Information interaction method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure provide an information interaction method and apparatus, a device, and a storage medium. The information interaction method comprises: providing at least one scenario in an interaction window between a user and a digital assistant, a first scenario among the at least one scenario being configured with corresponding configuration information to execute a corresponding type of task, and the configuration information comprising at least one of the following: scenario setting information and plug-in information, wherein the scenario setting information is used for describing information related to a corresponding scenario, and the plug-in information indicates at least one plug-in used for executing the task in the corresponding scenario; and in response to receiving the selection of the first scenario among the at least one scenario, executing interaction between the user and the digital assistant at least on the basis of the configuration information of the first scenario. In this way, environments and task instances can be flexibly selected on the basis of user requirements, thereby implementing diversified interaction operations with the digital assistant.

Description

Method, device, equipment and storage medium for information interaction

[0001] This application claims priority to the Chinese invention patent application entitled “Methods, devices, equipment and storage media for information interaction” filed on October 31, 2023, with application number 202311436542.9, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for information interaction. Background Art

[0003] With the rapid development of Internet technology, the Internet has become an important platform for people to access and share content. Users can access the Internet through terminal devices and enjoy various Internet services. Terminal devices present corresponding content and interact with users and provide services to users through the user interface of the application. Therefore, a rich and colorful application interactive interface is an important means to enhance the user experience. With the development of information technology, various terminal devices can provide people with various services in work and life. For example, terminal devices can be deployed with applications that provide services. Terminal devices or applications can provide users with digital assistant-like functions to assist users in using terminal devices or applications. How to improve the flexibility of user interaction with digital assistants is a technical problem that needs to be explored.

[0004] Summary of the Invention

[0005] In a first aspect of the present disclosure, a method for information interaction is provided. The method comprises: providing at least one scenario in an interaction window between a user and a digital assistant, wherein a first scenario in the at least one scenario is configured with corresponding configuration information for performing a corresponding type of task, the configuration information comprising at least one of the following: scenario setting information and plug-in information, wherein the scenario setting information is used to describe information related to the corresponding scenario, and the plug-in information indicates at least one plug-in for performing the task in the corresponding scenario; and in response to receiving a selection of the first scenario in the at least one scenario, performing interaction between the user and the digital assistant based at least on the configuration information of the first scenario.

[0006] In a second aspect of the present disclosure, a method for information interaction is provided. The method includes: in response to an operation of starting a new topic, starting a first topic in an interaction window between a user and a digital assistant; presenting a dividing line between the first topic and a previous topic in the interaction window; and in response to performing an interaction between the user and the digital assistant in the first topic, presenting a first topic identifier at an associated area of ​​the dividing line, the first topic identifier being based at least on interaction information between the user and the digital assistant in the first topic.

[0007] In a third aspect of the present disclosure, a method for creating a scenario is provided. The method comprises: in response to receiving a scenario creation operation, providing a first page for creating a target scenario; obtaining, via the first page, scenario creation information for the target scenario, the scenario creation information including at least target configuration information for the target scenario, the target configuration information including at least one of the following: scenario setting information describing information related to the target scenario and plug-in information indicating at least one plug-in for performing a task in the target scenario; and in response to receiving a creation confirmation operation, creating the target scenario based on the obtained target configuration information.

[0008] In a fourth aspect of the present disclosure, a device for information interaction is provided. The device includes: a scenario providing module configured to provide at least one scenario in an interaction window between a user and a digital assistant, wherein a first scenario in the at least one scenario is configured with corresponding configuration information to perform a corresponding type of task, the configuration information including at least one of the following: scenario setting information and plug-in information, wherein the scenario setting information is used to describe information related to the corresponding scenario, and the plug-in information indicates at least one plug-in for performing the task in the corresponding scenario; and an interaction execution module configured to, in response to receiving a selection of the first scenario in the at least one scenario, execute the interaction between the user and the digital assistant based at least on the configuration information of the first scenario.

[0009] In a fifth aspect of the present disclosure, a device for information interaction is provided. The device includes: a topic start module configured to, in response to an operation of starting a new topic, start a first topic in an interaction window between a user and a digital assistant; a dividing line presentation module configured to present a dividing line between the first topic and a previous topic in the interaction window; and an identifier presentation module configured to, in response to an interaction between the user and the digital assistant in the first topic, present a first topic identifier at an associated area of ​​the dividing line, the first topic identifier being based at least on interaction information between the user and the digital assistant in the first topic.

[0010] In a sixth aspect of the present disclosure, a device for scene creation is provided. The device includes: a page providing module configured to, in response to receiving a scene creation operation, provide a first page for creating a target scene; an information acquisition module configured to, via the first page, acquire scene creation information of the target scene, the scene creation information including at least target configuration information of the target scene, the target configuration information including at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in for performing a task in the target scene; and a scene creation module configured to, in response to receiving a creation confirmation operation, create the target scene based on the acquired target configuration information.

[0011] In a seventh aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect, the method of the second aspect, or the method of the third aspect.

[0012] In an eighth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect, the method of the second aspect, or the method of the third aspect.

[0013] It should be understood that the content described in this section is not intended to limit the key features 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

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0015] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0016] 2A to 2H are schematic diagrams illustrating example client interfaces of interactive windows according to some embodiments of the present disclosure;

[0017] 3A to 3I are schematic diagrams showing example client interfaces for creating scenes according to some embodiments of the present disclosure;

[0018] 4A to 4I are schematic diagrams illustrating example client interfaces for editing a created scene according to some embodiments of the present disclosure;

[0019] FIG5 shows a flowchart of a process for information interaction according to some embodiments of the present disclosure;

[0020] FIG6 shows a flowchart of a process for information interaction according to some embodiments of the present disclosure;

[0021] FIG7 shows a flowchart of a process for scene creation according to some embodiments of the present disclosure;

[0022] FIG8 shows a block diagram of an apparatus for information interaction according to some embodiments of the present disclosure;

[0023] FIG9 shows a block diagram of an apparatus for information interaction according to some embodiments of the present disclosure;

[0024] FIG10 shows a block diagram of an apparatus for scene creation according to some embodiments of the present disclosure; and

[0025] FIG11 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0026] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below.

[0028] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0029] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0030] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0031] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0033] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0034] 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In this example environment 100, a digital assistant 120 and an application 125 are installed in a terminal device 110. A user 140 can interact with the digital assistant 120 and the application 125 via the terminal device 110 and / or an attached device of the terminal device 110.

[0035] In some embodiments, the digital assistant 120 and the application 125 can be downloaded and installed on the terminal device 110. In some embodiments, the digital assistant 120 and the application 125 can also be accessed through other means, such as through a web page. In the environment 100 of FIG. 1 , in response to the application 125 being launched, the terminal device 110 can present an interface 150 of the digital assistant 120 and the application 125.

[0036] Applications 125 include, but are not limited to, one or more of the following: chat applications (also known as instant messaging applications), document applications, audio and video conferencing applications, email applications, task applications, calendar applications, objectives and key results (OKR) applications, and the like. Although a single application is shown in FIG1 , in reality, multiple applications may be installed on the terminal device 110. In some embodiments, the applications 125 may include a multi-functional collaboration platform, such as an office collaboration platform (also known as an office suite) that can provide integration of various types of applications or components to facilitate people's office work, communication, and other activities. In the multi-functional collaboration platform, people can start different applications or components as needed to complete corresponding information processing, sharing, communication, and the like.

[0037] Application 125 may provide content entities 126. Content entities 126 may be content instances created by user 140 or other users on application 125. For example, depending on the type of application 125, content entities 126 may be documents (e.g., word documents, PDF documents, presentations, spreadsheets, etc.), emails, messages (e.g., conversation messages on instant messaging applications), calendars, schedules, tasks, audio, video, images, etc.

[0038] In some embodiments, the digital assistant 120 can be provided by a separate application or can be integrated into an application 120 that can provide content entities. The application used to provide the client interface of the digital assistant can correspond to a single-function application or a multi-function collaboration platform, such as an office suite or other collaboration platform that can integrate multiple components. In some embodiments, the digital assistant 120 supports the use of plug-ins. Each plug-in can provide one or more functions of the application. Such plug-ins include, but are not limited to, one or more of the following: a search plug-in, a contact plug-in, a message plug-in, a document plug-in, a table plug-in, an email plug-in, a calendar plug-in, a schedule plug-in, a task plug-in, and the like.

[0039] Digital assistant 120 is an intelligent assistant for the user, capable of intelligent dialogue and information processing. In embodiments of the present disclosure, digital assistant 120 is used to interact with user 140 to assist user 140 in using a terminal device or application. An interaction window with digital assistant 120 may be presented in the client interface. In this interaction window, user 140 can communicate with digital assistant 120 by inputting natural language to instruct the digital assistant to assist in completing various tasks, including operations on content entity 126.

[0040] In some embodiments, the digital assistant 120 can be included as a contact of the user 140 in the current user 140's contact list in the office suite, or included in the information flow of the chat component. In some embodiments, the user 140 has a corresponding relationship with the digital assistant 120. For example, the first digital assistant corresponds to the first user, the second digital assistant corresponds to the second user, and so on. In some embodiments, the first digital assistant can uniquely correspond to the first user, the second digital assistant can uniquely correspond to the second user, and so on. In other words, the first digital assistant of the first user can be specific to or exclusive to the first user. For example, in the process of the first digital assistant providing assistance or services to the first user, the first digital assistant can utilize its historical interaction information with the first user, the data authorized by the first user to which it has access, the current interaction context with the first user, etc. If the first user is an individual or person, the first digital assistant can be considered a personal digital assistant. It is understood that in the disclosed embodiments, the first digital assistant accesses the data to which it is granted permission based on the authorization of the first user. It should be understood that "uniquely corresponding" or similar expressions in this disclosure are not intended to limit the first digital assistant to being updated accordingly based on the interaction process between the first user and the first digital assistant. Of course, depending on actual application needs, the digital assistant 120 does not have to be specific to the current user 140, but can be a general digital assistant.

