Interaction method and device based on artificial intelligence, intelligent agent, equipment and medium

Abstract

The invention provides an interaction method and device based on artificial intelligence, an intelligent agent, equipment, a medium and a program product, and relates to the technical field of artificial intelligence, in particular to the technical fields of natural language processing, large models, multimedia interaction and the like. The specific implementation scheme of the interaction method is as follows: obtaining interaction information input by a target object in a video playing interface; in response to the received interaction information, determining virtual object information of a virtual object used for interacting with the target object based on a video clip being played on the video playing interface; generating feedback information for the interaction information based on the virtual object information, the interaction information and the video content of the video clip; the feedback information is displayed in an interactive active area of the video playing interface, and the interactive active area is determined based on the opening states of multiple interactive areas in the video playing interface.

Description

Technical Field

[0001] The present disclosure relates to the technical field of artificial intelligence, particularly to the technical fields of natural language processing, large models, multimedia interaction, etc., and specifically relates to an interaction method, device, intelligent agent, device, medium, and program product based on artificial intelligence. Background Art

[0002] With the rapid development of the network video industry, sending bullet comments or reviews during video playback has become an indispensable channel for users to express their opinions. In the related art, the functions of interaction areas such as bullet comments or reviews are relatively single. How to improve the user experience has become a research and development direction. Summary of the Invention

[0003] The present disclosure provides an interaction method, device, intelligent agent, device, medium, and program product based on artificial intelligence.

[0004] According to one aspect of the present disclosure, there is provided an interaction method based on artificial intelligence, including: obtaining interaction information input by a target object on a video playback interface; in response to receiving the interaction information, determining virtual object information of a virtual object for interacting with the target object based on a video segment being played on the video playback interface; generating feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment; and displaying the feedback information in an interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

[0005] According to another aspect of the present disclosure, there is provided an interaction device of artificial intelligence, including: an information receiving module for obtaining interaction information input by a target object on a video playback interface; an object determining module for determining virtual object information of a virtual object for interacting with the target object based on a video segment being played on the video playback interface in response to receiving the interaction information; a feedback generating module for generating feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment; and a feedback displaying module for displaying the feedback information in an interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

[0006] According to another aspect of the present disclosure, there is provided an intelligent agent of artificial intelligence, including: an input module for receiving input information; a processing module for determining a target task based on the input information received by the input module and performing the method according to the present disclosure based on the target task to obtain output information; and an output module for outputting the output information obtained by the processing module.

[0007] According to another aspect of the present disclosure, there is provided an electronic device, including: 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 method as described in the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method as described in the present disclosure.

[0009] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which implements the method as described in the present disclosure when executed by a processor.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 Schematically shows an exemplary system architecture to which an interaction method and apparatus based on artificial intelligence can be applied according to an embodiment of the present disclosure;

[0013] Figure 2 Schematically shows a flowchart of an interaction method based on artificial intelligence according to an embodiment of the present disclosure;

[0014] Figures 3a - 3c Respectively schematically show the display effect diagrams of displaying feedback information in an interaction active area according to embodiments of the present disclosure;

[0015] Figure 4 Schematically shows a schematic diagram of a cross-region interaction mechanism according to an embodiment of the present disclosure;

[0016] Figure 5 Schematically shows a flowchart of an interaction method based on artificial intelligence according to another embodiment of the present disclosure;

[0017] Figure 6 Schematically shows a block diagram of an interaction device based on artificial intelligence according to an embodiment of the present disclosure;

[0018] Figure 7 Schematically shows a block diagram of the structure of an intelligent agent of artificial intelligence according to an embodiment of the present disclosure; and

[0019] Figure 8A block diagram of an electronic device suitable for implementing an artificial intelligence-based interaction method according to an embodiment of the present disclosure is schematically shown. Detailed implementation manners

[0020] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0021] In the technical solution of the present disclosure, the processing of collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information complies with the provisions of relevant laws and regulations, takes necessary confidentiality measures, and does not violate public order and good customs.

[0022] In the technical solution of the present disclosure, before obtaining or collecting user personal information, the authorization or consent of the user is obtained.

[0023] Figure 1 An exemplary system architecture to which an artificial intelligence-based interaction method and apparatus can be applied according to an embodiment of the present disclosure is schematically shown.

[0024] It should be noted that Figure 1 The example shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments, or scenarios. For example, in another embodiment, the exemplary system architecture to which an artificial intelligence-based interaction method and apparatus can be applied may include a terminal device, but the terminal device can implement the artificial intelligence-based interaction method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0025] As Figure 1 shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0026] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (for example only).

[0027] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0028] The server 105 can be a server providing various services, such as a background management server that provides support for the content browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (for example only). The background management server can analyze and process data such as received user requests, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0029] It should be noted that the artificial intelligence-based interaction method provided by the embodiments of the present disclosure can generally be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the artificial intelligence-based interaction device provided by the embodiments of the present disclosure can also be set in the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0030] Alternatively, the artificial intelligence-based interaction method provided by the embodiments of the present disclosure can generally also be executed by the server 105. Correspondingly, the artificial intelligence-based interaction device provided by the embodiments of the present disclosure can generally be set in the server 105. The artificial intelligence-based interaction method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the artificial intelligence-based interaction device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0031] For example, when the user is watching a video, the first terminal device 101, the second terminal device 102, and the third terminal device 103 can obtain the interaction information input by the user, and then send the obtained interaction information to the server 105. The server 105 analyzes the interaction information in response to receiving it, determines the virtual object information for interacting with the user, generates feedback information based on the virtual object information, the interaction information, and the video content of the video segment, and displays the feedback information in the interaction active area of the video playback interface. Or a server or server cluster capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105 analyzes the interaction information, and finally realizes displaying the feedback information in the interaction active area of the video playback interface.

