Method and apparatus for information processing, and device and storage medium

By implementing multi-interaction mode switching in terminal devices, the user-digital assistant interaction solution is solved, and the flexibility and accuracy of information processing are improved.

WO2024245425A1PCT designated stage expired Publication Date: 2024-12-05BEIJING ZITIAO NETWORK TECH CO LTD +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/096832
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-06-01
Filing Date
2024-05-31
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

The digital assistants in existing terminal devices have low interaction flexibility and high threshold for effective utilization, making it difficult to achieve efficient interaction in various task scenarios, and the manual information processing efficiency is low and error-prone.

Method used

An information processing method is provided, through interactive mode switching based on multiple interactive modes, presenting different user-digital assistant interaction areas, including a session window and an operation panel, and providing intelligent information processing services using historical interaction information and specific data.

Benefits of technology

It improves the interaction flexibility and information processing accuracy between users and digital assistants, supports users to express their needs in a more free and concise way, and reduces the time cost and error rate of information processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024096832_05122024_PF_FP_ABST
    Figure CN2024096832_05122024_PF_FP_ABST
Patent Text Reader

Abstract

Provided in the embodiments of the present disclosure are a method and apparatus for information processing, and a device and a storage medium. The method comprises: on the basis of a triggered interaction mode among a plurality of interaction modes of a first digital assistant, presenting an interaction area between a first user corresponding to the triggered interaction mode and the first digital assistant, wherein there are different interaction manners of the first user and the first digital assistant under different interaction modes. Therefore, diversified interaction between a user and a digital assistant can be realized, and flexible switching can be performed between different interaction modes as needed.
Need to check novelty before this filing date? Find Prior Art

Description

Method, device, equipment and storage medium for information processing

[0001] This application claims priority to the Chinese invention patent application entitled “Methods, devices, equipment and storage media for information processing” and application number 202310644162.8, filed on June 1, 2023. The entire contents of that application are incorporated herein by reference. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for information processing. 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, an information processing method is provided. The method includes: based on a triggered interaction mode among multiple interaction modes of a first digital assistant, presenting an interaction area between a first user and the first digital assistant corresponding to the triggered interaction mode; wherein the first user and the first digital assistant interact in different ways under different interaction modes.

[0006] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: an interaction presentation module configured to present an interaction area between a first user and the first digital assistant corresponding to a triggered interaction mode among multiple interaction modes of the first digital assistant, wherein the first user interacts with the first digital assistant in different ways under different interaction modes.

[0007] In a third 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 electronic device to perform the method of the first aspect.

[0008] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0009] 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

[0010] 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:

[0011] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] 2A to 2D illustrate schematic diagrams of example client interfaces for multiple interaction modes between a user and a digital assistant according to some embodiments of the present disclosure;

[0013] 3A to 3F illustrate schematic diagrams of example client interfaces for multiple interaction modes between a user and a digital assistant according to some embodiments of the present disclosure;

[0014] 4A and 4B are schematic diagrams showing examples of interaction history records of other interaction modes in a first interaction mode according to some embodiments of the present disclosure;

[0015] 5A to 5H illustrate schematic diagrams of example entry controls of a digital assistant in a second interaction mode according to some embodiments of the present disclosure;

[0016] FIG6 shows a flowchart of a process for information processing according to some embodiments of the present disclosure;

[0017] FIG7 shows a block diagram of an apparatus for information processing according to some embodiments of the present disclosure; and

[0018] FIG8 illustrates an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] It is understood that before using the technical solutions disclosed in each embodiment of this disclosure, the type, scope of use, and usage scenarios of the information involved in this disclosure should be informed to relevant users in an appropriate manner in accordance with relevant laws and regulations, and authorization from relevant users should be obtained. Relevant users can include any type of right holders, such as individuals, enterprises, and groups.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100, a multifunctional collaboration platform 120 is installed in a terminal device 110. A user 140 can interact with the multifunctional collaboration platform 120 via the terminal device 110 and / or an attached device of the terminal device 110. The multifunctional collaboration platform 120, such as an office collaboration platform (also referred to as an office suite), can provide an integration of various types of functions or components to facilitate people's office work, communication, and other activities. In the multifunctional collaboration platform 120, people can activate different functions or components as needed to complete corresponding information processing, sharing, communication, etc.

[0028] The multifunctional collaboration platform 120 can provide the user 140 with the integration of multiple components. These components can serve as component modules in the multifunctional collaboration platform 120. The components integrated in the multifunctional collaboration platform 120 are sometimes also referred to as "applications", "components", etc. Such components include but are not limited to office components, tool components, etc. As an example, the components integrated in the multifunctional collaboration platform 120 may include but are not limited to one or more of the following: a chat component (also known as an instant messaging component), a document component, an audio and video conferencing component, an email component, a calendar component, a schedule component, a task component, an objectives and key results (OKR) component, etc. It will be understood that various other types of components can also be integrated into the office suite.

[0029] In some embodiments, the multifunctional collaboration platform 120 can be downloaded and installed as an application on the terminal device 110. In some embodiments, the multifunctional collaboration platform 120 can also be accessed through other means, such as through a web page.

[0030] In the environment 100 of Figure 1 , if the multifunctional collaboration platform 120 is started, the terminal device 110 may present an interface 150 of the multifunctional collaboration platform 120. The interface 150 may include various user interfaces provided by the multifunctional collaboration platform 120. The interface 150 is sometimes also referred to as a client interface.

[0031] In some embodiments, the terminal device 110 communicates with the server 130 to enable the provision of services to the multifunctional collaboration platform 120. 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 server 130 can be various types of computing systems / servers that can provide computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0032] 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.

[0033] Although some multifunctional collaboration platforms can provide integration functions for different components, their intelligence level is insufficient. The content of many components (for example, documents, tables, appointments, meeting summaries, etc.) relies on manual processing and lacks the ability to automatically generate and collaborate. However, manual information processing is inefficient, repetitive, inefficient, and prone to errors. Many scenarios require searching, understanding, and organizing massive amounts of data, which further increases the difficulty of manual processing. Moreover, manual labor is time-consuming in areas such as data search and reading documents or meeting minutes. It is inefficient and prone to errors in scenarios such as summarization, text writing and calculation, reading comprehension, cross-language search, and cross-component content interaction.