[0041] In some embodiments, multiple interaction modes can be provided between user 140 and digital assistant 120, and flexible switching between the multiple interaction modes can be achieved. When a certain interaction mode is triggered, a corresponding interaction area is presented to facilitate interaction between user 140 and digital assistant 120. In different interaction modes, the interaction methods between user 140 and digital assistant 120 are different, which can flexibly adapt to the interaction needs in different application scenarios.

[0042] In some embodiments, information processing services specific to user 140 can be provided based on historical interaction information between user 140 and digital assistant 120 and / or data ranges specific to user 140. In some embodiments, historical interaction information of user 140 interacting with digital assistant 120 in multiple interaction modes can be stored in association with user 140. In this way, in one of the multiple interaction modes (any or a designated one), digital assistant 120 can provide services to user 140 based on the historical interaction information stored in association with user 140.

[0043] The digital assistant 120 can be called or awakened by an appropriate means (e.g., a shortcut key, a button, or voice) to present an interaction window with the user 140. By selecting the digital assistant 1201, the interaction window with the digital assistant 120 can be opened. The interaction window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. In other embodiments, the digital assistant 120 can be awakened through an entry control or menu provided in a page, or by inputting a preset command.

[0044] The interaction window between the digital assistant 120 and the user 140 may include a conversation window, such as a conversation window in an instant messaging application or an instant messaging module of a target application. In some embodiments, the interaction window between the digital assistant 120 and the user 140 may include a floating window corresponding to the digital assistant.

[0045] In some embodiments, digital assistant 120 may support a conversation window interaction mode, also referred to as conversation mode. In this interaction mode, a conversation window is presented between user 140 and digital assistant 120, in which user 140 and digital assistant 120 interact through conversation messages. In conversation mode, digital assistant 120 can perform tasks based on the conversation messages in the conversation window.

[0046] In some embodiments, the conversation mode between user 140 and digital assistant 120 can be invoked or awakened by an appropriate means (e.g., a shortcut key, button, or voice) to present a conversation window. By selecting digital assistant 120, a conversation window with digital assistant 120 can be opened. The conversation window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like.

[0047] In some embodiments, the digital assistant 120 may support an interactive mode of a floating window (or floating window), also referred to as a floating window mode. When the floating window mode is triggered, the operation panel (also referred to as a floating window) corresponding to the digital assistant 120 is presented, and the user 140 can issue instructions to the digital assistant 120 based on the operation panel. In some embodiments, the operation panel may include at least one candidate shortcut instruction. Alternatively or additionally, the operation panel may include an input control for receiving instructions. In floating window mode, the digital assistant 120 can perform tasks according to instructions issued by the user 140 through the operation panel.

[0048] In some embodiments, the floating window mode of the user 140 and the digital assistant 120 can also be called or awakened by an appropriate means (e.g., a shortcut key, a button, or voice) to present the corresponding operation panel. In some embodiments, the awakening of the digital assistant 120 can be supported in a specific application, such as a document application, to provide interaction in the floating window mode. In some embodiments, in order to trigger the floating window mode to present the operation panel corresponding to the digital assistant 120, an entry control for the digital assistant 120 can be presented in the application interface. In response to detecting a triggering operation for the entry control, it can be determined that the floating window mode is triggered, and the operation panel corresponding to the digital assistant 120 is presented in the target interface area.

[0049] In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly taken as an example, which is a conversation window.

[0050] In some embodiments, the terminal device 110 communicates with the server 130 to enable the provision of services to the digital assistant 120 and the application 125. The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the user (such as a "wearable" circuit, etc.). The application 130 can be various types of computing systems / servers that can provide computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0051] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0052] As briefly mentioned above, digital assistants can assist users in using terminal devices or applications. Some applications can provide integrated functions of different plug-ins. In addition to being able to have free conversations with digital assistants, users can also use natural language instructions to enable digital assistants to use different plug-ins to complete some more complex business-related operations related to the application, such as creating documents, inviting schedules, creating tasks, etc. However, since most users cannot explore the usage scenarios of digital assistants through interaction with digital assistants, it is necessary to provide users with targeted guidance. In addition, traditionally, when digital assistants are needed to perform tasks in different scenarios, users often need to interact with different digital assistants (that is, each digital assistant is only used to perform tasks in one scenario), which will result in information not being saved in one place, and these multiple digital assistants cannot share information. This will make the interactive function of digital assistants less flexible.

[0053] According to some embodiments of the present disclosure, an improved scheme for information interaction is proposed. In an embodiment of the present disclosure, at least one scene is provided in a conversation window between a user and a digital assistant, and the first scene in the at least one scene is configured with corresponding configuration information to perform a task of a corresponding type, and the configuration information includes at least one of the following: scene setting information, plug-in information, wherein the scene setting information is used to describe information related to the corresponding scene, and the plug-in information indicates at least one plug-in for performing a task in the corresponding scene. In response to receiving a selection of the first scene in the at least one scene, in the conversation window, the interaction between the user and the digital assistant is performed based at least on the configuration information of the first scene. In this way, scene selection can be achieved.

[0054] According to some embodiments of the present disclosure, an improved scheme for information interaction is proposed. In an embodiment of the present disclosure, in response to an operation of opening a new topic, a first topic is opened in a conversation window between a user and a digital assistant. A dividing line between the first topic and the previous topic is presented in the conversation window. In response to performing an interaction between the user and the digital assistant in the first topic, a first topic identifier is presented at an associated area of ​​the dividing line, and the first topic identifier is based at least on the interaction information between the user and the digital assistant in the first topic. In this way, different scenarios / topics can be distinguished.

[0055] According to some embodiments of the present disclosure, an improved scheme for scene creation is proposed. In an embodiment of the present disclosure, in a conversation window between a first user and a first digital assistant, in response to receiving a scene creation operation, a first page for creating a target scene is provided. Via the first page, scene creation information of the target scene is obtained, the scene creation information includes at least target configuration information of the target scene, and the target configuration information includes at least one of the following: scene setting information, plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in for performing tasks under the target scene. In response to receiving a creation confirmation operation, the target scene is created based on the acquired target configuration information. In this way, editing of the created scene can be achieved.

[0056] In general, users can only communicate with digital assistants by selecting plug-ins, but this requires users to have a certain level of cognitive ability, know which plug-ins to choose for different task scenarios, and manually select the plug-ins one by one. According to the embodiments of the present disclosure, by providing scenario-based interaction, the user's entry threshold for using digital assistants is lowered and the user's operation is simplified.

[0057] Some example embodiments of the present disclosure will be described in detail below with reference to examples in the accompanying drawings.

[0058] As mentioned above, in an embodiment of the present disclosure, a digital assistant is used to interact with a user. An interaction window between the user and the digital assistant can be presented in the client interface. The interaction window between the user and the digital assistant may include a conversation window, in which the interaction between the user and the digital assistant may be presented in the form of a conversation message. Alternatively or additionally, the interaction window between the user and the digital assistant may also include other types of windows, such as a window in floating mode, in which the user can trigger the digital assistant to perform corresponding operations by inputting instructions, selecting shortcut instructions, etc. As an intelligent assistant, the digital assistant has intelligent dialogue and information processing capabilities. In the interaction window, the user inputs an interactive message, and the digital assistant provides a reply message in response to the user input. The client interface for providing the digital assistant may correspond to a single-function application or a multi-function collaboration platform, such as an office suite or other collaboration platform capable of integrating multiple components.

[0059] In some embodiments, the terminal device 110 can present a conversation window between a user and one or more other users. Here, the conversation window between the user and one other user can be, for example, a single chat window between user A and user B, and the conversation window between the user and multiple other users can be, for example, a group chat window between user A and a group of other users. The user can interact with at least one other user by sending and / or receiving messages in the conversation window. The terminal device 110 can, for example, determine the content of the message to be sent by the user in response to detecting the text entered by the user in the input box. The terminal device 110 can also, for example, collect the user's audio in response to detecting the user's triggering operation on the audio space. The terminal device 110 can determine the audio or the text content corresponding to the audio as the content of the message to be sent by the user. It should be noted that the operations performed by the aforementioned terminal device 110 and the operations performed by the terminal device 110 described subsequently can specifically be performed by relevant applications installed on the terminal device 110.

[0060] In the conversation window, users can enter messages through the input box or through other appropriate means (e.g., voice), and the digital assistant can provide reply messages based on the input message and relevant knowledge. Messages in the conversation window are generally conversation messages. Such conversation messages can be considered part of a topic.

[0061] 2A to 2H illustrate schematic diagrams of an example client interface 200 of an interactive window according to some embodiments of the present disclosure. The client interface 200 may be implemented at the terminal device 110. The examples of FIG. 2A to FIG. 2H are described below with reference to FIG.

[0062] In a conversation window between a user and at least one other user, the terminal device 110 (for example, an instant messaging application installed on the terminal device 110, or a suite application integrated with an instant messaging application installed on the terminal device 110) can present a trigger control for a digital assistant (for example, a first digital assistant) in response to detecting a preset input in the input box of the conversation window. As shown in FIG2A , the launch entry of the instant messaging application is presented in area 230 of the interface 200, and the information stream (feed) of the instant messaging application is presented in area 220 of the interface 200. In response to the user selecting any contact or any group in the information stream of the instant messaging application, the terminal device 110 can present a corresponding conversation window in area 210 of the interface 200. For example, in response to the user invoking the digital assistant through a preset operation (for example, selecting a digital assistant from a contact list), the terminal device 110 can present a conversation window (also referred to as a main conversation window) for the user to interact with the digital assistant in area 210 of the interface 200.

[0063] In some embodiments, in response to the digital assistant being invoked, the terminal device 110 may, by default, open a new topic (e.g., the first topic) in the conversation window and present a dividing line corresponding to the first topic in the conversation window. As shown in FIG2A , in response to the digital assistant being invoked, the terminal device 110 may, by default, present a dividing line 211 corresponding to the new topic and a message card 212 associated with the new topic in the interface 200.

[0064] In this article, a "topic" corresponds to a specific context of interaction. During the interaction process of each topic, the interaction information between the user and the digital assistant will be regarded as contextual information to assist the digital assistant in determining subsequent conversation messages. In some embodiments, a topic is sometimes also referred to as or presented as a theme.