[0032] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0033] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers.

[0034] Figure 2 The flowchart of the interaction method based on artificial intelligence according to an embodiment of the present disclosure is schematically shown.

[0035] As Figure 2 shown, the method includes operations S210 to S240.

[0036] In operation S210, obtain the interaction information input by the target object on the video playback interface.

[0037] In operation S220, in response to receiving the interaction information, based on the video segment being played on the video playback interface, determine the virtual object information of the virtual object for interacting with the target object.

[0038] In operation S230, generate feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment.

[0039] In operation S240, display the feedback information in the interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

[0040] The target object can be a user watching a video. The video playback interface can be an interface or window of a client of a video social platform, a live streaming platform, or a short video website. The video playback interface can display a video image and an interaction area for the target object to input interaction information. The target object can watch the video on the video playback interface and perform human-computer interaction through the interaction area.

[0041] For example, when watching a video, the target object can input interaction information on the video playback interface by means of clicking, keyboard input, voice input, gesture operation, etc. The interaction information can include likes, collections, published comments, bullet screens, voices, pictures, videos, etc.

[0042] The virtual object can be a character, an animal character, or a virtual character that appears in the video content, or a virtual character constructed based on the video content. The virtual object information can be relevant information about the virtual object extracted from the video content, and the virtual object information can include, but is not limited to, object attribute information such as the age, gender, personality, interests, knowledge field, and skills of the virtual object.

[0043] In some embodiments, the target object can trigger the interaction area of the video playback interface to pause the video, input interaction information, etc.

[0044] The feedback information can be generated based on the virtual object information, the interaction information, and the video content. The expression mode of the feedback information can be determined by imitating the virtual object based on the virtual object information. The emotion expressed by the feedback information can be determined based on the emotion expressed by the video content. The feedback intention expressed by the feedback information can be determined based on the interaction information of the target object.

[0045] For example, the interaction information input by the target object is a "like" icon. The protagonist in the video clip can be used as the virtual object for interacting with the target object. Based on the identity information of the protagonist, such as the identity information of "dad" as the virtual object information, the expression mode is simulated. Based on the warm emotion or atmosphere expressed by the video content, the emotion expression is simulated. Using the interaction information as the feedback intention, the feedback information is generated. The feedback information can be, for example, "hi, saw you liked it, thank you! I am watching you!"

[0046] In some embodiments, the video playback interface may include multiple interaction areas, which may include but are not limited to a bullet comment area, a comment area, or an area available for interaction. The target object may input interaction information in one of the interaction areas and receive feedback information in that area. However, it is not limited thereto. A cross-area interaction mechanism may be adopted. When outputting feedback information, the interaction area for inputting interaction information is in a closed state, and the feedback information may be displayed in the active interaction area. The active interaction area may refer to an interaction area in an open state. For example, the target object inputs a like icon as interaction information in the comment area. However, the comment area is closed after the input. After generating the feedback information, the bullet comment area may be used as the active interaction area, and the feedback information may be displayed in the bullet comment area so that the target object can receive the feedback information in the active interaction area with the bullet comment area as the active interaction area. That is, the feedback information may be displayed in the active interaction area in a cross-area manner, enabling the target object to quickly view the feedback information.

[0047] According to embodiments of the present disclosure, by determining the simulation object information of the simulation object to be interacted with according to the interaction information of the target object and generating feedback information for the interaction information based on the simulation object information, the intelligence and companionship of the interaction can be improved; at the same time, flexibly displaying the feedback information in the active interaction area can implement a cross-area interaction mechanism for different interaction areas, enhancing the interaction efficiency with the user, thereby improving the user experience.

[0048] According to embodiments of the present disclosure, for the operation S210 as shown in Figure 2 obtaining the interaction information input by the target object in the video playback interface may include: determining the active interaction area from multiple interaction areas based on the open state of each of the multiple interaction areas. Obtaining the interaction information input by the target object from the active interaction area.

[0049] In some embodiments, the interaction information input by the target object in the video playback interface may be input in the comment area, or may also be input in the bullet comment area, like area, etc. The open state of each of the multiple interaction areas may be monitored. According to the open state of each of the multiple interaction areas, the current active interaction area is determined. For example, if the current user is inputting text in the comment area and the comment area is in an open state, the comment area is the active interaction area. The information input by the target object may be obtained from the comment area as the interaction information.

[0050] According to embodiments of the present disclosure, interaction ports for each of the multiple interaction areas may be established to communicate separately, thereby enabling the acquisition of interaction information from different interaction areas, increasing the acquisition channels of interaction information, and further improving the flexibility and richness of the user's input of interaction information.