[0034] To enhance intelligence, some multifunctional collaboration platforms integrate digital assistant-like features for user interaction. However, current digital assistant use cases are limited, and the barriers to effective utilization are high. Some digital assistant features have lengthy triggering paths, making it difficult to achieve efficient interaction across diverse task scenarios.

[0035] According to an embodiment of the present disclosure, an improved scheme for information processing is proposed. In this embodiment of the present disclosure, based on the interaction mode triggered among multiple interaction modes of the first digital assistant, an interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode is presented; wherein, the first user and the first digital assistant interact differently in different interaction modes. This enables diversified interactions between the user and the digital assistant, and allows flexible switching between different interaction modes as needed.

[0036] Some example embodiments of the present disclosure will be described in detail below with reference to examples in the accompanying drawings.

[0037] As previously described, in embodiments of the present disclosure, a digital assistant is used to interact with a user. As an intelligent assistant, the digital assistant has intelligent dialogue and information processing capabilities. The digital assistant performs operations in response to user input instructions. The client interface for providing 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 capable of integrating multiple components.

[0038] In an embodiment of the present disclosure, multiple interaction modes are provided between the user and the digital assistant, and flexible switching between the multiple interaction modes is possible. When a certain interaction mode is triggered, a corresponding interaction area is presented to facilitate interaction between the user and the digital assistant. The user interacts with the digital assistant in different ways under different interaction modes, which can flexibly adapt to the interaction needs in different application scenarios.

[0039] In some embodiments, the digital assistant can be included as a contact of the user in the contact list of the current user in the office suite, or included in the information flow of the chat component. In some embodiments, the user has a corresponding relationship with the digital assistant. 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. That is, 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 service 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 that it can access, its current interaction context with the first user, etc. If the first user is an individual or an individual, the first digital assistant can be regarded as a personal digital assistant. It can be understood that in the disclosed embodiment, the first digital assistant accesses the data to which permission is granted based on the authorization of the first user.

[0040] It should be understood that "uniquely corresponds" or similar expressions in the present disclosure are not intended to limit the first digital assistant to be updated accordingly based on the interaction process between the first user and the first digital assistant.

[0041] In some embodiments, it is possible to provide information processing services specific to the first user based on the historical interaction information between the first user and the first digital assistant and / or the data range specific to the first user. In some embodiments, the historical interaction information of the first user interacting with the first digital assistant in multiple interaction modes can be associated with the first user and stored. In this way, in one interaction mode (any one or a specified interaction mode) among the multiple interaction modes, the first digital assistant can provide services to the first user based on the historical interaction information stored in association with the first user.

[0042] In this way, the degree of freedom of interaction between the first user and the first digital assistant can be improved. For example, when a user interacts with a traditional assistant, the user is usually required to clearly and explicitly express the need for information processing according to certain requirements. On the contrary, by considering historical interaction information and / or user-specific data ranges, the embodiments of the present disclosure can support users to express their information processing needs in a more free and concise manner without affecting the quality of the information processing services obtained. In addition, such an approach can also improve the information processing accuracy of the first digital assistant. According to such an example implementation, a "unique correspondence" between the first user and the first digital assistant can be established.

[0043] In some embodiments, a first interaction mode among multiple interaction modes may include a conversation window-based interaction mode, also referred to as a conversation mode. When the first interaction mode among the multiple interaction modes is triggered, a conversation window between the first user and the first digital assistant is presented, in which the first user and the first digital assistant interact through conversation messages. In the first interaction mode, the first digital assistant may perform tasks based on the conversation messages in the conversation window.

[0044] In some embodiments, the first interaction mode (i.e., conversation mode) between the first user and the first digital assistant can be invoked or awakened by an appropriate means (e.g., a shortcut key, button, or voice) to present a conversation window. By selecting the first digital assistant, a conversation window with the first digital assistant 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.

[0045] In some embodiments, the second interaction mode among multiple interaction modes may include an interaction mode based on an operation panel. When the second interaction mode among multiple interaction modes is triggered, the operation panel corresponding to the first digital assistant is presented, and the first user can issue instructions to the first digital assistant 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 some embodiments, the operation panel can be presented in the form of a floating window, so the second interaction mode is also referred to as a floating window mode in this disclosure. In the second interaction mode, the first digital assistant can perform tasks according to the instructions issued by the first user through the operation panel.

[0046] In some embodiments, the second interaction mode (i.e., floating window mode) between the first user and the first digital assistant can also be called or awakened by appropriate means (e.g., shortcut keys, buttons, or voice) to present the corresponding operation panel. In some embodiments, in order to trigger the second interaction mode to present the operation panel corresponding to the first digital assistant, an entry control for the first digital assistant can be presented in the target interface area. In response to detecting a triggering operation for the entry control, it can be determined that the second interaction mode is triggered, and the operation panel corresponding to the first digital assistant is presented in the target interface area. There can be multiple ways to trigger the second interaction mode, which will be discussed in more detail below.

[0047] In some embodiments, two or more interaction modes among the multiple interaction modes can be triggered simultaneously. In the case where the triggered interaction modes include more than two interaction modes, the first user's client interface can simultaneously present interaction areas corresponding to the two or more interaction modes and the first digital assistant. In this way, in different interaction areas of the same client interface, different interaction modes are used to interact with the first digital assistant.

[0048] For ease of understanding, the following description will be made with reference to the accompanying drawings, taking the first interaction mode and the second interaction mode as examples.