[0065] In some embodiments, if the user previously had historical interaction information or historical topics with the digital assistant, in response to the digital assistant being invoked, the terminal device 110 may present a portion of the historical interaction information or historical topics in the conversation window. As shown in FIG2B , the terminal device 110 may present a portion of the historical interaction information between the user and the digital assistant in the main conversation window of the interface 200. Alternatively or additionally, in some embodiments, in response to the digital assistant being invoked, the terminal device 110 may not present the message card 212 and the historical interaction information in the main conversation window.

[0066] In some embodiments, the terminal device 110 may open a new topic (e.g., the first topic) in the conversation window between the user and the digital assistant in response to receiving an operation to open a new topic. The conversation window may include an input box, and the terminal device 110 may receive user input through the input box, for example. If the terminal device 110 detects that the user input is a user input indicating the opening of a new topic, it is determined that the operation to open a new topic has been received. In some embodiments, the conversation window may also include an operation control for opening a new topic (e.g., the operation control 201 in Figure 2B). For example, the terminal device 110 may determine that the operation to open a new topic has been received in response to detecting a trigger operation on the operation control 201. The terminal device 110 may then present the main conversation window as shown in Figure 2A or Figure 2C.

[0067] As shown in Figures 2A and 2C , in response to the operation of opening a new topic, the terminal device 110 opens the first topic in the main conversation window, displays a dividing line 211 between the new topic and the previous topic in the interface 200, and presents at least one scene in the conversation area of ​​the first topic. The conversation area of ​​the first topic here can be, for example, a message card 212. For example, in response to opening a new topic, the terminal device 110 can clear the main conversation window and present the dividing line 211 at the top (as shown in Figure 2A ). In this case, the clearing effect is not reversed when the user enters and sends a conversation message for the new topic in the main conversation window. The user can scroll through the message list to view conversation messages in the previous topic. When viewing conversation messages in the previous topic, the ceiling effect of the dividing line 211 is removed. In some embodiments, when the historical topic dividing line appears in the main conversation window, it does not stay at the top. For example, in response to opening a new topic, the terminal device 110 can also present the dividing line 211 between the previous topic and the new topic (as shown in Figure 2C ).

[0068] The terminal device 110 may present at least one scenario (e.g., scenario 213 and scenario 214) in the message card 212. A scenario here refers to a collection of tasks of the same type, i.e., one scenario corresponds to multiple tasks of the same type. One or more scenarios may be configured with corresponding configuration information to perform tasks of the corresponding type. The scenario configuration information includes at least one of the following: scenario setting information and plug-in information. The scenario setting information is used to describe information related to the corresponding scenario. The plug-in information indicates at least one plug-in used to perform the task in the corresponding scenario. As discussed below, the scenario configuration information may also include, for example, an indication of the selected model (where the model is called to determine the response to the user in the corresponding scenario), scenario guidance information (the scenario guidance information is presented to the user after the corresponding scenario is selected), at least one recommended question for the digital assistant (the at least one recommended question is presented to the user for selection after the corresponding scenario is selected), and so on. In some embodiments, the scenario setting information and configuration information of the scene may be configured, for example, using natural language, so that the scenario creator can easily constrain the output of the model and configure a variety of scenarios.

[0069] The scenario setting information of a scene can affect the digital assistant's response to the user to a certain extent, or be used to determine the digital assistant's response to the user. In some embodiments, the scenario setting information is used to construct a prompt input to provide to the model used in the corresponding scenario. The digital assistant's response to the user is based on the output of the model. The scenario setting information of the scene may, for example, include a description of the corresponding type of task, the digital assistant's response style in the scenario, a definition of the workflow to be executed in the corresponding scenario, a definition of the digital assistant's response format in the corresponding scenario, and so on. In some embodiments, the digital assistant will use the model to understand the user input and provide a response to the user based on the model's output. The model used by the digital assistant can run locally on the terminal device 110 or on a remote server. By using the scenario setting information to construct a portion of the model's prompt input, the model can be guided to complete the task to be achieved in the corresponding scenario. In some embodiments, the model can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The model can also be based on other appropriate models.

[0070] The plug-in information of the scenario can be used to configure the plug-in to be used in the corresponding scenario. In some embodiments, in the corresponding scenario, during the operation of the plug-in, the plug-in can also call the model to complete the corresponding task. In some embodiments, a plug-in can also call the open interface provided by other applications (for example, documents, calendars, meetings, etc.) to complete the corresponding task, such as modifying documents, creating schedules, summarizing meetings, etc.

[0071] In some embodiments, the terminal device 110 may further present an operation control 215 in the message card 212. In response to detecting a trigger operation on the operation control 215, the terminal device 110 may present more scenarios. For example, to ensure the simplicity of the main conversation window, when multiple scenarios are included, the terminal device 110 may present only some of the scenarios in the operation card 212, and present more scenarios in response to detecting a trigger operation on the operation control 215. The message card 212 may further include a plug-in selection entry 216. The user may select at least one plug-in to be used in the new topic (i.e., the first topic) by clicking on the plug-in selection entry 216.

[0072] As shown in Figure 2D, in response to the user clicking on the plug-in selection entry 216 and selecting the calendar plug-in, the terminal device 110 determines the calendar plug-in as the plug-in to be used in the new topic and presents the plug-in identifier 211 corresponding to the calendar plug-in in the message card 212. The terminal device 110 may also, for example, present a message card 222 in the main conversation window based on the selected plug-in. The message card 222 may, for example, present at least one recommended question for the digital assistant in the new topic (e.g., question 223, question 224, and question 225) for the user to directly select or guide the user to enter the same or similar question. In response to detecting a selection operation on a recommended question, the terminal device 110 may present a corresponding conversation message from the user in the main conversation window. For example, in response to detecting a selection operation on question 225, the terminal device 110 may present a conversation message "Appointment Schedule" from the user in the main conversation window.

[0073] In some embodiments, the terminal device 110 receives a selection of a first scene in at least one scene in a message card 212, and performs interaction between the user and the digital assistant in a new topic based at least on the configuration information of the first scene. For example, the terminal device 110 may provide guidance information related to the first scene in the conversation window in response to receiving a selection of the first scene in at least one scene. Exemplarily, as shown in Figures 2A and 2E, if a trigger operation is received for the scene 213 in the message card 212 shown in Figure 2A, the terminal device 110 may determine that a selection of the scene 213 has been received, and present a message card 232 as shown in Figure 2E. The message card 232 is a card corresponding to the scene 213 (i.e., the content creation scene). Guidance information related to the selected scene 213 is presented in the message card 232.

[0074] In addition to selecting a scene via the message card 212 corresponding to the new topic, in some embodiments, the conversation window may also include an operation control for selecting a scene. For example, in response to detecting a triggering operation on the operation control for selecting a scene, the terminal device 110 may provide a set of scenes. This set of scenes may include at least one scene. In response to receiving a selection of the first scene in the set of scenes, the terminal device 110 may then open a first topic in the conversation window and, in the first topic, perform user interaction with the digital assistant based at least on the configuration information of the first scene. Similarly, in response to receiving a selection of the first scene in the set of scenes, the terminal device 110 may provide guidance information related to the first scene in the conversation window. As shown in Figures 2B, 2F, and 2G, the interface 200 shown in Figure 2B may also include an operation control 202 for selecting a scene. In response to receiving a triggering operation on the operation control 202, the terminal device 110 may present the interface 200 shown in Figure 2F. The interface 200 shown in Figure 2F includes a window 241. Window 241 may present a set of scenes (e.g., scene 242, scene 243, scene 244, scene 245, etc.). Window 241 may also present an operation control 246 for managing scenes and an operation control 247 for presenting more scenes. Furthermore, in response to receiving a trigger operation for a scene in the set of scenes (e.g., scene 242), terminal device 110 may determine that a selection of that scene has been received and present interface 200 as shown in FIG2G . Interface 200 shown in FIG2G presents a message card 232. Message card 232 may present guidance information related to the selected scene 242. It will be understood that since scene 242 and scene 213 are both content creation scenes, the message cards 232 in FIG2E and FIG2G are both cards for the corresponding content creation scenes. It should be noted that when a scene is selected using the operation control for selecting a scene, in response to the scene being selected, terminal device 110 may, by default, simultaneously determine to start a new topic and perform interactions for the selected scene within the new topic while simultaneously executing interactions for the selected scene.

[0075] The above reference Figures 2A to 2D describe the scene recommendation and scene selection in the conversation window between the user and the digital assistant. Although not shown in the accompanying drawings, scene recommendation and scene selection can also be provided in the floating window in the floating window mode of the digital assistant. In some embodiments, the floating window mode of the digital assistant may be invoked in a specific application, for example, when the user edits the target document through a document application. In this case, one or more scenes may also be provided for the user to select. In the floating window mode, the one or more scenes provided may be related to the context or specific application in which the floating window mode of the digital assistant is invoked, so finer-grained scenes can be defined for the context or application scenario, and each scene is configured to perform corresponding finer-grained tasks. For example, if the digital assistant is invoked in a document application, then for the document application, finer-grained scenes such as content continuation, content editing, and content understanding can be configured. In this way, in the corresponding application, the digital assistant can still achieve specific task requirements by selecting a specific scene.

[0076] When the user interacts with the digital assistant in the selected scene, the terminal device 110 may also present a dividing line with a first topic identifier in the conversation window. The first topic identifier is based at least on the interaction information between the user and the digital assistant in the selected scene. The first topic identifier may, for example, include a scene identifier (e.g., scene name) of the first scene. As shown in Figures 2E and 2G, in response to the content creation scene (scene 213 and / or scene 242) being selected, the terminal device 110 presents a message card 232 and a dividing line 231 corresponding to the content creation scene in the interface 200. The dividing line 232 presents the first topic identifier "Content Creation", where the first topic identifier is the scene name of the selected scene (i.e., the scene identifier). That is, in a certain topic, if the user does not select a specific scene, a general default topic identifier, such as "New Topic" or "Topic", may be presented in the associated area of ​​the dividing line. If the user selects a specific scene in the topic, the topic identifier will specifically present the scene identifier to identify the scene involved in the topic. The topic identifiers may be displayed on the topic dividing line (as shown in the figure), or may be displayed in an adjacent area of ​​the topic dividing line.