[0051] According to embodiments of the present disclosure, for the situation as shown in Figure 2The operation S240 shown, displaying feedback information in the interactive active area of the video playback interface may include: determining the interactive active area from multiple interactive areas based on the opening states of the respective interactive areas. When the interactive active area includes a bullet comment area, the feedback information is displayed in the bullet comment area in the form of bullet comments.

[0052] In some embodiments, a switch button for opening and closing the interactive area may be provided on the video playback interface. When it is detected that the switch button of the interactive area is in the open state, the interactive area is the interactive active area. Alternatively, it may also be determined whether the interactive area is the interactive active area according to whether the interactive area is displayed within the current video playback interface, or according to whether the interactive area is in an active state, such as the state of opening an input box or swiping the interface, etc.

[0053] In some embodiments, when displaying feedback information in the bullet comment area, the feedback information may appear in the bullet comment area in the form of bullet comments in real time. When displaying feedback information in the comment area, the feedback information is displayed in the comment area in the form of comments.

[0054] According to the embodiments of the present disclosure, by first determining the opening states of multiple interactive areas and then selecting the interactive active area from the multiple interactive areas to display the feedback information, it can be ensured that the feedback information is not limited to being only displayed in the interactive area where the target object inputs interactive information, but can also be displayed across regions in another interactive active area different from the interactive area where the interactive information is input. Thus, the real-time performance and interactivity of the feedback information display are enhanced through the cross-region interaction mechanism.

[0055] Figures 3a - 3c Schematic diagrams respectively show the display effect diagrams of displaying feedback information in the interactive active area according to the embodiments of the present disclosure.

[0056] In some embodiments, as Figure 3a shown, the video playback interface 310 may include a video playback area 311, a comment area 313, and a bullet comment area 312. A life segment about the protagonist A300 is played in the playback area 311. After receiving the first interactive information input by the target object in the comment area 313, if the comment area 313 is in the open state, the object identifier representing the virtual object and the first feedback information may be displayed in the comment area 313. Similarly, after receiving the second interactive information of the target object in the bullet comment area 312, if the bullet comment area 312 is in the open state, the object identifier and the second feedback information may be displayed in the bullet comment area 312.

[0057] In some embodiments, as Figure 3b shown, the target object may input interactive information in the comment area 313. When it is detected that the bullet comment area 312 is in the open state, for example, after the target object inputs a comment and then continues to watch the video, resulting in the folding of the comment area, at this time, the object identifier and the feedback information may be displayed in the bullet comment area 312.

[0058] In some embodiments, such as Figure 3c shown, if the target object inputs interaction information in the bullet screen area 312, when it is detected that the comment area 313 is in an open state, for example, the target object is browsing comments, at this time, the object identifier and feedback information can be displayed in the comment area 313.

[0059] In some embodiments, if the target object inputs interaction information in the comment area and both the comment area and the bullet screen area are in an open state, the interaction area that is convenient for the target object to view can be automatically selected as the interaction active area according to the positions of the comment area and the bullet screen area in the video playback interface to display the feedback information. Or, the feedback information can be displayed in both the comment area and the bullet screen area.

[0060] According to the embodiments of the present disclosure, displaying the feedback information in the interaction active area of the video playback interface is not limited to determining the interaction active area. It can also include determining the display method. For example: based on the object attribute information of the target object, personalized information is determined. When the personalized information includes the information format, the feedback information is formatted according to the personalized information and displayed in the interaction active area.

[0061] Figure 4 Schematically shows a schematic diagram of a cross-region interaction mechanism according to an embodiment of the present disclosure.

[0062] Such as Figure 4 shown, the target object can input interaction information in the video playback interface 401. When inputting a comment in the comment area, the comment can be sent to the server port 405 through the comment area port 402, so that the large model loaded on the server can perform an operation of generating feedback information based on the interaction information. When inputting a bullet screen in the bullet screen area, the bullet screen can be sent to the server port 405 through the bullet screen area port 403. When giving a like in the like area, the like can be sent to the server port 405 through the like area port 404. The large model processes the sent interaction information and generates feedback information to be transmitted to the interaction active area port 406. The feedback information is sent to the interaction active area of the video playback interface 401 through the interaction active area port 406, and the feedback information is displayed in the interaction active area, so that cross-region interaction with the target object can be realized.

[0063] In some embodiments, the information format can include the font, font size, color, typesetting method, etc. of the text. The information format can also include the size, resolution, format, etc. of the picture. The information format can also include the resolution, frame rate, encoding format, etc. of the video.

[0064] For example, if the object attribute information of the target object indicates that the target object is an elderly user, and the personalized information indicates that the feedback information is to be displayed in a large font text format, the feedback information can be converted into a large font text format, and a voice playback function can also be added to facilitate reading by the elderly user.

[0065] According to an embodiment of the present disclosure, by formatting the feedback information according to the personalized information and then displaying it in the interactive active area, the personalized needs of multiple target objects with different object attribute information can be satisfied, and the user experience can be improved.

[0066] According to an embodiment of the present disclosure, for the operation S220 as shown in Figure 2 Based on the video segment being played on the video playback interface, the virtual object information for interacting with the target object can be determined, including: determining the virtual object information of the virtual object based on the identification information of the video segment and a predetermined mapping relationship, where the predetermined mapping relationship represents the correspondence between the identification information of the video segment and the virtual object information of the virtual object.