[0049] Figures 2A to 2D show schematic diagrams of example client interfaces of multiple interaction modes between users and digital assistants according to some embodiments of the present disclosure. The first interaction mode is triggered, and a conversation window between the first digital assistant ("XX Assistant") and the first user ("User A") is presented in area 210 of the client interface 200. In the example of Figure 2A, the first digital assistant can be regarded as one of the contacts of the first user and is presented in the information flow of the instant messaging component. The first user can enter the conversation window by selecting the first digital assistant. In addition, the client interface 200 can correspond to a multifunctional collaboration platform that integrates multiple different types of components. Area 230 of the client interface 200 presents access entry icons for multiple components, and by selecting these icons, the corresponding components in the multifunctional collaboration platform can be started for operation.

[0050] It should be understood that Figures 2A to 2D and subsequent figures only illustrate examples of interactive areas, and other interactive areas may also exist. In addition, the various specific information, icons, etc. provided in these figures are only examples and do not limit the scope of the embodiments of the present disclosure.

[0051] In the conversation window of area 210, the first user can input a message through the input box 212 or through other appropriate means (for example, voice), and the first digital assistant can provide a reply message based on the input message and in combination with relevant knowledge. The message in the conversation window is usually a conversation message. In an embodiment of the present disclosure, the conversation message in the conversation window between the first user and the first digital assistant (for example, the conversation message of the conversation window) can be associated with the corresponding content in multiple components (for example, a multi-functional collaboration platform or an office suite). In some embodiments, the multiple components can be multiple components supported by the multi-functional collaboration platform corresponding to the client interface.

[0052] As an example, the multiple components include, but are not limited to, one or more of the following: an instant messaging component, a document component, an audio and video conferencing component, an email component, a calendar component, a schedule component, a task component, an objectives and key results (OKR) component, and the like. The content associated with the conversation message can be in the format of text, image, audio, video, or any other appropriate format. In the example of Figure 2A, the conversation message input by the first user indicates the creation of a document, and the conversation message replied by the first digital assistant provides the document automatically created by the first digital assistant based on the input of the first user.

[0053] In some embodiments, in the conversation window, the content of the component associated with each conversation message may be partially or completely included in the conversation message. For example, the conversation message provided by the first digital assistant in FIG2A displays a portion of the target document in the document component (i.e., a thumbnail of the target document). In some embodiments, the conversation message may include an access path or access entry to the content of the associated component, such as a link, a view icon, etc., through which the associated content can be accessed.

[0054] In some embodiments, the content associated with the conversation message can be presented in another area of ​​the client interface automatically or based on a user trigger (for example, the user selects a document in the conversation message). Specifically, a conversation window between the first user and the first digital assistant can be presented in the first area of ​​the client interface, and the target content can be presented in the second area of ​​the client interface. The target content is associated with the first conversation message in the conversation window and can be content provided by the first component of the multifunctional collaboration platform. What is displayed in the second area may be an operational interface provided by the first component, which includes the target content. In this way, various operational capabilities provided by the first component can be supported in the second area.

[0055] As shown in FIG2A , a conversation window is presented in area 210 of the client interface 200, and a target document in the document component to which the conversation message is associated is presented in area 220 of the client interface 200. Area 220 may include a document page of the document component. Note that in FIG2A and other figures, the first area containing the conversation window and the second area containing the target content are illustrated as being arranged side by side on the left and right. In other embodiments, the first area and the second area, as well as other areas in the client interface, may be arranged in other ways as needed. For example, the second area may be presented on the left side and the first area may be presented on the right side of the client interface. For another example, the first area and the second area may be arranged in an upper and lower partition manner, and so on.

[0056] In some embodiments, the target content presented in the second area can change with the changes in the conversation messages in the conversation window. Because multiple conversation messages in the conversation window with the first digital assistant can be associated with the content in one or more components, the target content in the second area partitioned with the conversation window can also automatically change with the changes in the conversation messages. Specifically, the first digital assistant updates the target content in the second area based on the message interaction with the first user in the conversation window, such as continuing to write a document according to the instructions of the first user. In some embodiments, the target content presented in the second area can change with the selection operation made by the first user in the conversation window. That is, the first user can control the target content presented in the second area as needed. For example, the first user may want to keep presenting a document associated with the previous conversation message, even if the subsequent conversation message in the conversation window may have been associated with the content of other documents or other components. The first user's selection operation is, for example, a click operation, a specific message entered in the conversation window, etc.

[0057] In some embodiments, in the area where the target content is displayed, another interactive mode of the first digital assistant can also be triggered. Specifically, as shown in Figure 2A, after selecting the partial content 214 of the target document in area 220, a menu 216 can be displayed, which includes the entry control of the first digital assistant, namely the "XX Assistant" control 218. By triggering the "XX Assistant" control 218, an operation panel 222 as shown in Figure 2B can be presented. The operation panel 222 may include a plurality of candidate shortcut instructions 226 and an input control 224 for receiving instructions. In the example of Figure 2B, the input control 224 for receiving instructions may be an input box for receiving text input. In other examples, alternatively or additionally, the input control for receiving instructions may also include other input controls for receiving voice input, image input, and / or video input.

[0058] As shown in Figure 2B, in the client interface 200, the interaction area corresponding to the first interaction mode (i.e., conversation mode) and the interaction area corresponding to the second interaction mode (i.e., floating window mode) are simultaneously presented. The first user can interact with the first digital assistant in either area as needed.

[0059] In some embodiments, in the second interaction mode, the operation panel corresponding to the first digital assistant can be presented in the target interface area corresponding to the target content. For example, in the example of Figure 2B, the operation panel 222 is presented in the area 220 corresponding to the target document. In this example, the operation panel 222 is presented in the form of a floating window.

[0060] It should be understood that the target content in the accompanying drawings is described using documents as an example. In other embodiments, the target content may also include any other suitable content that can be processed by the platform, including but not limited to audio, video, images, emails, calendars, schedules, tasks, etc. These contents can be adjusted with the help of the first digital assistant in any interaction mode.