[0077] Regarding the guidance information associated with the first scenario, in some embodiments, this guidance information may include scenario guidance information for the first scenario, at least one recommended question for the digital assistant in the first scenario, at least one shortcut command for the digital assistant in the first scenario, an indication of the plug-ins used in the first scenario, and so on. The scenario guidance information may, for example, be a description of a task instance that can be performed in the scenario. The indication of the plug-in used in the first scenario may, for example, be an identifier of the plug-in presented in the form of text, a chart, or the like. It should be noted that in some embodiments, the plug-in used in the first scenario may be a pre-set plug-in. In this case, the indication is only used to indicate which plug-in can be used, and is not used to instruct the user to select the plug-in to be used in the scenario. As shown in Figures 2E and 2G, the message card 232 may present the scenario guidance information "Hello, in the [content creation] scenario, I can help you with product solutions, etc.", at least one recommended question (e.g., recommended question 233, recommended question 234, and recommended question 235), and an indication of the plug-in 236. The indication of the plug-in 236 may, for example, indicate that the plug-in selected in the content creation scenario is a document plug-in.

[0078] In addition to presenting guidance information by presenting a message card 232, in some embodiments, the terminal device 110 can also present guidance information directly in the conversation window. For example, the terminal device 110 can directly present at least one shortcut instruction (including shortcut instruction 237, shortcut instruction 238, shortcut instruction 239, etc.) in the interface 200. It should be noted that although recommended questions and shortcut instructions can both be used to indicate a certain character to be executed in the scene, the terminal device 110 will perform different interactions after the two are selected. After a recommended question from at least one recommended question is selected, the terminal device 110 will present the selected recommended question in the conversation window in the form of a conversation message from the user. The terminal device 110 and / or the digital assistant can analyze and reply to the conversation message. After a shortcut instruction from at least one shortcut instruction is selected, the terminal device 110 can directly execute the task instance indicated by the selected shortcut instruction.

[0079] In response to receiving a selection of at least one shortcut command, the terminal device 110 may execute a task instance corresponding to the shortcut command. In response to receiving a selection of at least one recommended question, the terminal device 110 may also present the recommended question in the form of a user conversation message in a conversation window. For example, the terminal device 110 may also receive a conversation message input by the user (e.g., a conversation message entered by the user via an input box). The terminal device 110 may provide the received conversation message (recommended question or user input) to the digital assistant and / or model and determine a reply message for the conversation message. If the recommended question indicates the execution of a task instance, the terminal device 110 may also execute the task instance and present the execution result as a reply message in the conversation window. In other words, the terminal device 110 may determine the task instance to be executed based on the interaction information in the scenario. As shown in Figure 2H, in response to receiving a conversation message 251 input by the user, the terminal device 110 may provide the conversation message 251 to the digital assistant and / or model and determine a reply message 252 for the conversation message 251. In the case where the conversation message indicates the execution of the first task instance, the reply message 252 can be the execution result obtained by the terminal device 110 / digital assistant / model after analyzing the conversation message 251, determining the first task instance indicated by it, and executing the first task instance.

[0080] In some embodiments, as the interaction in the selected scenario proceeds, the first topic identifier presented at the associated area of ​​the dividing line of the current topic may also include a task identifier of the first task instance performed in the first topic. In response to executing the first task instance in the scenario, the terminal device 110 may also present the task identifier of the executed first task instance in the dividing line. In the example shown in Figure 2H, the terminal device 110 can determine that the conversation message 251 indicates that the task instance of creating a camping activity copy is to be executed by analyzing the conversation message 251. The terminal device 110 then switches the first topic identifier presented in the dividing line 231 from "Content Creation" to "Content Creation: Creating Camping Activity Copy".

[0081] The above describes the interaction between the user and the digital assistant regarding topics, environments, and task instances performed in the conversation window. The following describes the creation of the scene in conjunction with Figures 3A to 3I.

[0082] 3A to 3I show schematic diagrams of an example client interface 300 for creating a scene according to some embodiments of the present disclosure. The client interface 300 may be implemented at the terminal device 110. The examples of FIG. 3A to FIG. 3I are described below with reference to FIG. 1 .

[0083] In some embodiments, the terminal device 110 may, in response to receiving a scene creation operation, provide a first page for creating a target scene. The terminal device 110 may, via the first page, obtain scene creation information for the target scene, the scene creation information including at least target configuration information for the target scene. The terminal device 110 may then, in response to receiving a creation confirmation operation, create the target scene based on the obtained target configuration information.

[0084] In some embodiments, the terminal device 110 may, for example, determine that a scene viewing operation has been received in response to receiving a trigger operation on a related operation control in the interface 200. Exemplarily, referring back to FIG2D , the terminal device 110 may, for example, determine that a scene viewing operation has been received in response to receiving a trigger operation on the operation control 215. Referring back to FIG2F , the terminal device 110 may, for example, determine that a scene viewing operation has been received in response to receiving a trigger operation on the operation control 246 / operation control 247. It will be understood that the terminal device 110 may determine that a scene viewing operation has been received in response to receiving a trigger operation on any appropriate operation control, and the present disclosure does not limit specific operation controls. Alternatively or additionally, in some embodiments, the terminal device 110 may also determine that a scene viewing operation has been received in response to receiving user input indicating viewing a scene in the session window.

[0085] In response to receiving a scene viewing operation, the terminal device 110 may, for example, provide an interface 300 as shown in FIG3A , FIG3B , or FIG3C . The interface 300 includes a page 310 for presenting the user's existing scenes. In some embodiments, the interface 300 provided by the terminal device 110 may also include only page 310. Page 310 includes multiple scenes of the user and an operation control 301 for creating a scene. In some embodiments, page 310 may be referred to as a page for presenting a scene library. The scene library may, for example, include all scenes that the user can select for interacting with the digital assistant.

[0086] If all scenes owned by the user can be displayed on page 310, the terminal device 110 may, for example, present the interface 300 shown in FIG3A or FIG3C , with the operation control 301 displayed at the bottom of all scenes. If all scenes owned by the user cannot be displayed on page 310, the terminal device 110 may, for example, present the interface 300 shown in FIG3B , with the operation control 301 fixedly displayed at the bottom of page 310. In the interface 300 shown in FIG3B , the terminal device 110 may present more scenes in response to receiving an upward swipe operation / a downward swipe operation.

[0087] In some embodiments, the page 310 used to present the user's existing scenes may also present the scene's status. The scene's status may include, for example, an enabled state and a disabled state. As shown in FIG3C , the terminal device 110 may, for example, present scenes in different states in different display styles. For example, if the scene "Write a face review" is in the disabled state, the terminal device 110 may present this scene in a different color than other scenes on page 310. The terminal device 110 may also present a status identifier for the corresponding scene state in association with the scene. For example, the terminal device 110 may present a status identifier for the disabled state (e.g., the text "Disabled") in association with the scene "Write a face review." In some embodiments, in response to receiving a triggering operation (e.g., a click operation, a long press operation, a hover operation, etc.) on the status identifier, the terminal device 110 may also present descriptive information describing the corresponding state. For example, in response to receiving a triggering operation on the status identifier "Disabled," the terminal device 110 may present descriptive information 311 describing the disabled state.

[0088] The terminal device 110 may determine that a scene creation operation has been received in response to detecting a trigger operation on the operation control 301 in the interface 300 shown in Figures 3A to 3C. Alternatively or additionally, in some embodiments, the terminal device 110 may also determine that a scene creation operation has been received in response to receiving user input instructing to create a scene in the conversation window. In response to receiving the scene creation operation, the terminal device 110 may present a first page for creating a target scene. Such a first page may, for example, be shown in the interface 300 shown in Figure 3D, where the interface 300 shown in Figure 3D includes a page 320 for creating a target scene. Similarly, in some embodiments, the first page presented by the terminal device 110 may only include page 320.

[0089] The terminal device 110 may obtain scene creation information for the target scene via page 320. In some embodiments, the scene creation information may include identification information for the target scene. The identification information for the target scene may include, for example, the name and icon of the target scene. As shown in Figures 3D and 3E, page 320 may include an operation control 321 and an area 322 for receiving the scene identification information. In response to receiving a trigger operation on operation control 321 in interface 300 shown in Figure 3D, the terminal device 110 may present interface 300 as shown in Figure 3E. As shown in Figure 3E, page 320 of interface 300 includes window 330. Window 330 presents the options "Icon" and "Upload Image." If the option "Icon" is selected, the terminal device 110 may present an area 331 for setting the color of the icon for the target scene and an area 332 for setting the icon for the target scene in the window. For example, multiple colors can be provided in area 331, and multiple icons can be provided in area 332. The terminal device 110 can determine the icon color and icon style of the target scene based on the user's selections in areas 331 and 332. When "Upload Image" is selected, the terminal device 110 can, for example, receive an image uploaded by the user and determine the image as the icon of the target scene. Returning to reference Figure 3D, the terminal device 110 can determine the name of the target scene based on the user input received in area 322.

[0090] The scene creation information may also include target configuration information for the target scene, and the target configuration information may include at least one of the following: scene setting information and plug-in information. The scene setting information is used to describe information related to the target scene. In some embodiments, the scene setting information may also include a description of the target type of task corresponding to the target scene, the response style of the digital assistant in the target scene, the definition of the workflow to be executed in the target scene, the definition of the response format of the digital assistant in the target scene, and so on. As shown in Figures 3D and 3F, page 320 may also include an input area 323 (also known as a first input area) for receiving scene setting information. The input area 323 may present first guidance information for inputting the scene setting information. The first guidance information may be used to prompt the user that the scene setting information may include a description of the target type of task corresponding to the target scene, the response style of the digital assistant in the target scene, the definition of the workflow to be executed in the target scene, the definition of the response format of the digital assistant in the target scene, and so on. In some embodiments, in response to receiving a trigger operation on the input area 323, the terminal device 110 may present an interface 300 as shown in Figure 3F. In page 320 of interface 300 shown in FIG3F , terminal device 110 may highlight (e.g., by adding a bold border, highlighting, or any other appropriate means) the triggered input area 323 and may also present a prompt message "Scene setting is required" in association with input area 323. In some embodiments, the first guidance message in input area 323 may be canceled in response to receiving user input in input area 323.

