] Figure 7 FIG. 1 shows a schematic diagram of a video playback page according to an embodiment of the present disclosure. Figure 7As shown, the video playback page 700 includes a conversation area 710, in which the first reply result 720 may include a second target video 730. After clicking the second target video 730, the conversation area 710 is closed and the second target video 730 is played in the video playback area 740. After closing the conversation area 710, the video playback area 740 can be restored from a compressed state, and the conversation interaction object 750 can be redisplayed in the video playback page 700. After entering the second target video 730, the above steps S612-S613 can be executed to complete the expansion of the second video stream, and steps S402-S409 can be executed based on the relevant information of the second target video to achieve a chat experience for the second target video.

[0104] Figure 8 FIG. 1 shows a schematic diagram of an information display system according to an embodiment of the present disclosure. Figure 8 As shown, the information display system 800 may include three main parts, namely, a video immersive container 810 , a dialogue container 820 and a large model capability layer 830 .

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

[0106] In some embodiments, the conversation container 820 may further include text chat, voice chat, text to speech (TTS) playback, and multi-round conversations. The information display method, device, and implementation of these methods and devices proposed in the present disclosure can support 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, which respectively correspond to the prompt word recommendation module, video recommendation module and large model generation module introduced above.

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

[0109] The second user input can be received on the main conversation page, and then the large model generation module is called to obtain a third reply result. After the third reply result is displayed on the screen, in response to detecting a third operation (e.g., click) on the first target video in the reply result, the video immersive state page (i.e., video playback page) is displayed and the first target video is played.

[0110] The video immersive page carries video information and / or the conversation context of the main conversation page, and can call a video recommendation module (e.g., a video recommendation 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 video immersive page carries the context of the video information and / or the main conversation page, calls a prompt word recommendation module (eg, a prompt word recommendation large model) to generate recommended prompt words, and displays them at the bottom of the page.

[0112] After the user triggers the recommended prompt word, the chat panel (i.e., the dialogue area in the video playback page) can be called up, and the prompt word can be automatically used to conduct a large model dialogue question and answer around the current video. This process involves calling the large model generation module.

[0113] After the user triggers the dialogue interaction object, the chat panel (i.e., the dialogue area in the video playback page) can be called up. In some embodiments, the recommended prompt words can be rotated in the input box. The input box supports the user to use the rotating prompt words or manually enter the query text (query) to call the large model generation module to use the large model capability to conduct a dialogue question and answer around the current video.

[0114] The chat panel supports multiple rounds of conversations. Users can watch the video without closing the chat panel and ask multiple questions. The big model will answer based on the current context.

[0115] The big model may recommend new videos (i.e., the second target video; it should be noted that the second target is recommended by the big model generation module, not the video recommendation module) during multiple rounds of conversations. After the user clicks on a video in the conversation area, the conversation area closes, and the video immersive page automatically switches the current video to the video clicked by the user, and recommends prompt words and video streams based on the new video content, forming a new round of watching and chatting experience.

[0116] According to another aspect of the present disclosure, a large model-based information display device is provided. Fig.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 calling unit 1040, configured to call a large model generation module using the first user input to obtain a first reply result; and a third display unit 1050, configured to display the first reply result in the dialogue area.

[0117] It can be understood that the operations of unit 1010 to unit 1050 can refer to the above description of step S201 to step S205, respectively, and will not be repeated here.

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

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

[0120] According to some embodiments, the information display device may further include: a second calling unit, configured to call a prompt word recommendation module to obtain a recommended prompt word; a fourth display unit, configured to display the recommended prompt word on the video playback page; a third calling unit, configured to respond to detecting a second operation of the user on the recommended prompt word, and use the recommended prompt word to call the large model generation module to obtain a second reply result; and a fifth display unit, configured to display a dialogue area in the video playback page, and display the second reply result in the dialogue display area.