[0061] In some embodiments, in the second interaction mode, one or more candidate shortcut instructions in the operation panel can be determined based on various appropriate methods to facilitate user selection for processing the target content. In some embodiments, the candidate shortcut instructions can be determined based on at least a portion of the target content, for example, can be determined based on at least a selected portion of the target content. In this way, the candidate shortcut instructions provided are particularly suitable for processing this portion of content. As shown in Figure 2B, in the operation panel 222, the candidate shortcut instructions provided include polishing, summarizing, abbreviation, translation, continuation, and analysis of advantages and disadvantages of the selected portion. In some embodiments, the candidate shortcut instructions can be determined based on historical processing operations on the target content, or interaction-related information for the target content in other interaction modes other than the second interaction mode. By considering the historical context of the target content, the user's processing requirements for the target content can be better understood, more suitable shortcut instructions can be provided, and the time required for the user to enter instructions can be avoided, thereby improving processing efficiency.

[0062] In some embodiments, in the second interaction mode, based on the target instruction detected for the target content, the processing result for the target instruction is determined, and the target instruction includes a shortcut instruction triggered in at least one candidate shortcut instruction, or an instruction received through an input control. The target content is adjusted based on the processing result. In some embodiments, in the second interaction mode, the processing result can also be presented in the operation panel. In response to detecting user confirmation of the processing result, the target content is adjusted based on the processing result. For example, if a trigger for the candidate shortcut instruction "Continue" in the operation panel is detected in Figure 2B, as shown in Figure 2C, the continued content 242 is presented in the operation panel 222, and shortcut instructions 244 for the continued content 242 can also be presented, including "Abbreviation", "Insert", "Redo" and "Delete" and the like. If a trigger for the instruction "Insert" is detected, that is, user confirmation is detected, then the continued content 242 is inserted into the target document, as shown in Figure 2D.

[0063] Figures 2B to 2D are explained by taking the example of the shortcut command in the operation panel being triggered in the second interaction mode. In other examples, the command input by the first user through the input control 224 in the operation panel can also be detected. Through the input control, the first user can input any command according to the processing needs. The first digital assistant can be used to understand the user input command and determine the corresponding processing result to adjust the target content. The candidate shortcut command or the command input by the user can be a processing requirement for at least a part of the target content, or a processing requirement for the target content as a whole. The scope of the embodiments of the present disclosure is not limited here.

[0064] In some embodiments, in the second interaction mode, after adjusting the target content based on the processing results, an undo control for the adjustment may be provided. For example, the undo control may be presented adjacent to the adjusted portion of the target content, or at any appropriate location. If the undo control is triggered, the adjustment to the target content may be undone. As shown in FIG2D , after inserting the continuation content 242, an undo control 252 is provided to allow the user to undo the insertion operation.

[0065] In some embodiments, for certain commands, or for all commands, the processing results may not be presented in the operation panel, but the target content may be adjusted directly based on the processing results. This allows the first user to quickly and directly see the processing results. If the first user is not satisfied with the processing results, they can also cancel the adjustment to the target content by issuing a subsequent command or using a provided undo control.

[0066] In some embodiments, the first interaction mode (i.e., conversation mode) and the second interaction mode (i.e., floating window mode) can allow users to perform different interactions as needed. For example, in application scenarios such as retrieval, analysis, summarization, data extraction, and optimization of typesetting, the first user can conduct multiple rounds of dialogue with the first digital assistant in the first interaction mode to complete the information processing task. In the following scenario, if a part of the target content needs to be modified, polished, continued, abbreviated, and other optimization processing, the first user can wake up the first digital assistant at a certain position in the target content and perform the information processing task in the second interaction mode. In this way, the user can interact with the first digital assistant conveniently and quickly in different interfaces or areas in different scenarios as needed to complete the information processing operation with the help of the first digital assistant. It should be understood that in any interaction mode, the first user can initiate instructions to the first digital assistant in any appropriate manner. The instruction can be an overall processing requirement for a single content or multiple contents (e.g., analysis, summary, typesetting), or it can be a specific processing requirement for a specific part of the content (e.g., polishing, modification, abbreviation, etc.). The embodiments of the present disclosure are not limited to the specific instructions under different interaction modes.

[0067] In the examples of Figures 2A to 2D, an example of simultaneously presenting the interaction areas corresponding to the two interaction modes when the first interaction mode and the second interaction mode are triggered is shown. In other embodiments, interaction areas corresponding to different interaction modes can also be presented in different client interfaces. Figures 3A to 3F show schematic diagrams of example client interfaces of multiple interaction modes between a user and a digital assistant according to some embodiments of the present disclosure. In Figure 3A, the first interaction mode (i.e., conversation mode) is triggered, and a conversation window corresponding to the first user and the first digital assistant is presented in the client interface 300.

[0068] In some cases, the first user triggers the presentation of the target content, for example, by clicking on the conversation message 310 in the conversation window, and presenting the client interface 302 as shown in Figure 3B. The target document is presented in the client interface 302. In the client interface 302, the first user can trigger the second interaction mode with the first digital assistant in an appropriate manner. As shown in Figure 3C, by selecting part of the content 320 in the target document, a menu 322 is presented, which includes the entry control of the first digital assistant, namely the "XX Assistant" control 324. By triggering the control 324, an operation panel 330 as shown in Figure 3D is presented. The operation panel 330 may include multiple candidate shortcut instructions 332 and an input control 334 for receiving instructions. If the triggering of the candidate shortcut instruction "Continue" in the operation panel is detected in Figure 3D, as shown in Figure 3E, the continued content 342 is presented in the operation panel 330, and shortcut instructions 344 for the continued content 342 may also be presented, including "Insert", "Regenerate" and "Continue Conversation". If a trigger for the instruction "insert" is detected, that is, user confirmation is detected, then the continuation content 342 is inserted into the target document, as shown in FIG3F.

[0069] The above discussion discusses the interaction between the first user and the first digital assistant in different interaction modes. In addition to the dialogue mode and the floating window mode, there may also be other interaction modes or interaction methods between the first user and the first digital assistant.