[0067] In an embodiment of the present disclosure, the identification information may be the position identification information of the video segment in the entire video. A video can be divided into multiple video segments in advance, and each video segment has its own identification information. Specifically, a video can be divided into multiple video segments according to the time progress of the video, and respective identification information can be added to each video segment in sequence according to the time progress.

[0068] The virtual object information can be extracted in advance according to the video content of each video segment, and a virtual object for interaction can be generated for each video segment. The virtual objects of different video segments can be the same or different. Associating the identification information and the virtual object information of each video segment gives the predetermined mapping relationship.

[0069] During the process of the target object watching the video, if the target object inputs interaction information at a certain time progress, the identification information of the video segment corresponding to this time progress is obtained, and according to the identification information and the predetermined mapping relationship, the virtual object information corresponding to this identification information is queried, and the virtual object is imitated according to the virtual object information for interaction, so as to provide feedback information for the target object using the virtual object.

[0070] According to an embodiment of the present disclosure, since the identification information of the video segment and the predetermined mapping relationship are determined in advance, when the target object inputs interaction information, the virtual object information can be directly and quickly determined, thereby improving the efficiency of responding to the interaction information of the target object.

[0071] According to an embodiment of the present disclosure, when the interaction method executes as shown in Figure 2Before the operation S220 shown determines the virtual object information of the virtual object for interacting with the target object based on the video clip being played on the video playback interface, the interaction method may include an operation of generating a predetermined mapping relationship. Generating the predetermined mapping relationship may include the following operations: when the video clip is of the plot type, determining the virtual object information based on the role information of the target role in the video clip; when the video clip is of the non-plot type, determining the virtual object information of the virtual object based on the video content of the video clip and the predetermined virtual rules; and generating a predetermined mapping relationship based on the identification information of the video clip and the virtual object information.

[0072] When the video clip is of the plot type, the virtual object information may be the information of a certain role in the current video clip. For example, identity information, personal ability information, and / or personality information, etc. For example, if the protagonist of the current video is of a certain occupation, the virtual object information may be the identity information of a certain occupation in the current video.

[0073] In some embodiments, if the current video clip includes multiple role information, the role information of the key role may be extracted as the virtual object information. The present disclosure is not limited thereto. Multiple virtual object information may also be obtained according to the multiple role information included in the current video clip. At this time, according to the interaction information input by the target object, the role that the user hopes to interact with may be identified as the virtual object, and the role information of the role that the user hopes to interact with may be used as the virtual object information.

[0074] For example, if the current video clip includes three roles, namely role A, role B, and role C, and the interaction information input by the target object is "I want to talk to B", then the virtual object for interacting with the target object is role B. The virtual object information is determined according to the role information of role B.

[0075] Alternatively, a button of "virtual object selection" may also be provided on the video playback interface for the target object to select the virtual object to interact with.

[0076] When the video clip is of the non-plot type, the virtual object information may also be determined based on the current video content and the predetermined virtual rules. The predetermined virtual rules may be the behavior logic rules for generating virtual objects, environmental interaction rules, etc. The predetermined virtual rules may be used in combination with the current video content to generate logical and interactive virtual object information.

[0077] For example, if the user is watching a video clip of a fire safety video, the behavior logic rules of firefighters and the environmental interaction rules may be used in combination with the fire safety video to determine that the firefighter is the virtual object, and the role information of the firefighter is used as the virtual object information.

[0078] Associating the identification information of the video clip and the virtual object information gives a predetermined mapping relationship.

[0079] According to an embodiment of the present disclosure, for different types of video clips, corresponding virtual object information is obtained by using different processing methods, so that the generated virtual object can well fit the video content and meet the user's personalized interaction needs.

[0080] According to an embodiment of the present disclosure, for the operation S230 as shown in Figure 2 Based on the virtual object information, interaction information, and video content of the video clip, the feedback information generated for the interaction information may include: generating identity prompt information for indicating the interaction identity of the large model based on the virtual object information; generating tone prompt information for indicating the interaction tone of the large model based on the video content; and inputting the identity prompt information, tone prompt information, and interaction information into the large model to generate feedback information.

[0081] In an embodiment of the present disclosure, the large model is a machine learning model that can recognize natural language and / or other inputs (such as audio-visual, images, speech, etc.) input into the large model, and perform comprehensive language processing tasks such as semantic analysis and answering questions, and then generate output information related to the interaction information and / or perform operations in response to the interaction information.

[0082] The large model learns the characteristics and rules of the input information by training a large amount of diverse training data. It usually has hundreds of millions to hundreds of billions of model parameters (model parameters are variables that control the behavior of the target model), and can capture complex relationships and patterns in the input information. The large model can include large language models, vision large models, multi-modal large models, and so on. The model involved in the embodiments of the present disclosure can be a general large model or an expert large model obtained by fine-tuning based on requirements. The embodiments of the present disclosure do not limit this.

[0083] Generating identity prompt information for indicating the interaction identity of the large model based on the virtual object information may include generating identity prompt information such as the name, self-introduction, area of expertise, and interaction style of the virtual object. So that the large model can better simulate the behavior and language of the virtual object to fit the role in the video clip during the interaction process. When the large model answers the questions of the target object or chats with the target object, it can fit the identity and characteristics of the virtual object and provide a real and interesting interaction experience.