[0091] In some embodiments, the scene setting information is used to construct a prompt word input to be provided to the model used in the target scenario. The target configuration information may also include an indication of the selected model. This selected model is called to determine the response to the user in the target scenario. As shown in Figures 3D, 3G and 3H, page 320 may also include an entry 324 for selecting a model. The model identifier of the model selected by default (for example, the model name of the model A selected by default) may be presented in the entry 324. In the interface 300 shown in Figure 3D, in response to receiving a trigger operation on the entry 324, the terminal device 110 may present the interface 300 shown in Figure 3G. In the interface 300 shown in Figure 3G, the terminal device 110 may present a card 340, in which at least one model that can be selected is presented. In response to receiving a selection operation for a certain model in the card 340, the terminal device 110 may present the model identifier (for example, the model name) of the selected model in the entry 324. For example, in response to receiving a selection operation on the model “Custom Model A” in card 340 , terminal device 110 may present interface 300 shown in FIG3H . In interface 300 shown in FIG3H , the model name of Custom Model A is presented in entry 324 .

[0092] In some embodiments, the target configuration information may also include scenario guidance information and at least one recommended question for the digital assistant. After the target scenario is selected, the terminal device 110 may present the scenario guidance information to the user. After the target scenario is selected, the terminal device 110 may present at least one recommended question to the user for selection. As shown in Figures 3D and 3I , in some embodiments, in interface 300 shown in Figure 3D , the terminal device 110 may present interface 300 shown in Figure 3I in response to receiving a downward swipe operation on page 320. Interface 300 includes an input area 325 (also known as a second input area) for receiving scenario guidance information. Second guidance information regarding the input of the scenario guidance information may be presented in input area 325. In some embodiments, the second guidance information in input area 325 may be removed from presentation in response to receiving user input in input area 325. Page 320 may also present at least one recommended question. This at least one recommended question may be user-entered, i.e., a user-defined question, a question generated by the terminal device 110 based on the scenario setting information, a default question common to all scenarios, and so on. The terminal device 110 may present a delete control 327 associated with each question (for example, if three questions are included, delete controls 327-1, 327-2, and 327-3 may be presented in association with the three questions, respectively). In response to receiving a selection operation on a delete control 327, the terminal device 110 may determine that a delete operation has been received for the corresponding question. The page 320 may also include an operation control 328. In response to receiving a trigger operation on the operation control 328, the terminal device 110 determines that a create operation has been received to create a new question.

[0093] In some embodiments, page 320 may further include an information generation control. In response to detecting a trigger operation on the information generation control in the first page, the terminal device 110 may generate candidate scene guidance information and / or at least one candidate recommendation question based at least on the received scene setting information. The terminal device 110 may present the candidate scene guidance information in a second input area in the first page for receiving scene guidance information, and / or present at least one candidate recommendation question in a third input area in the first page for receiving recommendation questions. Exemplarily, as shown in FIG3I , the terminal device 110 may also present an information generation control (e.g., a control “Generate according to scene setting”) in association with the input area 325. In some embodiments, in response to receiving a first preset operation (e.g., a click operation, a hover operation, etc.) on the control “Generate according to scene setting”, the terminal device 110 may present prompt information 326 for prompting the function of the control “Generate according to scene setting”. In some embodiments, in response to receiving a second preset operation (such as a click operation, a double-click operation, a long press operation, etc.) for the control "Generate according to scene settings", the terminal device 110 can execute the operation indicated by the control "Generate according to scene settings" (that is, automatically generate scene guidance information and / or at least one candidate recommendation question based on the scene setting information).

[0094] In the interface 300 shown in Figures 3D to 3I, page 320 may also include, for example, a create control 303 and a cancel control 302. The terminal device 110 may respond to and receive a trigger operation for the create control 303, determine that a create confirmation operation has been received, and create a target scene based on the target configuration information obtained in page 320. The created target scene may, for example, be included in a scene library associated with the user. For example, the created target scene may be presented in page 310 shown in Figures 3A to 3C. In some embodiments, in the user's scene library, at least the target scene is marked as a user-defined scene type. That is, the terminal device 110 may identify the target scene created by the user as a user-defined scene type. For example, the terminal device 110 may present identification information (e.g., the text "custom") in association with the target scene to indicate that the target scene is a user-defined scene. It will be understood that if a selection of a created target scene is received, the terminal device 110 may perform interaction between the first user and the first digital assistant in the conversation window based at least on the configuration information of the target scene. The terminal device 110 may cancel the creation of the target scene in response to receiving the trigger operation of the cancel control 302. The terminal device 110 may clear the target configuration information received in the page 320 or save the target configuration information received in the page 320 to the draft box.

[0095] Some example embodiments of creating a scene are described above. Some example embodiments of editing a created scene are described below with reference to FIG. 4A to FIG. 4I .

[0096] 4A to 4I illustrate schematic diagrams of an example client interface 400 for editing a created scene according to some embodiments of the present disclosure. The client interface 400 may be implemented at the terminal device 110. The examples of FIG. 4A to FIG. 4I are described below with reference to FIG.

[0097] In some embodiments, users can also edit a created target scene. For example, they can delete or deactivate a created target scene. In response to the creation of a target scene, the terminal device 110 can set the target scene to be in an enabled state. It is understood that the user who created the target scene has editing permissions, sharing permissions, deactivation permissions, activation permissions, removal permissions for removing the target scene from the scene library, and so on. The user who created the target scene can share the target scene with other users and can also set permissions for other users. For example, other users with whom the target scene is shared can be set to have sharing permissions for the target scene, removal permissions for removing the target scene from the first scene library, and so on. Users with removal permissions (for example, including the target user who created the target scene and other users with permissions) can remove the target scene from the scene library to delete the target scene. Users with deactivation permissions (for example, the user who created the target scene) can deactivate the target scene to deactivate the target scene. In response to detecting that the target scene has been deleted or deactivated, the terminal device 110 can set the target scene to be in a deactivated state.

[0098] Regarding the specific method of deactivating or removing the target scene, as shown in Figure 4A, in response to receiving a preset operation on a scene in window 241 (for example, the scene "Write Face Review"), the terminal device 110 can present an operation control 401. In some embodiments, the terminal device 110 can also present the operation control 401 by default. In response to receiving a trigger operation on the operation control 401, the terminal device 110 can present a window 402. Window 402 presents at least one operation control for editing the scene (for example, the operation control "Edit Scene", the operation control "Share Scene", the operation control "Remove Scene", etc.). As shown in Figure 4B, in response to receiving a trigger operation on a scene in page 310 (for example, the scene "Content Understanding"), the terminal device 110 can present a window 403. Window 403 can present at least one operation control for editing the scene. In some embodiments, as shown in Figure 4C, when a scene has been deactivated, in response to receiving a trigger operation on the deactivated scene, the terminal device 110 can present an operation control 404. The terminal device 110 may present a window 405 in response to receiving a triggering operation on the operation control 404. Window 405 includes at least one operation control, which is a control corresponding to an operation that can be performed on a deactivated scene. In some embodiments, in response to a scene being deactivated, the terminal device 110 may present information indicating that the scene is deactivated (e.g., the text "deactivated") in association with the scene. The terminal device 110 may present a prompt message 406 indicating that the scene has been deactivated in response to receiving a triggering operation on the information.

[0099] In some embodiments, in response to receiving a triggering operation on an operation control for removing a scene from the scene library (e.g., the operation control "Remove Scene" in window 402, window 403, or window 405), the terminal device 110 may present an interface 400 as shown in FIG4D . In the interface 400 shown in FIG4D , the terminal device 110 may present a window 410. Window 410 may include a prompt prompting the user to confirm whether to remove the scene, a control for confirming the removal operation (e.g., the control "OK"), and a control for canceling the removal operation (e.g., the control "Cancel").

[0100] In some embodiments, in response to receiving a trigger operation on an operation control for deactivating a scene, the terminal device 110 may present an interface 400 as shown in FIG4E . In the interface 400 shown in FIG4E , the terminal device 110 may present a window 4E0 . Window 410 may include a prompt prompting the user to confirm whether to deactivate the scene, a control for confirming deactivation of the scene (e.g., a “OK” control), and a control for canceling deactivation of the scene (e.g., a “Cancel” control).

[0101] In some embodiments, for a user who creates a target scene, the terminal device 110 may present an interface 400 as shown in FIG4F in response to receiving a triggering operation on an operation control for removing a scene from the scene library (e.g., the operation control “Remove Scene” in window 402, window 403, or window 405). In the interface 400 shown in FIG4F, the terminal device 110 may present a window 430. Window 410 presents a prompt message prompting the user to confirm whether to remove the scene, a control for confirming the execution of the removal operation (e.g., the control “Remove Only”), a control for removing the scene and deactivating the scene (e.g., the control “Remove and Deactivate”), and a control for canceling the removal operation (e.g., the control “Cancel”).

[0102] In some embodiments, in response to receiving a trigger operation for an operation control for editing a created target scene (e.g., the operation control "Edit Scene" in window 402 or window 403), the terminal device 110 may determine that an edit request for the created target scene has been received. In response to receiving an edit request for a created target scene, the terminal device 110 may provide a page for editing the target scene, in which the scene creation information of the target scene can be edited. In some embodiments, for a user with editing authority (e.g., a user who created the target scene), the terminal device 110 may present an interface 400 as shown in FIG. 4G. For a user who does not have editing authority, the terminal device 110 may present an interface 400 as shown in FIG. 4H. In the interface 400 shown in FIG. 4H, the terminal device 110 may present a prompt message 407 to prompt the user that the target scene cannot be edited. Alternatively or additionally, in some embodiments, the terminal device 110 may not present a page for editing the target scene to a user who does not have editing authority.