[0070] As described above, the historical interaction information of the first user interacting with the first digital assistant in multiple interaction modes can be associated with the first user and stored. In this way, in any of the multiple interaction modes, the first digital assistant can provide services to the first user based on the historical interaction information stored in association with the first user. In some embodiments, in the first interaction mode, when the first digital assistant performs a task according to the conversation message in the conversation window, the information related to the interaction between the first user and the first digital assistant in other interaction modes other than the first interaction mode is used as context. Similarly, in some embodiments, in the second interaction mode, when the first digital assistant performs a task according to the instruction issued by the first user through the operation panel, the information related to the interaction between the first user and the first digital assistant in other interaction modes other than the second interaction mode is used as context. In other words, the first digital assistant supports interacting with the first user through different interaction methods in different triggering scenarios, but the historical interaction information in different interaction modes can be considered together as the context for subsequent task processing, regardless of the interaction mode in which the subsequent task processing is triggered. In this way, the intelligence of the first digital assistant and its uniqueness for the first user can be significantly improved, so that the first digital assistant provides the user with processing results that meet the needs.

[0071] Considering that the first interaction mode is a conversation mode, in which the conversation window usually records historical interaction information, in some embodiments, information related to the interaction between the first user and the first digital assistant in other interaction modes other than the first interaction mode can also be presented in the conversation window corresponding to the first interaction mode. In this way, the interaction status of the first user and the first digital assistant in multiple interaction modes can be recorded in the conversation window. In some embodiments, the interaction-related information presented in the conversation window may include a description of operations performed in other interaction modes, for example, it may include an indication of instructions issued by the first user in other interaction modes, and / or an indication of the execution result of the first digital assistant in response to the instruction, and so on.

[0072] Specifically, if a target instruction of the first user for the target content is detected in the second interaction mode and a processing result for the target instruction is determined, a target message may be presented in the conversation window corresponding to the first interaction mode, and the target message at least indicates the processing result.

[0073] In some embodiments, the target message presented in the conversation window includes a first conversation message corresponding to the first user and a second conversation message corresponding to the first digital assistant, wherein the first conversation message indicates the target instruction and the second conversation message indicates the processing result. In this way, interaction-related information in other interaction modes (e.g., the second interaction mode) can be presented in the form of one or more rounds of conversations between the first user and the first digital assistant.

[0074] Figure 4A shows a schematic diagram of an example of the interaction history of other interaction modes in the first interaction mode according to some embodiments of the present disclosure. As shown in Figure 4A, the conversation window corresponding to the first user and the first digital assistant in the first interaction mode is presented in area 410 of the client interface 400, wherein the conversation message 412 corresponding to the first user indicates the instruction "help me polish this paragraph" issued by the first user in the other interaction mode, and the conversation message 414 corresponding to the first digital assistant indicates the processing result determined by the first digital assistant in the other interaction mode, that is, "I helped you polish this paragraph". These conversation messages record the interaction process between the first user and the first digital assistant in the other interaction mode.

[0075] In some embodiments, the target message presented in the conversation window may include a system message in the conversation window. The system message will not be presented as a conversation message corresponding to the first user or the first digital assistant in the conversation window. Figure 4B shows a schematic diagram of an example of interaction history records for other interaction modes in the first interaction mode according to some embodiments of the present disclosure. In the example of Figure 4B, it is assumed that in the client interface 402, the first digital assistant polishes part of the content in the target document through instructions issued on the operation panel 432 in the second interaction mode. After the first interaction mode is triggered, a system message 434 is presented in the conversation window corresponding to the client interface 404, which records the processing results of the first digital assistant on the target content.

[0076] In some embodiments, the target message presented in the conversation window may include an access link to the processing result. The access link is used to link to the portion of the target content related to the processing result. For example, in the examples of Figures 4A and 4B, "This paragraph" in messages 412, 414, and 434 includes an access link. Clicking the access link jumps to the polished portion of the target content. Providing the access link allows the first user to quickly access the processed content from the target message in the conversation window as needed.

[0077] In some embodiments, after the target message is presented in the conversation window corresponding to the first interaction mode, a reply to the conversation message input by the user can be determined in the first interaction mode based at least on the target message. In other words, the target message can be conveniently referenced in the first interaction mode as historical interaction information. For example, the first user can continue to initiate a conversation with the target message in the conversation window, requesting the first digital assistant to continue to make other adjustments or processes to the target content connected to the target message or a portion thereof. The first digital assistant can directly understand the processing requirements of the first user.

[0078] In the above embodiments, at least a portion of the target content is selected to present the entry control corresponding to the first digital assistant to trigger the second interaction mode. As mentioned above, there may be more ways to trigger the second interaction mode. Figures 5A to 5H show schematic diagrams of example entry controls of a digital assistant in the second interaction mode according to some embodiments of the present disclosure.

[0079] In some embodiments, the entry control corresponding to the first digital assistant is fixedly displayed at a predetermined position in the target interface area. As shown in Figure 5A, the target interface area corresponding to the target content is presented in the client interface 500, and the entry control 520 corresponding to the first digital assistant is presented at a predetermined position in the target interface area, such as a menu position. In this way, when the target interface area corresponding to the target content is presented, the first user can trigger the entry control at the predetermined position as needed to trigger the second interaction mode corresponding to the first digital assistant.

[0080] In some embodiments, the entry control corresponding to the first digital assistant can be presented in the target interface area in response to a preset operation. The preset operation can be any appropriate operation, including the selection of part of the content described above in conjunction with Figures 2A to 2D and Figures 3A to 3F. In some examples, the preset operation can also include inputting preset symbols in the target interface area or target content, hovering operations in preset areas, and the like. For example, in the client interface 501 of Figure 5B, in response to inputting " / " in the target document, a menu can be presented, which includes the entry control 520 corresponding to the first digital assistant. In the client interface 502 of Figure 5C, in response to a hovering operation in the preset area of ​​the target document, a control 522 is presented, and the hovering operation on the control 522 will further trigger the display of a menu including the entry control 520 corresponding to the first digital assistant. In the client interface 504 of Figure 5D, in response to a hovering operation on a paragraph in the target document, a control 524 is presented, and the hovering operation on the control 524 will further trigger the display of a menu including the entry control 520 corresponding to the first digital assistant. In the client interface 506 of Figure 5E, in response to partial content in the target document being selected, a menu including an entry control 520 corresponding to the first digital assistant is presented.