[0084] Generating tone prompt information for indicating the interaction tone of the large model based on the video content may include generating tone prompt information of the virtual object according to the emotions expressed in the video content or the environmental atmosphere, etc. For example, whether the virtual object is cheerful, serious, tense, relaxed, etc.

[0085] In some embodiments, a video content summary including key events, character descriptions, and emotional expressions may be generated based on the video content of a video clip, and tone prompt information for indicating the interaction tone of a large model may be generated based on the video content summary. The present disclosure is not limited thereto. The multi-modal large model may also be used to process the video clip to generate the tone prompt information.

[0086] Applying the generated tone prompt information to the interaction process of the large model can enable the large model to adjust the output tone style according to the tone prompt information when answering the questions of the target object or chatting with the target object, and output feedback information with emotional tendency and personalization.

[0087] Inputting the identity prompt information, tone prompt information, and interaction information into the large model, the large model can identify the identity of the virtual object to be played and the tone of the reply by parsing the identity prompt information and tone prompt information. The specific needs of the target object can be identified by parsing the interaction information. After identifying the needs of the target object, the large model can combine its own huge knowledge base and powerful language processing capabilities, and generate feedback information for the needs of the target object according to the identity and tone of the virtual object. Thus, personalized interaction with the target object can be quickly completed.

[0088] According to an embodiment of the present disclosure, inputting the identity prompt information, tone prompt information, and interaction information into the large model to generate feedback information includes: determining personalized information based on the object attribute information of the target object; and when the personalized information includes an expression mode, inputting the identity prompt information, tone prompt information, personalized information, and interaction information into the large model to generate feedback information.

[0089] In the embodiment of the present disclosure, the object attribute information of the target object may include information such as the gender, age, and region of the object. In some embodiments, the object attribute information of the target object may be determined according to the historical behavior data of the target object.

[0090] The personalized information may include the expression mode preferred by the target object, or the habitual speaking mode, etc. Different target objects may prefer different expression modes. For example, for young target objects, they will prefer lively and trendy languages and expression modes. For elderly target objects, they will prefer steady and concise languages and expression modes.

[0091] Inputting the identity prompt information, tone prompt information, personalized information, and interaction information into the large model, the large model can not only meet the identity and tone requirements of the virtual object, but also combine the expression mode preferred by the target object. Thus, feedback information that meets the personalized needs of the user can be generated.

[0092] Figure 5A flowchart of an interaction method according to another embodiment of the present disclosure is schematically shown.

[0093] As Figure 5 shown, the target object inputs interaction information 502 in the video playback interface 501 of the terminal device. The terminal device sends the interaction information 502 to the server. The server obtains the interaction information 502 sent by the terminal device. In response to receiving the interaction information 502 input by the target object in the video playback interface 501, based on the video content of the video segment 503 being played in the video playback interface 501, the server determines virtual object information 504 of the virtual object for interacting with the target object. A tone prompt information 508 for indicating the interaction tone of the large model M509 is generated according to the video content of the video segment 503. An identity prompt information 507 for indicating the interaction identity of the large model M509 is generated according to the virtual object information 504. Personalized information 506 is generated according to the object attribute information 505 of the target object. The identity prompt information 507, the tone prompt information 508, the personalized information 506, and the interaction information 502 are input into the large model M509 to generate feedback information 510. The server sends the feedback information 510 to the interaction active area 511 of the video playback interface of the terminal device for display, so as to realize cross-region interaction between the terminal device and the target object.

[0094] According to an embodiment of the present disclosure, inputting the identity prompt information, the tone prompt information, and the interaction information into the large model to generate feedback information may include: obtaining status information of the target object watching the target video, where the status information includes at least one of an expression image and voice. Updating the tone prompt information using the status information to obtain updated tone prompt information; and inputting the identity prompt information, the updated tone prompt information, and the interaction information into the large model to generate feedback information.

[0095] In some embodiments, when the interaction information of the target object is voice information, the status information of the target object may be determined according to the voice, intonation, speech rate, etc. of the target object. A faster intonation and speech rate may indicate that the target object is nervous or excited, and a slower intonation and speech rate may indicate fatigue or frustration. A rising pitch may indicate excitement, and a decreasing pitch may indicate fatigue, etc.

[0096] In some embodiments, when the interaction information of the target object is an expression image, the status information of the target object may be determined according to the expression of the expression image. For example, if the expression image is a smiling face, it indicates that the target object is in a happy state.

[0097] In some embodiments, when the interaction information of the target object is a video, the status information of the target object may be determined according to the facial expressions, body languages, etc. in the video.

[0098] In some embodiments, when the interaction information of the target object is text information, natural language processing tools can be used to identify the emotion words in the interaction information, such as emotion words related to or similar to happiness, anger, anxiety, etc. The state information of the target object watching the target video is judged according to the identified emotion words.

[0099] Optional example, the state information of the target object is not limited to being determined by the interaction information. It can also be voice or facial expression images obtained through other channels. As long as it is information representing the state of the target object watching the video segment.

