Methods, apparatuses, storage media, and program products for use in sessions

Abstract

A method, apparatus, storage medium, and program product for use in conversations are provided. According to the proposed method, an input component is presented in a first interface, the first interface being used to display a conversation, the participants of which include at least two users; input content is received via the input component, the input content including a first element indicating a reference to a first resource; and during the conversation, a first message is sent, the first message being used to trigger an intelligent system to perform an action, the first message including the input content, the action being related to the first resource. This approach improves the convenience of conversations.

Description

Technical Field

[0001] The examples in this article generally relate to the field of computer science, and in particular to methods, apparatuses, devices, and computer-readable storage media for use in sessions. Background Technology

[0002] With the development of network communication and information technology, session-based interaction methods are widely used in various application scenarios. For example, users can exchange information with other users through the session interface on electronic devices, and complete communication and collaboration by sending messages, sharing information, or discussing tasks. Summary of the Invention

[0003] In a first aspect, a method for a conversation is provided. The method includes: presenting an input component in a first interface for displaying a conversation, the participants of which include at least two users; receiving input content via the input component, the input content including a first element indicating a reference to a first resource; and sending a first message in the conversation, the first message for triggering an intelligent system to perform an action, the first message including the input content and the action being related to the first resource.

[0004] In a second aspect, an apparatus for a conversation is provided. The apparatus includes: a presentation module configured to present an input component in a first interface for displaying a conversation, the participants of which include at least two users; a receiving module configured to receive input content via the input component, the input content including a first element indicating a reference to a first resource; and a sending module configured to send a first message in the conversation, the first message triggering an intelligent system to perform an action, the first message including the input content and the action relating to the first resource.

[0005] In a third aspect, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] In this way, by introducing resource references during the conversation input process and generating a first message based on the resource to trigger the intelligent system to perform actions, the intelligent system can directly obtain explicit resource indication information. This approach reduces the computational load of parsing and reasoning about natural language content, lowers the uncertainty of semantic understanding, thereby improving the stability and efficiency of the processing and enhancing the convenience of the conversation.

[0009] It should be understood that the content described in this section is not intended to limit the key or important features of the examples in this article, nor is it intended to restrict the scope of the solution. Other features will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the various examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of the example environment is shown; Figures 2A to 2H Example interfaces for some scenarios are shown; Figure 3 Flowcharts of example procedures for sessions in some scenarios are shown; Figure 4 Schematic block diagrams of example devices for use in conversations are shown in some scenarios; and Figure 5 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0011] The examples in the text will now be described in more detail with reference to the accompanying drawings. While some examples are shown in the drawings, it should be understood that solutions can be implemented in various forms and should not be construed as limited to the examples presented herein. Rather, these examples are provided to provide a more thorough and complete understanding of the solutions. It should be understood that the drawings and examples in this document are for illustrative purposes only and are not intended to limit the scope of protection of the solutions.

[0012] It should be noted that the headings of any section / subsection provided herein are not restrictive. Various examples are described throughout this document, and examples of any type may be included under any section / subsection. Furthermore, examples described in any section / subsection may be combined in any way with any other examples described in the same section / subsection and / or different sections / subsections.

[0013] In the description of the examples in this document, 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 "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The term "some examples" should be understood as "at least some examples". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0014] The examples in this document may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and provisions. In the examples presented herein, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means, in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario; the scope of the solution is not limited in this regard.

[0015] In this manual and the sample solutions, any processing of personal information will be conducted only under legal grounds (such as obtaining the consent of the data subject or being necessary for the performance of a contract) and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0016] In this paper, an intelligent system refers to a system capable of autonomous control based on machine learning models. An intelligent system is, for example, a virtual object or physical entity capable of making decisions and autonomously executing actions based on machine learning models to achieve preset goals or complete preset tasks. An intelligent system can be an automated program that understands user intent and can utilize models or invoke tools to complete various types of tasks. In some contexts, examples of intelligent systems may include, but are not limited to: agents, bots, chatbots, digital avatars, intelligent customer service, digital assistants, etc. Alternatively, an intelligent system can also be an intelligent role implemented based on machine learning models. An "intelligent system" can process user requests based on generative models (e.g., language models, multimodal models) to perform specified types of tasks.