[0081] In some embodiments, when the target content type is a preset type, the entry control is embedded in the target content in the target interface area. The preset type can be set as needed, for example, it can be a type of content that is predetermined to specifically trigger the first digital assistant to assist in processing. In some embodiments, the preset type can include, for example, a type of blank content (e.g., a blank document) or a type of content that only includes a title.

[0082] As shown in Figure 5F, a blank document is presented in the client interface 508, in which the entry control 522 corresponding to the first digital assistant is directly embedded. In some embodiments, based on the preset type, the entry control corresponding to the first digital assistant can also be configured to trigger the corresponding instruction. For example, in Figure 5F, by triggering the entry control 522, the "help me write" instruction can be triggered to request the first digital assistant to help write the document. In the client interface 510 shown in Figure 5G, if the target document is a document that only includes a title, after triggering the entry control, the first digital assistant can write the document content based on the title, and present an operation panel 524, which includes input controls and some candidate shortcut instructions such as "redo" and "stop". In some examples, if the target content does not include a title, as shown in the client interface 512 in Figure 5H, after triggering the entry control, the operation panel 525 of the first digital assistant can be presented, which includes input controls to prompt the user to enter the document subject.

[0083] It should be understood that Figures 5A to 5H only illustrate example presentation methods for the entry control of the first digital assistant in the interface area corresponding to the target content. Depending on actual application needs, the entry control corresponding to the first digital assistant can also be configured as other presentation methods, and the embodiments of the present disclosure are not limited thereto.

[0084] 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.

[0085] 6 shows a flow chart of a process 600 for information processing according to some embodiments of the present disclosure. The process 600 may be implemented at the terminal device 110. For ease of discussion, the process 200 will be described with reference to the environment 100 of FIG.

[0086] In box 610, the terminal device 110 presents the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode based on the interaction mode triggered among the multiple interaction modes of the first digital assistant; wherein, the interaction method between the first user and the first digital assistant is different in different interaction modes.

[0087] In some embodiments, presenting the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: when the triggered interaction mode includes more than two interaction modes, in the client interface of the first user, the interaction areas between the first user and the first digital assistant corresponding to the two or more interaction modes are simultaneously presented.

[0088] In some embodiments, historical interaction information of the first user interacting with the first digital assistant in multiple interaction modes is stored in association with the first user; in one of the multiple interaction modes, the first digital assistant provides services to the first user based on the historical interaction information stored in association with the first user.

[0089] In some embodiments, presenting the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: when the first interaction mode among multiple interaction modes is triggered, presenting a conversation window between the first user and the first digital assistant, in which the first user and the first digital assistant interact through conversation messages.

[0090] In some embodiments, process 600 also includes: presenting information related to the interaction between the first user and the first digital assistant in other interaction modes in a conversation window corresponding to the first interaction mode; wherein the other interaction modes are interaction modes other than the first interaction mode among multiple interaction modes.

[0091] In some embodiments, the interaction-related information includes descriptions of operations performed in other interaction modes.

[0092] In some embodiments, in the first interaction mode, when the first digital assistant performs a task based on the conversation message in the conversation window, it uses the interaction-related information between the first user and the first digital assistant in other interaction modes as context; wherein the other interaction modes are interaction modes other than the first interaction mode among multiple interaction modes.

[0093] In some embodiments, presenting the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: when the second interaction mode among multiple interaction modes is triggered, presenting an operation panel corresponding to the first digital assistant, the operation panel including at least one of the following: at least one candidate shortcut instruction, and an input control for receiving instructions, and the first user issues instructions to the first digital assistant based on the operation panel.

[0094] In some embodiments, in the second interaction mode, when the first digital assistant performs a task according to the instructions issued by the first user through the operation panel, the first digital assistant uses the interaction-related information between the first user and the first digital assistant in other interaction modes as context; wherein, the other interaction modes are interaction modes other than the second interaction mode among multiple interaction modes.

[0095] In some embodiments, presenting the operation panel corresponding to the first digital assistant includes: presenting an entry control for the first digital assistant in a target interface area corresponding to the target content; determining that the second interaction mode is triggered in response to detecting a trigger operation for the entry control; and presenting the operation panel corresponding to the first digital assistant in the target interface area.

[0096] In some embodiments, the entry control is fixedly displayed at a predetermined location in the target interface area. In some embodiments, the entry control is presented in the target interface area in response to a preset operation. In some embodiments, if the target content is of a preset type, the entry control is embedded within the target content in the target interface area.

[0097] In some embodiments, at least one candidate shortcut instruction in the operation panel is determined based on at least one of the following: at least a portion of the target content, historical processing operations on the target content, or interaction-related information for the target content in other interaction modes, where the other interaction modes are interaction modes other than the second interaction mode in multiple interaction modes.

[0098] In some embodiments, process 600 also includes: in the second interaction mode, based on the detected target instruction for the target content, determining the processing result for the target instruction, the target instruction including a shortcut instruction triggered from at least one candidate shortcut instruction, or an instruction received through the input control; and adjusting the target content based on the processing result.

[0099] In some embodiments, adjusting the target content based on the processing result includes: presenting the processing result in an operation panel; and in response to detecting user confirmation of the processing result, adjusting the target content based on the processing result.

[0100] In some embodiments, process 600 also includes providing an undo control for the adjustment.

[0101] In some embodiments, process 600 also includes: when multiple interaction modes include a first interaction mode, and in the first interaction mode, the interaction area between the first user and the first digital assistant is a conversation window, presenting a target message in the conversation window corresponding to the first interaction mode, and the target message at least indicates a processing result.