[0100] Updating the tone prompt information using the state information can be adding the state information of the target object to the tone prompt information to obtain the updated tone prompt information, so that when the large model processes input information such as identity prompt information, updated tone prompt information, and interaction information, it can consider the current emotional tendency information of the target object, and more user-intent and emotion-expression compliant feedback information can be generated according to the current emotional tendency information of the target object. However, it is not limited to this. It can also be adjusting the tone prompt information using the state information to obtain the updated tone prompt information. For example, in the case where the state information represents that the target object is angry, the tone prompt information used to represent happiness can be updated to a more detailed tone prompt information representing stability or relaxation.

[0101] According to an embodiment of the present disclosure, after or before performing the operation S240 as Figure 2 shown, the interaction method may further include: determining the interaction intention of the target object based on the interaction information; and determining a feedback strategy based on the interaction intention; wherein, the feedback strategy includes at least one of the following: a trigger strategy for generating feedback information, a feedback frequency strategy.

[0102] In some embodiments, the interaction heat of the target object can be determined according to the content and frequency of the interaction information output by the target object. When the interaction heat of the target object is high, indicating a strong willingness to communicate, a high-frequency feedback strategy can be adjusted and adopted. For example, if the target object continuously and quickly inputs multiple questions, the virtual object needs to reply in a timely manner to maintain the fluency of the conversation.

[0103] When the interaction heat of the target object is low, or the interaction content is relatively simple, a low-frequency feedback strategy is adopted. For example, if the target object simply says "Hello", the virtual object can pause slightly and then reply "Hello, how can I help you", avoiding making the target object feel pressured by overly frequent replies.

[0104] In some embodiments, for some urgent or important interaction intentions, an immediate trigger strategy is adopted. For some non-urgent interaction intentions, a delayed trigger strategy can be adopted. For example, when the user asks "What's the weather like tomorrow", the virtual object can delay slightly after the target object inputs and then feedback the weather information to simulate the thinking and reaction process of humans. It can also trigger the generation of feedback information according to specific conditions. For example, when the target object asks the same type of question continuously for multiple times, or when the interaction heat reaches a certain level, more detailed feedback information generation is triggered.

[0105] In some embodiments, the feedback frequency can be dynamically adjusted according to the actual situation during the interaction process. For example, when the target object shows strong interest in a certain topic, the feedback frequency can be appropriately increased to discuss the topic in depth; when the target object starts to show impatience, the feedback frequency should be reduced to avoid disturbing the user excessively.

[0106] According to the embodiments of the present disclosure, by determining the interaction strategy according to the user's intention, the generation strategy of the feedback information can be dynamically adjusted to ensure that the feedback information has strong real-time performance and interactivity.

[0107] Figure 6 A block diagram of an interaction device based on artificial intelligence according to an embodiment of the present disclosure is schematically shown.

[0108] As Figure 6 shown, the interaction device includes an information receiving module 610, an object determining module 620, a feedback generating module 630, and a feedback displaying module 640.

[0109] The information receiving module 610 is used to obtain the interaction information input by the target object on the video playback interface.

[0110] The object determining module 620 is used to, in response to receiving the interaction information, determine the virtual object information of the virtual object for interacting with the target object based on the video segment being played on the video playback interface.

[0111] The feedback generating module 630 is used to generate feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment.

[0112] The feedback displaying module 640 is used to display the feedback information in the interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

[0113] According to the embodiments of the present disclosure, the feedback displaying module 640 includes: a state determining sub-module and a displaying sub-module.

[0114] A status determination sub-module, configured to determine an interaction active area from multiple interaction areas based on the opening status of each of the multiple interaction areas.

[0115] A first display sub-module, configured to display the feedback information in the form of bullet comments in the bullet comment area when the interaction active area includes the bullet comment area.

[0116] According to an embodiment of the present disclosure, the feedback display module 640 includes: a personality determination sub-module and a second display sub-module.

[0117] A personality determination sub-module, configured to determine personalized information based on the object attribute information of the target object.

[0118] A second display sub-module, configured to perform format conversion on the feedback information according to the personalized information and display it in the interaction active area when the personalized information includes an information format.

[0119] According to an embodiment of the present disclosure, the information receiving module includes: a status determination sub-module and an information receiving sub-module.

[0120] A status determination sub-module, configured to determine an interaction active area from multiple interaction areas based on the opening status of each of the multiple interaction areas.

[0121] An information receiving sub-module, configured to obtain the interaction information input by the target object in the comment area from the interaction active area.

[0122] According to an embodiment of the present disclosure, the object determination module 620 includes a first determination sub-module.

[0123] A first determination sub-module, configured to determine the virtual object information of the virtual object based on the identification information of the video segment and a predetermined mapping relationship, where the predetermined mapping relationship represents the corresponding relationship between the identification information of the video segment and the virtual object information of the virtual object.

[0124] According to an embodiment of the present disclosure, the object determination module 620 further includes a second determination sub-module, a third determination sub-module, and a generation sub-module.

[0125] A second determination sub-module, configured to determine the virtual object information based on the role information of the target role in the video segment when the video segment is of a plot type.

[0126] A third determination sub-module, configured to determine the virtual object information of the virtual object based on the video content of the video segment and a predetermined virtual rule when the video segment is of a non-plot type.

[0127] A mapping relationship generation sub-module, configured to generate a predetermined mapping relationship based on the identification information of the video segment and the virtual object information.