[0121] According to some embodiments, the recommended prompt word may be generated by a prompt word recommendation module based on 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 key frames of the first target video; and text information extracted from a 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 time, a prompt word recommendation module may be called to obtain a recommended prompt word.

[0124] According to some embodiments, the recommended prompt words may be displayed in a carousel in an adjacent area of ​​the dialog interaction object.

[0125] According to some embodiments, the information display device may further include: a sixth display unit configured to display a main conversation page; a second acquisition unit configured to acquire a second user input from the main conversation page; and a fourth calling unit configured to call the large model generation module based on the second user input to obtain a third reply result, the third reply result including the first target video. In response to detecting the 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 also include: a fifth calling unit, configured to call the video recommendation module to obtain multiple first recommended videos based on the conversation context of the main conversation page, and add the multiple first recommended videos to the first video stream corresponding to the first target video; and a first replacement unit, configured to replace the currently played video with other videos in the first video stream in response to detecting a video switching operation.

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

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

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

[0130] refer to Fig.11, a block diagram of an electronic device 1100 that can be used as a server or client of the present disclosure will now be described, 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, 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 disclosure described and / or required herein.

[0131] like Fig.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. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0132] Multiple components in the electronic device 1100 are connected to the I / O interface 1105, including: an input unit 1106, an output unit 1107, a storage unit 1108, and a communication unit 1109. The input unit 1106 can be any type of device that can input information to the electronic device 1100. The input unit 1106 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and / or a remote controller. The output unit 1107 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1108 can include but is not limited to a disk and an optical disk. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMax device, a cellular communication device and / or the like.

[0133] The computing unit 1101 may be a variety of general and / or special 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 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 1101 performs the various methods, processes, and / or processes described above. For example, in some embodiments, these methods, processes, and / or processes may be implemented as computer software programs, which are tangibly included in machine-readable media, such as storage units 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 processes described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform these methods, processes and / or processing in any other suitable manner (eg, by means of firmware).

[0134] 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.

[0135] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may 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 may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0136] In the context of the present disclosure, 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.

[0137] 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).

[0138] The systems and techniques described herein can be implemented in a computing system that includes backend 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 frontend 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 backend components, middleware components, or frontend components. The components of the system can 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), the Internet, and a blockchain network.

[0139] 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. 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 for a distributed system, or a server combined with a blockchain.

[0140] 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 this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0141] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A method for displaying information based on a large model, comprising: Displaying a video playback page, wherein the video playback page includes 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; Acquire a first user input from the dialog area; Using the first user input, calling a large model generation module to obtain a first reply result; as well as The first reply result is displayed in the conversation area.

2. The method according to claim 1, further comprising: Calling a prompt word recommendation module to obtain a recommended prompt word; Displaying the recommendation prompt word on the video playback page; In response to detecting a second operation of the user on the recommendation prompt word, calling the large model generation module using the recommendation prompt word to obtain a second reply result; as well as The conversation area is displayed in the video playing page, and the second reply result is displayed in the conversation display area.

3. The method according to claim 2, wherein: The recommended prompt word is generated by the prompt word 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 key frames of the first target video; and Text information extracted from the title, summary and / or introduction 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 time, the prompt word recommendation module is called to obtain the recommended prompt word.

6. The method according to claim 2, wherein: The recommended prompt words are displayed in a carousel in the adjacent area of ​​the dialogue interaction object.

7. The method according to claim 2, further comprising: Display the main conversation page; Obtaining a second user input from the main dialogue page; as well as Based on the second user input, the large model generation module is called to obtain a third reply result, wherein the third reply result includes the first target video. In which, in response to detecting a third operation on the first target video, the video playback page is displayed and the first target video is played.

8. The method according to claim 7, wherein: The video playback area is used to play the video stream, and the method further includes: Based on the conversation context of the main conversation page, calling a video recommendation module to obtain a plurality of first recommended videos, and adding the plurality of first recommended videos to a first video stream corresponding to the first target video; and In response to detecting a video switching operation, the currently playing video is replaced with other videos in the first video stream.