[0102] In some embodiments, the target message includes a first conversation message corresponding to the first user and a second conversation message corresponding to the first digital assistant, the first conversation message indicating the target instruction, and the second conversation message indicating the processing result. In some embodiments, the target message includes a system message in the conversation window.

[0103] In some embodiments, the target message includes an access link to the processing result, where the access link is used to link to a portion of the target content that is related to the processing result.

[0104] In some embodiments, process 600 further includes: in the first interaction mode, determining a reply to the conversation message input by the user based on at least the target message.

[0105] In some embodiments, the target content includes one or more of the following: documents, audio, video, images, emails, calendars, schedules, and tasks.

[0106] 7 shows a schematic structural block diagram of an apparatus 700 for information processing according to some embodiments of the present disclosure. Apparatus 700 may be implemented as or included in terminal device 110. Each module / component in apparatus 700 may be implemented by hardware, software, firmware, or any combination thereof.

[0107] The device 700 includes an interaction presentation module 710, which is configured to present an interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode among multiple interaction modes of the first digital assistant; wherein the interaction method between the first user and the first digital assistant is different in different interaction modes.

[0108] In some embodiments, the interaction presentation module 710 includes: a simultaneous presentation module, which is configured to simultaneously present the interaction areas between the first user and the first digital assistant corresponding to the two or more interaction modes in the client interface of the first user when the triggered interaction mode includes more than two interaction modes.

[0109] In some embodiments, historical interaction information of the first user interacting with the first digital assistant in multiple interaction modes is stored in association with the first user; in one of the multiple interaction modes, the first digital assistant provides services to the first user based on the historical interaction information stored in association with the first user.

[0110] In some embodiments, the interaction presentation module 710 includes: a first interaction presentation module, configured to present a conversation window between the first user and the first digital assistant when the first interaction mode among multiple interaction modes is triggered, in which the first user and the first digital assistant interact through conversation messages.

[0111] In some embodiments, the device 700 also includes: an interaction information presentation module, configured to present information related to the interaction between the first user and the first digital assistant in other interaction modes in a conversation window corresponding to the first interaction mode; wherein the other interaction modes are interaction modes other than the first interaction mode among multiple interaction modes.

[0112] In some embodiments, the interaction-related information includes descriptions of operations performed in other interaction modes.

[0113] In some embodiments, in the first interaction mode, when the first digital assistant performs a task based on the conversation message in the conversation window, it uses the interaction-related information between the first user and the first digital assistant in other interaction modes as context; wherein the other interaction modes are interaction modes other than the first interaction mode among multiple interaction modes.

[0114] In some embodiments, the interaction presentation module 710 includes: a second interaction presentation module, configured to present an operation panel corresponding to the first digital assistant when a second interaction mode among multiple interaction modes is triggered, the operation panel including at least one of the following: at least one candidate shortcut instruction, and an input control for receiving instructions, and the first user issues instructions to the first digital assistant based on the operation panel.

[0115] In some embodiments, in the second interaction mode, when the first digital assistant performs a task according to the instructions issued by the first user through the operation panel, the first digital assistant uses the interaction-related information between the first user and the first digital assistant in other interaction modes as context; wherein, the other interaction modes are interaction modes other than the second interaction mode among multiple interaction modes.

[0116] In some embodiments, the second interaction presentation module includes: an entry presentation module, configured to present an entry control for the first digital assistant in a target interface area corresponding to the target content; a second interaction mode triggering module, configured to determine that the second interaction mode is triggered in response to detecting a trigger operation for the entry control; and a post-trigger presentation module, configured to present an operation panel corresponding to the first digital assistant in the target interface area.

[0117] In some embodiments, the entry control is fixedly displayed at a predetermined location in the target interface area. In some embodiments, the entry control is presented in the target interface area in response to a preset operation. In some embodiments, if the target content is of a preset type, the entry control is embedded within the target content in the target interface area.

[0118] In some embodiments, at least one candidate shortcut instruction in the operation panel is determined based on at least one of the following: at least a portion of the target content, historical processing operations on the target content, or interaction-related information for the target content in other interaction modes, where the other interaction modes are interaction modes other than the second interaction mode in multiple interaction modes.

[0119] In some embodiments, the device 700 also includes: a result determination module, configured to determine, in the second interaction mode, a processing result for the target instruction based on the detected target instruction for the target content, the target instruction including a shortcut instruction triggered from at least one candidate shortcut instruction, or an instruction received through an input control; and a content adjustment module, configured to adjust the target content based on the processing result.

[0120] In some embodiments, the content adjustment module includes: a result presentation module configured to present the processing result in the operation panel; and a post-confirmation adjustment module configured to adjust the target content based on the processing result in response to detecting user confirmation of the processing result.

[0121] In some embodiments, the apparatus 700 further includes: an undo providing module configured to provide an undo control for the adjustment.

[0122] In some embodiments, the device 700 also includes: a message presentation module, which is configured to present a target message in a conversation window corresponding to the first interaction mode when multiple interaction modes include a first interaction mode and the interaction area between the first user and the first digital assistant in the first interaction mode is a conversation window, and the target message at least indicates a processing result.

[0123] In some embodiments, the target message includes a first conversation message corresponding to the first user and a second conversation message corresponding to the first digital assistant, the first conversation message indicating the target instruction, and the second conversation message indicating the processing result. In some embodiments, the target message includes a system message in the conversation window.

[0124] In some embodiments, the target message includes an access link to the processing result, where the access link is used to link to a portion of the target content that is related to the processing result.

[0125] In some embodiments, the apparatus 700 further includes: a reply determination module configured to determine, in the first interaction mode, a reply to the conversation message input by the user based at least on the target message.

[0126] In some embodiments, the target content includes one or more of the following: documents, audio, video, images, emails, calendars, schedules, and tasks.

[0127] 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 .