[0103] In some embodiments, a user having a target scene and having sharing authority over the target scene can share the target scene with other users. If the user sharing the target scene is a first user, the first scene library of the first user includes the target scene, and the terminal device 110 can, for example, determine that a sharing request to share the created target scene to the second user is received in response to receiving a triggering operation of an operation control for the target scene to be shared (e.g., the operation control "Share Scene" in window 402 or window 403). The terminal device 110 can send a sharing link of the target scene to the second user in response to receiving a sharing request to share the created target scene to the second user. Via the sharing link, the target scene can be added to a second scene library associated with the second user, and the second scene library includes scenes that the second user can select for interacting with the second digital assistant. For the second user being shared, the terminal device corresponding to the second user can present an interface 400 as shown in Figure 4I for it. Window 440 is presented in the interface 400 shown in Figure 4I. Window 440 presents prompt information for prompting the user whether to add the shared scene, an operation control for adding the shared scene to the second scene library (such as the control "Add"), and an operation control for canceling the addition of the shared scene to the second scene library (such as the control "Cancel").

[0104] In summary, according to various embodiments of the present disclosure, during the interaction between a user and a digital assistant, the user is supported to switch between different scenarios during the interaction, so that the user can interact with the digital assistant in the selected scenario. In this way, it is possible to flexibly select environments and task instances based on user needs, thereby realizing diverse interactive operations with the digital assistant.

[0105] It should be understood that some embodiments of the present disclosure are described above with reference to the specific examples in the accompanying drawings, but these specific examples do not limit the scope of the embodiments of the present disclosure. The described embodiments can also be implemented in various other variations.

[0106] FIG5 shows a flow chart of a process 500 of information interaction according to some embodiments of the present disclosure. The process 500 may be implemented at the terminal device 110. The process 500 is described below with reference to FIG1.

[0107] At block 510, terminal device 110 provides at least one scenario in the user-digital assistant interaction window. A first scenario in the at least one scenario is configured with corresponding configuration information for performing a corresponding type of task. The configuration information includes at least one of the following: scenario setting information and plug-in information. The scenario setting information describes information related to the corresponding scenario, and the plug-in information indicates at least one plug-in used to perform the task in the corresponding scenario.

[0108] In box 520, in response to receiving a selection of a first scene among the at least one scene, the terminal device 110 performs user interaction with the digital assistant based on at least the configuration information of the first scene.

[0109] In some embodiments, providing at least one scenario includes: in response to an operation of opening a new topic in the interaction window, opening a first topic in the interaction window, and presenting at least one scenario in the interaction area of ​​the first topic; executing interaction between the user and the digital assistant includes: in response to receiving a selection of a first scene in at least one scenario, executing interaction between the user and the digital assistant in the first topic based at least on configuration information of the first scene.

[0110] In some embodiments, a plug-in selection portal is further presented in the interactive area of ​​the first topic, through which at least one plug-in used in the first topic can be selected.

[0111] In some embodiments, providing at least one scenario includes: providing a set of scenarios in response to receiving a trigger operation of a scenario entry control in an interaction window; and executing user interaction with the digital assistant includes: opening a first topic in the interaction window in response to receiving a selection of a first scene in a set of scenarios; and executing user interaction with the digital assistant in the first topic based at least on configuration information of the first scene.

[0112] In some embodiments, process 500 further includes: in response to receiving a selection of the first scene, presenting a first topic identifier at an associated area of ​​a dividing line between the first topic and a previous topic, the first topic identifier including at least identification information of the first scene.

[0113] In some embodiments, the first topic identifier also includes identification information of a first task instance performed in the first topic, and the identification information of the first task instance is determined based at least on interaction information between the user and the digital assistant in the first topic.

[0114] In some embodiments, process 500 also includes: in response to receiving a selection of a first scene in a group of scenes, providing guidance information related to the first scene in the interactive window, the guidance information including at least one of the following: scene guidance information of the first scene, at least one recommendation question for the digital assistant in the first scene, at least one shortcut instruction for the digital assistant in the first scene, or an indication of a plug-in used in the first scene.

[0115] In some embodiments, the configuration information also includes at least one of the following: an indication of the selected model, which is called to determine the response to the user in the corresponding scenario; scenario guidance information, which is presented to the user after the corresponding scenario is selected; or at least one recommended question for the digital assistant, which is presented to the user for selection after the corresponding scenario is selected.

[0116] In some embodiments, the scenario setting information is used to construct a prompt word input to provide to a model used in the corresponding scenario, and the response to the user is based on the output of the model.

[0117] In some embodiments, the scenario setting information includes at least one of the following: a description of the corresponding type of task, the response style of the digital assistant in the scenario, a definition of the workflow to be executed in the corresponding scenario, or a definition of the response format of the digital assistant in the corresponding scenario.

[0118] In some embodiments, the interaction window includes one or more of the following: a conversation window, a floating window.

[0119] In some embodiments, process 500 also includes: in response to receiving a scene creation operation, providing a first page for creating a target scene; obtaining scene creation information of the target scene via the first page, the scene creation information including at least target configuration information of the target scene; and in response to receiving a creation confirmation operation, creating the target scene based on the obtained target configuration information.

[0120] FIG6 shows a flow chart of a process 600 of information interaction according to some embodiments of the present disclosure. The process 600 may be implemented at the terminal device 110. The process 600 is described below with reference to FIG1.

[0121] In box 610, the terminal device 110 opens a first topic in the interaction window between the user and the digital assistant in response to the operation of opening a new topic.

[0122] In block 620 , the terminal device 110 presents a dividing line between the first topic and the previous topic in the interaction window.

[0123] In box 630, in response to the user interacting with the digital assistant in the first topic, the terminal device 110 presents a first topic identifier at the associated area of ​​the dividing line, and the first topic identifier is based at least on the interaction information between the user and the digital assistant in the first topic.

[0124] In some embodiments, process 600 also includes: in response to detecting a selection of the first scene in the interaction of the first topic, or in response to detecting that the first scene is selected to trigger the opening of the first topic, presenting the first topic identifier at the associated area of ​​the dividing line, wherein the first scene is configured with corresponding configuration information to guide the digital assistant to perform the first type of task.

[0125] In some embodiments, the first topic identifier includes a scene identifier of a first scene, and wherein the scene identifier of the first scene is presented at the dividing line in response to the first scene being selected.

[0126] In some embodiments, the first topic identifier includes a task identifier of a first task instance performed in the first topic, and the first task instance is determined based at least on interaction information in the first topic.

[0127] FIG7 shows a flow chart of a process 700 for scene creation according to some embodiments of the present disclosure. The process 700 may be implemented at the terminal device 110. The process 700 is described below with reference to FIG1.

[0128] In block 710 , in response to receiving a scene creation operation, the terminal device 110 provides a first page for creating a target scene.

[0129] In box 720, the terminal device 110 obtains scene creation information of the target scene via the first page, and the scene creation information includes at least target configuration information of the target scene. The target configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in used to perform the task in the target scene.

[0130] In block 730 , in response to receiving the creation confirmation operation, the terminal device 110 creates a target scene based on the acquired target configuration information.

[0131] In some embodiments, the created target scene is included in a first scene library associated with the first user, the first scene library including scenes that the first user can select for interacting with the first digital assistant.

[0132] In some embodiments, in response to receiving a scene creation operation, providing a first page for creating a target scene includes: providing a scene creation entrance in an interaction window between the first user and the first digital assistant; detecting a scene creation operation based on triggering the scene creation entrance; and in response to receiving the scene creation operation, providing a first page for creating a target scene.

[0133] In some embodiments, the target configuration information also includes at least one of the following: an indication of the selected model, which is called to determine the response to the user in the target scenario; scene guidance information, which is presented to the user after the target scene is selected; or at least one recommended question for the digital assistant, which is presented to the user for selection after the target scene is selected.

[0134] In some embodiments, the scenario setting information includes at least one of the following: a description of a target type of task corresponding to the target scenario, the response style of the digital assistant in the target scenario, a definition of the workflow to be executed in the target scenario, or a definition of the response format of the digital assistant in the target scenario.

[0135] In some embodiments, context-setting information is used to construct prompt word inputs to provide to the model for use in the target context.

[0136] In some embodiments, the first page for creating a target scene includes at least one of the following: a first input area for receiving scene setting information, wherein first guidance information about the input of the scene setting information is presented, or a second input area for receiving scene guidance information, wherein second guidance information about the input of the scene guidance information is presented, wherein the first guidance information is canceled in response to receiving input in the first input area, and / or the second guidance information is canceled in response to receiving input in the second input area.

[0137] In some embodiments, process 700 also includes: in response to detecting a trigger operation on the information generation control in the first page, generating candidate scene guidance information and / or at least one candidate recommendation question based at least on the received scene setting information; and presenting the candidate scene guidance information in a second input area in the first page for receiving scene guidance information, and / or presenting at least one candidate recommendation question in a third input area in the first page for receiving recommendation questions.

[0138] In some embodiments, the scene creation information also includes identification information of the target scene.

[0139] In some embodiments, in the first scene library, at least the target scene is marked as a type of user-defined scene.

[0140] In some embodiments, process 700 further includes, in response to receiving a selection of a created target scene, performing interaction between the first user and the first digital assistant based at least on configuration information of the target scene.

[0141] In some embodiments, process 700 further includes: in response to the target scene being created, setting the target scene to be in an enabled state; and in response to detecting that the target scene is deleted or the target scene is disabled, setting the target scene to be in a disabled state.

[0142] In some embodiments, the first user who creates the target scene has at least one of the following permissions on the target scene: editing permission, sharing permission, deactivation permission, activation permission, or removal permission for moving the target scene out of the first scene library; and / or other users other than the first user have at least one of the following permissions on the target scene: sharing permission, or removal permission for moving the target scene out of the first scene library.

[0143] In some embodiments, the process 700 further includes: in response to receiving an edit request for the created target scene, providing a second page for editing the target scene, where the scene creation information of the target scene can be edited.

[0144] In some embodiments, process 700 also includes: in response to receiving a sharing request to share the created target scene to a second user, sending a sharing link of the target scene to the second user, wherein the target scene can be added to a second scene library associated with the second user via the sharing link, and the second scene library includes scenes that the second user can select for interacting with the second digital assistant.

[0145] It should be understood that the processes 500 , 600 , and 700 described above may be implemented together or separately on a user's terminal device 110 .

[0146] 8 shows a block diagram of an apparatus 800 for information interaction according to some embodiments of the present disclosure. The apparatus 800 may be implemented in or included in the terminal device 110. Each module / component in the apparatus 800 may be implemented by hardware, software, firmware, or any combination thereof.