[0017] In some scenarios, intelligent systems can be represented as virtual avatars for interaction with users. The term "virtual object" can refer to a digital entity capable of interacting with a user. Virtual objects can include, but are not limited to, digital assistants, intelligent assistants, AI assistants, chatbots, and virtual agents. Virtual objects can possess intelligent dialogue and information processing capabilities, responding to user queries and providing appropriate answers. In some examples, virtual objects can be presented in a graphical form within the interactive interface, such as as avatars, animated characters, or other visual representations.

[0018] As used in this disclosure, the term "machine learning model" refers to a computational model that performs tasks by learning patterns and rules from data. Machine learning models can include, but are not limited to, neural network models, deep learning models, and large language models. In some cases, large language models are an example of machine learning models that can understand and generate natural language text and can be used to perform operations such as task decomposition, tool invocation, and content generation.

[0019] As mentioned above, with the development of information technology, session-based interaction has been widely used in various application scenarios. For example, users can exchange information with other users in the session interface of electronic devices, completing communication and collaboration by sending messages, sharing information, or discussing related content.

[0020] In some scenarios, conversational interactions involve not only message content but also various resources. For example, during a conversation, participants may need to share documents, data files, or other content to facilitate discussion or collaborative processing around relevant resources.

[0021] Furthermore, with the development of artificial intelligence technology, some conversational systems have begun to incorporate intelligent systems, enabling users to not only exchange information during conversations but also to initiate task requests to the intelligent system, which will then perform the corresponding processing and return the results.

[0022] In the aforementioned interaction scenarios, if a user wants to use certain resources during a session or initiate a task related to those resources, they typically need to prepare the resource files and provide them to the session system by uploading files, inputting resource locations, or copying resource content. This increases the complexity of the interaction and reduces the efficiency of the session interaction to some extent.

[0023] In view of this, this paper proposes a scheme for conversations. According to this scheme, an input component can be presented in a first interface, which is used to display the conversation, and the participants in the conversation include at least two users. Further, input content can be received via the input component, and the input content includes a first element indicating a reference to a first resource. Further still, a first message can be sent in the conversation, and the first message is used to trigger the intelligent system to perform an action; the first message includes input content, and the action is related to the first resource.

[0024] In this way, by introducing resource references into conversation messages within user conversation scenarios, the intelligent system can be triggered to execute corresponding actions based on the referenced resources simultaneously with message sending. This allows resource referencing and task triggering to be completed seamlessly within the conversation. Compared to methods that require providing resource information through a separate interface or additional operations, the solution presented in this paper allows the resource usage process to be more naturally integrated into the conversation interaction flow, thereby improving the efficiency and convenience of invoking the intelligent system to execute actions in conversation scenarios.

[0025] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0026] Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, example environment 100 may include electronic device 110.

[0027] In this example environment 100, electronic device 110 may run an application 120 that supports sessions. Application 120 may be any suitable type of application for sessions. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0028] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting sessions.

[0029] In some cases, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0030] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 in electronic devices 110 that support session usage.

[0031] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (Wi-Fi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the scheme.

[0033] The following description of the example will continue with reference to the accompanying drawings.

[0034] Figures 2A to 2HExample interfaces 200A to 200H are shown according to some scenarios. Interfaces 200A to 200H can, for example, be derived from... Figure 1 The interface is provided by the electronic device 110 shown, for example, by the application 120 running on the electronic device 110. It should be understood that the interface shown in the figures is merely an example, and various interface designs may exist in practice. The various graphic elements in the interface may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also be present.

[0035] The following text uses an interactive interface in a conversational scenario as an example for illustration. Figure 2A In this example, interface 200A includes a sample session interface. Through interface 200A, session content can be displayed, and information exchange between session participants can be supported. Session participants can include at least two users.