[0128] FIG8 shows a block diagram of an electronic device 800 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 800 shown in FIG8 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 800 shown in FIG8 may be used to implement the terminal device 110 of FIG1 .

[0129] As shown in FIG8 , electronic device 800 is a general-purpose electronic device. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 800.

[0130] The electronic device 800 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 820 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 830 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 800.

[0131] The electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG8 , 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 820 may include a computer program product 825 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0132] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 800 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 800 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0133] The input device 850 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 860 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 800 may also communicate with one or more external devices (not shown) via the communication unit 840 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 800, or with any device that allows the electronic device 800 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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. An information processing method, comprising: Based on a triggered interaction mode among a plurality of interaction modes of the first digital assistant, presenting an interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode; Among them, the interaction methods of the first user and the first digital assistant are different in different interaction modes.

2. The method according to claim 1, wherein: The interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: In the case where the triggered interaction mode includes more than two interaction modes, in the client interface of the first user, interaction areas between the first user and the first digital assistant corresponding to the two or more interaction modes are simultaneously presented.

3. The method according to claim 1, wherein: The historical interaction information of the first user interacting with the first digital assistant in the multiple interaction modes is stored in association with the first user; In one interaction mode among the multiple interaction modes, the first digital assistant provides services for the first user based on historical interaction information stored in association with the first user.

4. The method according to any one of claims 1 to 3, wherein: Presenting the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: When the first interaction mode among the multiple interaction modes is triggered, a conversation window between the first user and the first digital assistant is presented, in which the first user interacts with the first digital assistant through conversation messages.

5. The method according to claim 4, wherein: The method further includes: Presenting information related to the interaction between the first user and the first digital assistant in other interaction modes in the conversation window corresponding to the first interaction mode; The other interaction modes are interaction modes other than the first interaction mode among the multiple interaction modes.

6. The method according to claim 5, wherein: The interaction-related information includes a description of operations performed in the other interaction modes.

7. The method according to claim 5, wherein: In the first interaction mode, when the first digital assistant performs a task according to the conversation message in the conversation window, the first digital assistant uses information related to the interaction between the first user and the first digital assistant in other interaction modes as context; The other interaction modes are interaction modes other than the first interaction mode among the multiple interaction modes.

8. The method according to any one of claims 1 to 7, wherein: Presenting the interaction area between the first user and the first digital assistant corresponding to the triggered interaction mode includes: When the second interaction mode among the multiple interaction modes is triggered, an operation panel corresponding to the first digital assistant is presented, and the operation panel includes at least one of the following: at least one candidate shortcut command, and an input control for receiving commands, and the first user issues commands to the first digital assistant based on the operation panel.

9. The method according to claim 8, wherein: In the second interaction mode, when the first digital assistant performs a task according to an instruction issued by the first user through the operation panel, the first digital assistant uses information related to the interaction between the first user and the first digital assistant in other interaction modes as context; The other interaction modes are interaction modes other than the second interaction mode among the multiple interaction modes.

10. The method according to claim 8, wherein: The presenting of the operation panel corresponding to the first digital assistant comprises: Presenting an entry control for the first digital assistant in a target interface area corresponding to the target content; In response to detecting a triggering operation on the portal control, determining that the second interaction mode is triggered; and The operation panel corresponding to the first digital assistant is presented in the target interface area.

11. The method according to claim 10, wherein The entry control is fixedly displayed at a predetermined position in the target interface area; Alternatively, the entry control is presented in the target interface area in response to a preset operation; Alternatively, when the type of the target content is a preset type, the entry control is embedded in the target content in the target interface area.

12. The method according to claim 10, wherein the at least one candidate shortcut command in the operation panel is determined based on at least one of the following: at least a portion of the target content, the historical processing operations on the target content, or The information related to interaction with the target content in other interaction modes is an interaction mode other than the second interaction mode among the plurality of interaction modes.

13. The method according to claim 10, further comprising: In the second interaction mode, based on the detected target instruction for the target content, determining a processing result for the target instruction, the target instruction including a shortcut instruction triggered from the at least one candidate shortcut instruction, or an instruction received through the input control; as well as The target content is adjusted based on the processing results.

14. The method according to claim 13, wherein: adjusting the target content based on the processing result comprises: presenting the processing result in the operation panel; and in response to detecting a user confirmation of the processing result, adjusting the target content based on the processing result; Alternatively, the method further comprises: providing an undo control for the adjustment.

15. The method according to claim 13, further comprising: In the case where the plurality of interaction modes include a first interaction mode, and in the first interaction mode, the interaction area between the first user and the first digital assistant is a conversation window, A target message is presented in a conversation window corresponding to the first interaction mode, wherein the target message at least indicates the processing result.

16. The method according to claim 15, wherein The target message includes a first conversation message corresponding to the first user and a second conversation message corresponding to the first digital assistant, the first conversation message indicates the target instruction, and the second conversation message indicates the processing result; Alternatively, the target message includes a system message in the session window; Alternatively, the target message includes an access link to the processing result, and the access link is used to link to a portion of the target content that is related to the processing result.

17. The method according to claim 15, further comprising: In the first interaction mode, a reply to a conversation message input by a user is determined based at least on the target message.

18. The method of claim 10, wherein the target content comprises one or more of the following: Documents, audio, video, images, email, calendar, schedule, tasks.

19. An apparatus for information processing, comprising: An interaction presentation module, configured to present an interaction area between the first user and the first digital assistant corresponding to a triggered interaction mode among a plurality of interaction modes of the first digital assistant, based on the triggered interaction mode; Among them, the interaction methods of the first user and the first digital assistant are different in different interaction modes.

20. 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 causing the electronic device to perform the method according to any one of claims 1 to 18 when executed by the at least one processing unit.

21. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 18.

Citation Information

Patent Citations

  • Use of a digital assistant in communications

    CN111147357A

  • Interaction method and device and electronic equipment

    CN112306595A

  • Providing user interface elements for interactive sessions

    US20140298200A1

  • Methods and systems for helper bot platform assistance

    US20190068526A1