[0128] According to an embodiment of the present disclosure, the feedback generation module 630 includes a first information generation sub-module, a second information generation sub-module, and a third information generation sub-module.

[0129] The first information generation sub-module is configured to generate identity prompt information for indicating the interaction identity of the large model based on the virtual object information.

[0130] The second information generation sub-module is configured to generate tone prompt information for indicating the interaction tone of the large model based on the video content.

[0131] The third information generation sub-module is configured to input the identity prompt information, the tone prompt information, and the interaction information into the large model to generate feedback information.

[0132] According to an embodiment of the present disclosure, the third information generation sub-module includes an information determination unit and an information generation unit.

[0133] The information determination unit is configured to determine personalized information based on the object attribute information of the target object.

[0134] The first information generation unit is configured to input the identity prompt information, the tone prompt information, the personalized information, and the interaction information into the large model to generate feedback information when the personalized information includes an expression manner.

[0135] According to an embodiment of the present disclosure, the third information generation sub-module further includes an acquisition unit, an update unit, and a second information generation unit.

[0136] The acquisition unit is configured to acquire the status information of the target object watching the target video, where the status information includes at least one of an expression image and voice.

[0137] The update unit is configured to update the tone prompt information by using the status information to obtain updated tone prompt information.

[0138] The second information generation unit is configured to input the identity prompt information, the updated tone prompt information, and the interaction information into the large model to generate feedback information.

[0139] According to an embodiment of the present disclosure, the feedback display module 640 includes an active area determination sub-module and a bullet screen area display sub-module.

[0140] The active area determination sub-module is configured to determine an interaction active area from multiple interaction areas based on the opening status of each of the multiple interaction areas.

[0141] The bullet screen area display sub-module is configured to display the feedback information in the bullet screen area in the form of a bullet screen when the interaction active area includes a bullet screen area.

[0142] According to an embodiment of the present disclosure, the feedback display module 640 includes a personalized information determination sub-module and a personalized information display sub-module.

[0143] The personalized information determination sub-module is configured to determine personalized information based on the object attribute information of the target object.

[0144] The personalized information display sub-module is configured to, when the personalized information includes an information format, perform format conversion on the feedback information according to the personalized information and display it in the interactive active area.

[0145] According to an embodiment of the present disclosure, the interactive area includes a comment area; the above-mentioned interactive device further includes a receiving module configured to receive the interactive information input by the target object in the comment area.

[0146] According to an embodiment of the present disclosure, the above-mentioned interactive device further includes an interaction intention determination module and a policy determination module.

[0147] The interaction intention determination module is configured to determine the interaction intention of the target object based on the interactive information.

[0148] The policy determination module is configured to determine a feedback policy based on the interaction intention; wherein, the feedback policy includes at least one of the following: a trigger policy for executing feedback information generation, a feedback frequency policy.

[0149] According to an embodiment of the present disclosure, any multiple modules among the information receiving module 610, the object determination module 620, the feedback generation module 630, and the feedback display module 640 can be combined and implemented in one module, or any one of them can be split into multiple modules. Or, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module.

[0150] According to an embodiment of the present disclosure, at least one of the information receiving module 610, the object determination module 620, the feedback generation module 630, and the feedback display module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by any other reasonable means of integrating or packaging circuits, etc., in hardware or firmware, or can be implemented in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Or, at least one of the information receiving module 610, the object determination module 620, the feedback generation module 630, and the feedback display module 640 can be at least partially implemented as a computer program module, which can execute the corresponding functions when the computer program module is run.

[0151] Figure 7A structural block diagram of an agent of artificial intelligence according to an embodiment of the present disclosure is schematically shown.

[0152] In an embodiment of the present disclosure, as Figure 7 shown, the AI agent 700 may include an input module 710, a processing module 720, and an output module 730.

[0153] The input module 710 is configured to receive input information.

[0154] The processing module 720 is configured to determine a target task based on the input information received by the input module, determine a large model based on the target task, and execute an interaction method based on artificial intelligence provided according to an embodiment of the present disclosure by invoking the large model.

[0155] The output module 730 is configured to output the output information obtained by the processing module.

[0156] According to an embodiment of the present disclosure, the input module 710 is responsible for receiving or perceiving information such as queries, requests, instructions, signals, or data from the outside world (such as a user or an external environment), and converting it into a format that the AI agent 700 can understand and process. The input module 710 is the primary link for the AI agent 700 to interact with the outside world, enabling the AI agent 700 to efficiently and accurately obtain necessary "sensory" information from the outside world and respond to this information.

[0157] In an example, the input module 710 may input the interaction information described above.

[0158] In an example, the processing module 720 is the core support for the AI agent 700's ability to handle complex tasks. The processing module 920 may execute the interaction method based on artificial intelligence described above.

[0159] In an example, the performance of the processing module 720 may be closely related to the large model on which the AI agent 700 is based. To fully utilize the capabilities of the large model, the internal structure of the processing module 720 may be designed to be highly configurable and extensible to cope with various different types of tasks and requirements in real-world scenarios.

[0160] In an example, after the AI agent 700 obtains the interaction information, the processing module 720 may use the large model to process the interaction information of the target object, obtain feedback information, and transmit it to the output module 730.