[0036] In some scenarios, the electronic device 110 may present an input component on a first interface used to display a session, the participants of which include at least two users. The input component can be used to receive user input during the session to support information interaction between users within the session.

[0037] As an example, interface 200A may provide an input component 210 for entering conversation messages. In input component 210, the user can enter conversation content and send corresponding messages. Input component 210 may support text input, such as entering text in a text input box. Input component 210 may also support various input methods such as voice input and image input.

[0038] In some cases, electronic device 110 can display user-sent conversational messages in a conversational interface. Conversational messages may include information used to express the content of the communication. For example, in interface 200A, electronic device 110 can receive conversational messages sent by user 140. After receiving the message, electronic device 110 can display the user-sent message in interface 200A.

[0039] In some scenarios, a session may include an intelligent system, allowing users to initiate task requests to the system and receive processing results during the session. Session messages may also include content indicating task requests. For example, a session message might involve consulting about an object, requesting information related to that object (e.g., recommendations, comparisons, or reviews), or requesting the intelligent system to process relevant content.

[0040] In some examples, at least two users involved in the session may be different from the intelligent system. These at least two users can interact during the session, such as sending text, voice, or other forms of conversational messages, to facilitate communication and collaboration. During this process, the intelligent system may be in an inactive state and not participate in the real-time interaction of the session.

[0041] In some examples, an intelligent system can participate in a session in response to at least one message in the session, that is, when a session message meets predetermined conditions (such as containing specific content, referencing a specific resource, or indicating a task request), the intelligent system is triggered to perform the corresponding processing action.

[0042] The following examples, with reference to the accompanying drawings, illustrate some of these practices. These examples can be implemented in electronic device 110. It should be noted that the operations performed by electronic device 110 may specifically be performed by relevant applications installed on electronic device 110. Some operations described herein with reference to electronic device 110 may require the assistance of server 130.

[0043] In some cases, electronic device 110 can receive input content via an input component. The input content may include a first element that indicates a reference to a first resource. During user-interactive sessions, the session content may include not only text information directly entered by the user but also various resources related to the session. A resource can refer to a data object that can be referenced and processed. For example, a resource may include files, images, or other data content sent during the session, or it may include resources in a cloud environment or other external resources associated with the session. By including a first element in the input content to reference a resource, the resource is no longer merely existing as independent information but can participate in subsequent information processing.

[0044] In some cases, the first element can be a structured element used to represent a reference to a first resource in the input content. Unlike simply describing a resource in natural language, the first element explicitly indicates the target resource. By introducing the first element into the input content, conversational messages can not only express natural language content but also carry reference information to resources, thus providing a basis for triggering actions in intelligent systems based on resources.

[0045] In some cases, in response to a first instruction, electronic device 110 may present at least one identifier, which may correspond to at least one resource. Further, in response to the selection of a first identifier, electronic device 110 may present a first element in an input component, whereby the first identifier corresponds to a first resource.

[0046] As an example, refer to Figure 2BIn response to the first instruction, the electronic device 110 can present at least one identifier 225 corresponding to at least one resource in the input component 210. The at least one identifier can also be referred to as at least one resource identifier, which is a visual representation of the resource. The at least one identifier is associated with a corresponding resource, allowing the user to intuitively view different resources through the identifier. Furthermore, the at least one identifier 225 can be configured as a selectable interactive object, enabling the user to specify a target resource by selecting the identifier 225. In this way, the resource selection process can be integrated into the input process, reducing the need for users to switch between different interfaces or perform repetitive operations, thereby improving the convenience of resource retrieval.

[0047] Continue to refer to Figure 2C In response to the selection of a first identifier in at least one identifier 225, the electronic device 110 may present a first element 231 in the input component 210. The first element 231 is used to represent a reference to a first resource in the input content. By embedding the first element into the input content in the input component, the resource can participate in subsequent processing in a structured form without requiring the user to repeatedly describe the resource in natural language, thereby further improving interaction efficiency and reducing ambiguity.