[0147] As shown in the figure, the device 800 includes a scene providing module 810, which is configured to provide at least one scene in the interaction window between the user and the digital assistant. The first scene in the at least one scene is configured with corresponding configuration information to perform a corresponding type of task. The configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the corresponding scene, and the plug-in information indicates at least one plug-in used to perform the task in the corresponding scene. The device 800 also includes an interaction execution module, which is configured to execute the interaction between the user and the digital assistant in response to receiving a selection of the first scene in the at least one scene, at least based on the configuration information of the first scene.

[0148] In some embodiments, the scene providing module 810 is further configured to: in response to an operation of opening a new topic in the interaction window, open a first topic in the interaction window, and present at least one scene in the interaction area of ​​the first topic; executing the interaction between the user and the digital assistant includes: in response to receiving a selection of a first scene in at least one scene, executing the interaction between the user and the digital assistant in the first topic at least based on the configuration information of the first scene.

[0149] In some embodiments, a plug-in selection portal is further presented in the interactive area of ​​the first topic, through which at least one plug-in used in the first topic can be selected.

[0150] In some embodiments, the scene providing module 810 is further configured to: provide a set of scenes in response to receiving a trigger operation of a scene entry control in the interaction window; and execute the interaction between the user and the digital assistant including: opening a first topic in the interaction window in response to receiving a selection of a first scene in a set of scenes; and in the first topic, execute the interaction between the user and the digital assistant based at least on the configuration information of the first scene.

[0151] In some embodiments, the device 800 also includes: a topic identifier presentation module, configured to present a first topic identifier at an associated area of ​​a dividing line between the first topic and the previous topic in response to receiving a selection of the first scene, the first topic identifier including at least identification information of the first scene.

[0152] In some embodiments, the first topic identifier also includes identification information of a first task instance performed in the first topic, and the identification information of the first task instance is determined based at least on interaction information between the user and the digital assistant in the first topic.

[0153] In some embodiments, the device 800 also includes: a guidance information providing module, configured to provide guidance information related to the first scene in the interactive window in response to receiving a selection of the first scene in a group of scenes, the guidance information including at least one of the following: scene guidance information of the first scene, at least one recommendation question for the digital assistant in the first scene, at least one shortcut instruction for the digital assistant in the first scene, or an indication of the plug-in used in the first scene.

[0154] In some embodiments, the configuration information also includes at least one of the following: an indication of the selected model, which is called to determine the response to the user in the corresponding scenario; scenario guidance information, which is presented to the user after the corresponding scenario is selected; or at least one recommended question for the digital assistant, which is presented to the user for selection after the corresponding scenario is selected.

[0155] In some embodiments, the scenario setting information is used to construct a prompt word input to provide to a model used in the corresponding scenario, and the response to the user is based on the output of the model.

[0156] In some embodiments, the scenario setting information includes at least one of the following: a description of the corresponding type of task, the response style of the digital assistant in the scenario, a definition of the workflow to be executed in the corresponding scenario, or a definition of the response format of the digital assistant in the corresponding scenario.

[0157] In some embodiments, the interaction window includes one or more of the following: a conversation window, a floating window.

[0158] In some embodiments, the device 800 also includes: a creation module, configured to provide a first page for creating a target scene in response to receiving a scene creation operation; obtain scene creation information of the target scene via the first page, the scene creation information including at least target configuration information of the target scene; and create the target scene based on the obtained target configuration information in response to receiving a creation confirmation operation.

[0159] 9 shows a block diagram of an apparatus 900 for information interaction according to some embodiments of the present disclosure. The apparatus 900 may be implemented in or included in the terminal device 110. Each module / component in the apparatus 900 may be implemented by hardware, software, firmware, or any combination thereof.

[0160] As shown, the device 900 includes a topic start module 910, which is configured to start a first topic in the interaction window between the user and the digital assistant in response to an operation to start a new topic. The device 900 also includes a dividing line presentation module 920, which is configured to present a dividing line between the first topic and the previous topic in the interaction window. The device 900 also includes an identifier presentation module 930, which is configured to present a first topic identifier at an associated area of ​​the dividing line in response to the user interacting with the digital assistant in the first topic, the first topic identifier being based at least on the interaction information between the user and the digital assistant in the first topic.

[0161] In some embodiments, the device 900 also includes: a first topic identifier presentation module, configured to present the first topic identifier at the associated area of ​​the dividing line in response to detecting a selection of the first scene in the interaction of the first topic, or in response to detecting that the first scene is selected to trigger the opening of the first topic, wherein the first scene is configured with corresponding configuration information to guide the digital assistant to perform the first type of task.

[0162] In some embodiments, the first topic identifier includes a scene identifier of a first scene, and wherein the scene identifier of the first scene is presented at the dividing line in response to the first scene being selected.

[0163] In some embodiments, the first topic identifier includes a task identifier of a first task instance performed in the first topic, and the first task instance is determined based at least on interaction information in the first topic.

[0164] 10 shows a block diagram of an apparatus 1000 for scene creation according to some embodiments of the present disclosure. The apparatus 1000 may be implemented in or included in a terminal device 110. Each module / component in the apparatus 1000 may be implemented by hardware, software, firmware, or any combination thereof.

[0165] As shown in the figure, the device 1000 includes a page providing module 1010, which is configured to provide a first page for creating a target scene in response to receiving a scene creation operation. The device 1000 also includes an information acquisition module 1020, which is configured to acquire scene creation information of the target scene via the first page, wherein the scene creation information at least includes target configuration information of the target scene, and the target configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in for performing a task in the target scene. The device 1000 also includes a scene creation module 1030, which is configured to create the target scene based on the acquired target configuration information in response to receiving a creation confirmation operation.

[0166] In some embodiments, the created target scene is included in a first scene library associated with a first user who initiates the scene creation operation, and the first scene library includes scenes that the first user can select for interacting with the first digital assistant.

[0167] In some embodiments, the page providing module 1010 includes: an entry providing module, configured to provide a scene creation entry in the interaction window between the first user and the first digital assistant; an operation triggering module, configured to detect a scene creation operation based on triggering the scene creation entry; and a trigger-based page providing module, configured to provide a first page for creating a target scene in response to receiving a scene creation operation.

[0168] In some embodiments, the target configuration information also includes at least one of the following: an indication of the selected model, which is called to determine the response to the user in the target scenario; scene guidance information, which is presented to the user after the target scene is selected; or at least one recommended question for the digital assistant, which is presented to the user for selection after the target scene is selected.

[0169] In some embodiments, the scenario setting information includes at least one of the following: a description of a target type of task corresponding to the target scenario, the response style of the digital assistant in the target scenario, a definition of the workflow to be executed in the target scenario, or a definition of the response format of the digital assistant in the target scenario.

[0170] In some embodiments, context-setting information is used to construct prompt word inputs to provide to the model for use in the target context.

[0171] In some embodiments, the first page for creating a target scene includes at least one of the following: a first input area for receiving scene setting information, wherein first guidance information about the input of the scene setting information is presented, or a second input area for receiving scene guidance information, wherein second guidance information about the input of the scene guidance information is presented, wherein the first guidance information is canceled in response to receiving input in the first input area, and / or the second guidance information is canceled in response to receiving input in the second input area.

[0172] In some embodiments, the device 1000 also includes: a generation module, configured to generate candidate scene guidance information and / or at least one candidate recommendation question based at least on the received scene setting information in response to detecting a trigger operation on the information generation control in the first page; and present the candidate scene guidance information in a second input area in the first page for receiving the scene guidance information, and / or present at least one candidate recommendation question in a third input area in the first page for receiving the recommendation question.

[0173] In some embodiments, the scene creation information also includes identification information of the target scene.

[0174] In some embodiments, in the first scene library, at least the target scene is marked as a type of user-defined scene.

[0175] In some embodiments, the device 1000 also includes: a first interaction execution module, configured to, in response to receiving a selection of a created target scene, execute the interaction between the first user and the first digital assistant in the interaction window based at least on the configuration information of the target scene.

[0176] In some embodiments, the device 1000 further includes: a state adjustment module configured to set the target scene to an enabled state in response to the target scene being created; and to set the target scene to a disabled state in response to detecting that the target scene is deleted or the target scene is disabled.

[0177] In some embodiments, the first user who creates the target scene has at least one of the following permissions on the target scene: editing permission, sharing permission, deactivation permission, activation permission, or removal permission for moving the target scene out of the first scene library; and / or other users other than the first user have at least one of the following permissions on the target scene: sharing permission, or removal permission for moving the target scene out of the first scene library.

[0178] In some embodiments, the device 1000 further includes: a second page providing module configured to provide a second page for editing the target scene in response to receiving an editing request for the created target scene, wherein the scene creation information of the target scene can be edited in the second page.

[0179] In some embodiments, the device 1000 also includes: a sharing module, configured to send a sharing link of the target scene to the second user in response to receiving a sharing request to share the created target scene to the second user, wherein the target scene can be added to a second scene library associated with the second user via the sharing link, and the second scene library includes scenes that the second user can select for interacting with the second digital assistant.

[0180] It should be understood that one or more steps in the above method can be performed by an appropriate electronic device or combination of electronic devices. Such electronic device or combination of electronic devices may include, for example, the server 130, the terminal device 110, and / or the combination of the server 130 and the terminal device 110 in FIG. 1 .

[0181] Figure 11 shows a block diagram of an electronic device 1100 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 1100 shown in Figure 11 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 1100 shown in Figure 11 can be used to implement the terminal device 110 of Figure 1 , and the apparatus 800, apparatus 900, and / or apparatus 1000 shown in Figures 8 to 10 .

[0182] As shown in FIG11 , electronic device 1100 is a general-purpose electronic device. Components of electronic device 1100 may include, but are not limited to, one or more processors or processing units 1110, memory 1120, storage device 1130, one or more communication units 1140, one or more input devices 1150, and one or more output devices 1160. Processing unit 1110 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 1120. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 1100.

[0183] The electronic device 1100 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 1100, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1120 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1130 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 1100.

[0184] The electronic device 1100 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 11 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 1120 may include a computer program product 1125 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0185] The communication unit 1140 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 1100 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 1100 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or other network nodes.