[0161] It can be understood that although large language models have excellent language understanding and generation capabilities, like humans, without the aid of any tools, the tasks they can solve are very limited. When the AI agent 700 is given the ability to call tools, it can perform tasks such as mathematical operations with the help of a calculator, data analysis with the help of Python, and search tasks with the help of a search engine.

[0162] In the example, the output module 730 can output the feedback information described above.

[0163] The AI agent 700 according to the embodiments of the present disclosure can simply and effectively improve the degree of intelligence, and enhance flexibility and versatility.

[0164] Figure 8 FIG. shows a schematic block diagram of an example electronic device 800 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0165] As Figure 8 shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0166] A plurality of components in the device 800 are connected to the input / output (I / O) interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disc, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0167] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the artificial intelligence-based interaction method. For example, in some embodiments, the artificial intelligence-based interaction method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the artificial intelligence-based interaction method described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the artificial intelligence-based interaction method in any other suitable way (e.g., by means of firmware).

[0168] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0170] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection 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 include, 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 a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] To provide for 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for 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 acoustic, speech, or tactile input).

[0172] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system 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), and the Internet.

[0173] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0174] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and no limitation is imposed herein.

[0175] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. An artificial intelligence-based interaction method, comprising: Obtaining interaction information input by a target object on a video playback interface; In response to receiving the interaction information, determining virtual object information of a virtual object for interacting with the target object based on a video segment being played on the video playback interface; Generating feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment; And Displaying the feedback information in an interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

2. The method according to claim 1, wherein, The displaying the feedback information in the interaction active area of the video playback interface includes: Determining the interaction active area from multiple interaction areas based on the opening states of the multiple interaction areas; and When the interaction active area includes a bullet screen area, displaying the feedback information in the bullet screen area in the form of a bullet screen.

3. The method according to claim 1, wherein, The displaying the feedback information in the interaction active area of the video playback interface includes: Determining personalized information based on the object attribute information of the target object; and When the personalized information includes an information format, performing format conversion on the feedback information according to the personalized information and displaying it in the interaction active area.

4. The method according to any one of claims 1 to 3, wherein The obtaining interaction information input by a target object on a video playback interface includes: Determining the interaction active area from multiple interaction areas based on the opening states of the multiple interaction areas; Obtaining the interaction information input by the target object from the interaction active area.

5. The method according to any one of claims 1 to 4, wherein The determining virtual object information of a virtual object for interacting with the target object based on a video segment being played on the video playback interface includes: Determining the virtual object information of the virtual object based on the identification information of the video segment and a predetermined mapping relationship, where the predetermined mapping relationship represents the corresponding relationship between the identification information of the video segment and the virtual object information of the virtual object.

6. The method according to claim 5, further comprising: When the video segment is of a plot type, determining the virtual object information based on the role information of the target role in the video segment; When the video segment is of a non-plot type, determining the virtual object information of the virtual object based on the video content of the video segment and a predetermined virtual rule; And Generating the predetermined mapping relationship based on the identification information of the video segment and the virtual object information.

7. The method according to any one of claims 1 to 6, wherein The generating feedback information for the interaction information based on the virtual object information, the interaction information, and the video content of the video segment includes: Generating identity prompt information for indicating the interaction identity of the large model based on the virtual object information; Generating tone prompt information for indicating the interaction tone of the large model based on the video content; and Inputting the identity prompt information, the tone prompt information, and the interaction information into the large model to generate the feedback information.

8. The method according to claim 7, wherein Inputting the identity prompt information, the tone prompt information, and the interaction information into the large model to generate the feedback information includes: Determining personalized information based on the object attribute information of the target object; and When the personalized information includes an expression mode, inputting the identity prompt information, the tone prompt information, the personalized information, and the interaction information into the large model to generate the feedback information.

9. The method according to claim 7, wherein Inputting the identity prompt information, the tone prompt information, and the interaction information into the large model to generate the feedback information includes: Obtaining the status information of the target object watching the target video, where the status information includes at least one of an expression image and speech; Updating the tone prompt information using the status information to obtain updated tone prompt information; and Inputting the identity prompt information, the updated tone prompt information, and the interaction information into the large model to generate the feedback information.

10. The method according to any one of claims 1 to 9 further includes: Determining the interaction intention of the target object based on the interaction information; And Determining a feedback strategy based on the interaction intention; Wherein the feedback strategy includes at least one of the following: A trigger strategy for executing feedback information generation, a feedback frequency strategy.

11. An interaction device based on artificial intelligence includes: An information receiving module for obtaining interaction information input by a target object on a video playback interface; An object determining module for determining virtual object information of a virtual object for interacting with the target object based on a video segment being played on the video playback interface; A feedback generating module for generating feedback information for the interaction information in response to receiving the interaction information based on the virtual object information, the interaction information, and the video content of the video segment; And A feedback display module for displaying the feedback information in an interaction active area of the video playback interface, where the interaction active area is determined based on the opening states of multiple interaction areas in the video playback interface.

12. An intelligent agent of artificial intelligence includes: An input module for receiving input information; A processing module for determining a target task based on the input information received by the input module, and executing the method according to any one of claims 1 to 10 based on the target task to obtain output information; An output module for outputting the output information obtained by the processing module.

13. An electronic device includes: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 10.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images