[0048] In some cases, the first instruction includes a predefined character. The predefined character can be used to trigger an interactive process related to resource selection. In response to receiving the predefined character in the input component, the electronic device 110 can present at least one identifier for the user to select the corresponding resource. For example, the predefined character may include the "@" symbol. If the user enters the "@" symbol in the input component, the electronic device 110 can display the identifier of at least one resource associated with the session, thereby enabling the user to quickly select and reference the target resource during the session's input process.

[0049] In some scenarios, electronic device 110 can present at least one identifier of at least one resource related to the context of the session. For example, the type of at least one resource is related to the context of the session. The context can be used to represent the semantic state of the current session, reflecting the user's interaction purpose or processing needs in the current session. In other words, resources of a preset type can not be presented in a fixed manner, but the range of available resources can be dynamically adjusted based on the context of the current session, so that the presented resources better meet the usage needs of the current session. In this way, the resource selection process can be contextualized and adaptive, thereby reducing interference from irrelevant resources and improving the efficiency of resource invocation and the targeting of subsequent processing.

[0050] In some situations, the context of a session can be determined based on the session's contextual information. Contextual information may include, but is not limited to, session message content, historical interaction records, participant information, and resource usage. For example, in a session involving at least two users, the interaction content between different users and the relationships between them can collectively constitute the session's context, thereby influencing the range of available resources.

[0051] In some situations, electronic device 110 can utilize an intelligent system to identify the scenario of a conversation based on contextual information. In other words, the scenario of a conversation can be obtained by the intelligent system through analysis and identification of multidimensional information generated during the conversation, thereby achieving automatic understanding of the current interaction state.

[0052] In some examples, the context of a conversation can be related to its type. For example, conversation types can include, but are not limited to, personal conversations, group conversations, or conversations with intelligent systems. Different types of conversations may have different usage requirements, which can affect the type of resources presented. For example, in a group conversation, resources shared with multiple participants can be prioritized; while in a conversation with an intelligent system, resources suitable for intelligent processing can be prioritized.

[0053] In some examples, the context of a conversation can be associated with its topic. For instance, the topic of a conversation can be determined based on the content of the conversation, representing the direction of the current discussion. Based on different conversation topics, the electronic device 110 can present different types or ranges of resources. For example, under a topic related to document processing, document resources can be presented first; under a topic related to image creation, image resources can be presented first.

[0054] In some examples, the scenario of a session can be associated with its interaction mode. For example, interaction modes may include information query mode, content generation mode, or collaborative editing mode. Users may use resources differently under different interaction modes; therefore, electronic device 110 can adjust the type or form of the presented resources based on the interaction mode to better support the corresponding interaction needs.

[0055] As an example, refer to Figure 2B and Figure 2CIn response to a scenario related to information processing (e.g., an office scenario), electronic device 110 may present at least one identifier 225 of at least one document resource in input component 210. In response to the selection of the first identifier corresponding to the document resource, electronic device 110 may present a corresponding first element 231 in input component 210. The first element 231 represents the selected document resource and is embedded in the current input content to indicate a reference to the document resource, thereby facilitating the performance of information processing-related operations based on the document resource in subsequent session messages.

[0056] As another example, see Figure 2D and Figure 2E In response to a second scenario related to content generation (e.g., a content creation scenario based on an intelligent system), electronic device 110 may present at least one identifier 245 indicating at least one media resource in input component 210. The media resource may include content such as images, videos, or audio.

[0057] In some cases, a user may select at least one identifier. For example, a user may select multiple identifiers to indicate multiple resources. In response to the selection of a first identifier corresponding to a first media resource and a second identifier corresponding to a second media resource, the electronic device 110 may present corresponding first elements 251 and second elements 252 in the input component 210. The first elements 251 and second elements 252 may respectively represent the selected media resources (e.g., the first elements 251 and second elements 252 may be in the form of thumbnails) and are embedded in the input content to indicate references to multiple resources, thereby supporting content generation-related processing based on multiple resources.

[0058] In some cases, electronic device 110 can display identifiers corresponding to different resource types in different display components. A display component can refer to an interface area or control unit used to carry and display resource identifiers; it can be a sub-area in a session interface or other controls related to the input component. For example, display components can include, but are not limited to, list areas, tabs, card components, display panels, etc.