[0186] Input device 1150 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 1160 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 1100 may also communicate with one or more external devices (not shown) via communication unit 1140 as needed, such as storage devices, display devices, or the like, with one or more devices that allow a user to interact with electronic device 1100, or with any device that allows electronic device 1100 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0187] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0188] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0189] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0190] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0191] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0192] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for information interaction, comprising: In an interaction window between a user and a digital assistant, at least one scene is provided, wherein a first scene in the at least one scene is configured with corresponding configuration information to perform a task of a corresponding type, wherein the configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the corresponding scene, and the plug-in information indicates at least one plug-in used to perform a task in the corresponding scene; as well as In response to receiving a selection of a first scene among the at least one scene, the user's interaction with the digital assistant is performed based at least on configuration information of the first scene.

2. The method according to claim 1, wherein: The providing at least one scene comprises: in response to an operation of opening a new topic in the interaction window, opening a first topic in the interaction window, and presenting at least one scene in an interaction area of ​​the first topic; The executing of the interaction between the user and the digital assistant includes: in response to receiving a selection of a first scene among the at least one scene, executing the interaction between the user and the digital assistant in the first topic based at least on configuration information of the first scene. 3 . The method according to claim 2 , wherein a plug-in selection portal is also presented in the interactive area of ​​the first topic, and at least one plug-in used in the first topic can be selected via the plug-in selection portal.

4. The method according to claim 1, wherein: The providing at least one scene comprises: providing a set of scenes in response to receiving a trigger operation of a scene entry control in the interactive window; and The executing of the interaction between the user and the digital assistant includes: in response to receiving a selection of the first scene in the group of scenes, opening a first topic in the interaction window; and in the first topic, executing the interaction between the user and the digital assistant based at least on the configuration information of the first scene.

5. The method according to claim 2 or 4, further comprising: In response to receiving a selection of the first scene, a first topic identifier is presented at an associated area of ​​a dividing line between the first topic and a previous topic, the first topic identifier including at least identification information of the first scene.

6. A method according to claim 5, wherein the first topic identifier also includes identification information of a first task instance performed in the first topic, and the identification information of the first task instance is determined at least based on interaction information between the user and the digital assistant in the first topic.

7. The method according to claim 1, further comprising: In response to receiving a selection of the first scene in the set of scenes, providing guidance information related to the first scene in the interactive window, the guidance information comprising at least one of the following: scene guidance information of the first scene, asking at least one recommendation question of the digital assistant in the first scenario, at least one shortcut command for the digital assistant in the first scenario, or An indication of the plugin used in the first scenario.

8. The method according to claim 1, wherein the configuration information further comprises at least one of the following: an indication of a selected model, the model being invoked to determine a response to the user in a corresponding scenario; Scene guidance information, which is presented to the user after the corresponding scene is selected; or For at least one recommended question of the digital assistant, after the corresponding scenario is selected, the at least one recommended question is presented to the user for selection.

9. The method according to claim 1, wherein the scenario setting information is used to construct a prompt word input to provide to a model used in a corresponding scenario, and the reply to the user is based on the output of the model.

10. The method according to claim 1 or 9, wherein the scene setting information includes at least one of the following: A description of the task of the corresponding type, In the scenario, the digital assistant's response style is the definition of the workflow to be executed in the corresponding scenario, or Definition of the digital assistant's reply format in the corresponding scenario. The method according to claim 1 , wherein the interactive window comprises one or more of the following: a conversation window and a floating window.

12. The method according to claim 1, further comprising: In response to receiving a scene creation operation, providing a first page for creating a target scene; Acquire, via the first page, scene creation information of the target scene, the scene creation information including at least target configuration information of the target scene; as well as In response to receiving the creation confirmation operation, the target scene is created based on the acquired target configuration information.

13. A method for information interaction, comprising: In response to the operation of opening a new topic, opening a first topic in the interaction window between the user and the digital assistant; Presenting a dividing line between the first topic and a previous topic in the interactive window; as well as In response to performing interaction between the user and the digital assistant in the first topic, a first topic identifier is presented in an associated area of ​​the dividing line, and the first topic identifier is based at least on interaction information between the user and the digital assistant in the first topic.

14. The method according to claim 13, further comprising: In response to detecting a selection of a first scene in the interaction of the first topic, or in response to detecting that the first scene is selected to trigger the opening of the first topic, presenting the first topic identifier at an area associated with the dividing line, The first scenario is configured with corresponding configuration information to guide the digital assistant to perform a first type of task.

15. The method according to claim 13, wherein the first topic identifier comprises a scene identifier of the first scene, and The scene identifier of the first scene is presented at the dividing line in response to the first scene being selected.

16. The method according to claim 13, wherein the first topic identifier comprises a task identifier of a first task instance performed in the first topic, the first task instance being determined based at least on interaction information in the first topic.

17. A method for scene creation, comprising: In response to receiving a scene creation operation, providing a first page for creating a target scene; Acquire, via the first page, scene creation information of the target scene, the scene creation information at least including target configuration information of the target scene, the target configuration information including at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in used to perform a task in the target scene; as well as In response to receiving the creation confirmation operation, the target scene is created based on the acquired target configuration information.

18. A method according to claim 17, wherein the created target scene is included in a first scene library associated with a first user who initiates a scene creation operation, and the first scene library includes scenes that the first user can select for interacting with a first digital assistant.

19. The method according to claim 17, wherein in response to receiving a scene creation operation, providing a first page for creating a target scene comprises: Providing a scene creation entry in an interaction window between the first user and the first digital assistant; Detecting a scene creation operation based on triggering the scene creation entry; as well as In response to receiving a scene creation operation, a first page for creating a target scene is provided.

20. The method according to claim 17, wherein the target configuration information further includes at least one of the following: an indication of a selected model that is invoked to determine a response to a user in the target scenario; scene guidance information, which is presented to the user after the target scene is selected; or For at least one recommended question of the digital assistant, after the target scenario is selected, the at least one recommended question is presented to the user for selection.

21. The method of claim 17, wherein the scenario setting information is used to construct a prompt word input to provide to a model for use in the target scenario.

22. The method according to claim 17 or 21, wherein the scene setting information comprises at least one of the following: A description of the task of the target type corresponding to the target scenario, The digital assistant’s response style in the target scenario, the definition of the workflow to be executed in the target scenario, or Definition of the digital assistant's response format in the target scenario.

23. The method according to claim 17, wherein the first page for creating a target scenario comprises at least one of the following: a first input area for receiving scene setting information, wherein first guiding information for inputting the scene setting information is presented, or A second input area for receiving scene guide information, wherein second guide information regarding the input of the scene guide information is presented, The first guidance information is cancelled in response to receiving an input in the first input area, and / or the second guidance information is cancelled in response to receiving an input in the second input area.

24. The method of claim 17, further comprising: In response to detecting a triggering operation on the information generation control in the first page, generating candidate scene guidance information and / or at least one candidate recommendation question based at least on the received scene setting information; as well as The candidate scene guide information is presented in a second input area in the first page for receiving scene guide information, and / or the at least one candidate recommendation question is presented in a third input area in the first page for receiving recommendation questions.

25. The method according to claim 17, wherein the scene creation information further includes identification information of the target scene. 26 . The method according to claim 17 , wherein in the first scene library, at least the target scene is marked as a type of user-defined scene.

27. The method of claim 17, further comprising: In response to receiving a selection of the created target scene, in the interaction window, the interaction between the first user and the first digital assistant is performed based at least on the configuration information of the target scene.

28. The method of claim 17, further comprising: In response to the target scene being created, setting the target scene to be in an enabled state; as well as In response to detecting that the target scene is deleted or the target scene is deactivated, the target scene is set to be in a deactivated state.

29. The method according to claim 17, wherein the first user who creates the target scene has at least one of the following permissions on the target scene: editing permission, sharing permission, deactivation permission, activation permission, or removal permission for removing the target scene from the first scene library; and / or The other users except the first user have at least one of the following permissions on the target scene: sharing permission, or removal permission for removing the target scene from the first scene library.

30. The method of claim 17, further comprising: In response to receiving an edit request for the created target scene, a second page for editing the target scene is provided, in which the scene creation information of the target scene can be edited.

31. The method of claim 17, further comprising: In response to receiving a sharing request to share the created target scene with a second user, sending a sharing link of the target scene to the second user, Wherein, via the sharing link, the target scene can be added to a second scene library associated with the second user, and the second scene library includes scenes that the second user can select for interacting with a second digital assistant.

32. A device for information interaction, comprising: A scenario providing module is configured to provide at least one scenario in an interaction window between a user and a digital assistant, wherein a first scenario in the at least one scenario is configured with corresponding configuration information to perform a task of a corresponding type, wherein the configuration information includes at least one of the following: scenario setting information and plug-in information, wherein the scenario setting information is used to describe information related to the corresponding scenario, and the plug-in information indicates at least one plug-in used to perform a task in the corresponding scenario; as well as An interaction execution module is configured to, in response to receiving a selection of a first scene among the at least one scene, execute, in the interaction window, the interaction between the user and the digital assistant based at least on the configuration information of the first scene.

33. A device for information interaction, comprising: A topic opening module, configured to open a first topic in an interaction window between a user and a digital assistant in response to an operation of opening a new topic; a dividing line presentation module, configured to present a dividing line between the first topic and a previous topic in the interactive window; as well as An identification presentation module is configured to present a first topic identification in an associated area of ​​the dividing line in response to the user interacting with the digital assistant in the first topic, wherein the first topic identification is based at least on the interaction information between the user and the digital assistant in the first topic.

34. A device for scene creation, comprising: A page providing module, configured to provide a first page for creating a target scene in response to receiving a scene creation operation; An information acquisition module is configured to acquire, via the first page, scene creation information of the target scene, wherein the scene creation information at least includes target configuration information of the target scene, and the target configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to the target scene, and the plug-in information indicates at least one plug-in used to perform a task in the target scene; as well as The scene creation module is configured to create the target scene based on the acquired target configuration information in response to receiving a creation confirmation operation.

35. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method according to any one of claims 1 to 12, the method according to any one of claims 13 to 16, or the method according to any one of claims 17 to 31.

36. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 12, the method according to any one of claims 13 to 16, or the method according to any one of claims 17 to 31.

Images