9. The method according to claim 8, wherein: The first reply result includes a second target video, and the method further includes: In response to detecting a fourth operation on the second target video, closing the dialog area and playing the second target video in the video playing area; Based on the conversation context during the playing of the first target video, calling the video recommendation module to obtain a plurality of second recommended videos, and adding the plurality of second recommended videos to a second video stream corresponding to the second target video; and In response to detecting a video switching operation, the currently playing video is replaced with other videos in the second video stream.

10. The method according to any one of claims 1 to 9, wherein: The dialog area is embedded and displayed in the video playback page.

11. The method according to any one of claims 1 to 9, further comprising: In response to detecting the first operation on the dialogue interaction object, the video playback area is compressed, wherein the dialogue area does not overlap with the compressed video playback area.

12. An information display device based on a large model, comprising: A first display unit is configured to display a video playback page, wherein the video playback page includes a video playback area for playing a first target video and a dialogue interaction object; a second display unit, configured to display a conversation area in the video playback page in response to detecting a first operation on the conversation interaction object; A first acquisition unit, configured to acquire a first user input from the dialogue area; A first calling unit is configured to call a large model generation module using the first user input to obtain a first reply result; as well as A third display unit is configured to display the first reply result in the conversation area.

13. The apparatus according to claim 12, further comprising: A second calling unit is configured to call the prompt word recommendation module to obtain a recommended prompt word; A fourth display unit is configured to display the recommendation prompt word on the video playback page; A third calling unit is configured to, in response to detecting a second operation of the user on the recommendation prompt word, call the large model generation module using the recommendation prompt word to obtain a second reply result; as well as The fifth display unit is configured to display the conversation area in the video playback page and display the second reply result in the conversation display area.

14. The device according to claim 13, wherein: The recommended prompt word is generated by the prompt word recommendation module based on the video information of the first target video.

15. The device according to claim 14, wherein: The video information of the first target video includes: visual information extracted from key frames of the first target video; and Text information extracted from the title, summary and / or introduction of the first target video.

16. The device according to claim 13, wherein: In response to determining that the first target video has been played for more than a preset time, the prompt word recommendation module is called to obtain the recommended prompt word.

17. The device according to claim 13, wherein: The recommended prompt words are displayed in a carousel in the adjacent area of ​​the dialogue interaction object.

18. The apparatus according to claim 13, further comprising: a sixth display unit, configured to display a main conversation page; A second acquisition unit is configured to acquire a second user input from the main dialogue page; as well as a fourth calling unit, configured to call the large model generation module based on the second user input to obtain a third reply result, wherein the third reply result includes the first target video, In which, in response to detecting a third operation on the first target video, the video playback page is displayed and the first target video is played.

19. The device according to claim 18, wherein: The video playing area is used to play the video stream, and the device also includes: a fifth calling unit configured to call a video recommendation module to obtain a plurality of first recommended videos based on the conversation context of the main conversation page, and add the plurality of first recommended videos to a first video stream corresponding to the first target video; and The first replacement unit is configured to replace the currently played video with other videos in the first video stream in response to detecting a video switching operation.

20. The device according to claim 19, wherein The first reply result includes a second target video, and the device further includes: a playing unit, configured to, in response to detecting a fourth operation on the second target video, close the dialog area and play the second target video in the video playing area; a sixth calling unit, configured to call the video recommendation module to obtain a plurality of second recommended videos based on the conversation context during the playing 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 The second replacement unit is configured to replace the currently played video with other videos in the second video stream in response to detecting a video switching operation.

21. The device according to any one of claims 12 to 20, wherein: The dialog area is embedded and displayed in the video playback page.

22. The apparatus according to any one of claims 12 to 20, 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 does not overlap with the compressed video playback area.

23. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled 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 to enable the at least one processor to perform the method according to any one of claims 1 to 11.

24. 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 1-11.

25. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images