[0059] In other words, the electronic device 110 can distribute identifiers used to indicate resources in different display areas or components based on resource type, thereby achieving differentiated presentation of different types of resources. For example, resource types may include documents, images, audio, video, or other types. The electronic device 110 can present corresponding identifiers in different display components based on resource type, allowing users to select between different types of resources.

[0060] As an example, refer to Figure 2B and Figure 2D The electronic device 110 can provide a type selection control 220. The type selection control 220 is used to select the type of resource identifier presented in the input component 210. Users can switch between identifiers corresponding to different resource types by operating the type selection control 220. By filtering resources based on the session scenario and limiting the range of selectable resources, the electronic device reduces the amount of data that needs to be processed during resource identifier presentation and subsequent processing, thereby reducing system computational overhead and resource retrieval costs.

[0061] In some cases, the segmentation of identifiers presented in different display components can be based on other attributes of the resource. For example, it can be based on the resource's origin, access permissions, or associated objects. For instance, associated objects can include participants in a session, allowing users to filter resources related to them based on the participants.

[0062] In some cases, at least one identifier has a presentation order, which may be related to the degree of matching between at least one resource and the scenario. For example, electronic device 110 may sort at least one identifier based on the relevance between the resource and the current session scenario, thereby prioritizing the display of identifiers corresponding to resources that have a higher degree of matching with the current scenario.

[0063] In some cases, the presentation order of at least one identifier may be related to the historical access time or historical access frequency of at least one resource. For example, historical usage may include the historical access time, historical access frequency, or historical number of times a resource has been selected. Electronic device 110 may sort at least one identifier based on historical usage, so that resources recently accessed or frequently used by the user are presented first.

[0064] In some scenarios, in response to a session being associated with a second scenario, electronic device 110 may present at least one second identifier, which indicates at least one second resource. The at least one second resource may be associated with the second scenario. In other words, if the scenario of the session changes, electronic device 110 may adjust the range and presentation of presented resources accordingly, ensuring that the resources available for subsequent selection remain consistent with the current session requirements.

[0065] As an example, the conversation context can be dynamically updated as the conversation progresses. For instance, as conversation content continues to be input or the participants in the conversation change, the intelligent system can update its judgment of the context in real time, so that the presented resource identifiers always match the context of the current conversation.

[0066] In some situations, scene switching can be triggered by multiple factors. For example, receiving a second instruction might trigger a session to switch to a second scene. Alternatively, a change in session attributes might trigger a session to switch to a second scene. Session attributes can include at least one of the session's subject or the session's participants.

[0067] As an example, if the topic of a conversation changes from topic one to topic two, electronic device 110 can trigger the conversation to be associated with the new scenario based on the topic change. Alternatively, if the participants in a conversation change (e.g., a new participant is added or a participant leaves), electronic device 110 can also trigger the conversation to be associated with the new scenario based on the changes in the permissions or interaction relationships of the participants. Through these methods, resource adaptive presentation based on dynamic changes in the conversation can be achieved, enabling the resource selection mechanism to adjust in real time according to changes in the conversation scenario, thereby further enhancing the system's adaptability and intelligence in complex conversation environments.

[0068] In some scenarios, where at least two users are involved in a conversation, the range of resources available for reference can be further expanded compared to scenarios where only the user is interacting with an intelligent system. In other words, during a conversation between users, not only external resources can be utilized, but also various resources that naturally arise during the conversation or are associated with it, thus providing a richer source of resources for reference.

[0069] In some scenarios, the first resource can include resources already sent during the session. For example, during a session, participants may send files, images, or other forms of data content. These resources can be retained as part of the session context. In subsequent interactions, users can reuse the sent resources without having to re-upload or re-provide them, thus improving interaction efficiency.

[0070] In some cases, the first resource may include resources in a first resource set associated with a session. For example, the first resource set may include resources in a cache corresponding to the session (such as a set of files in a group space, a shared directory, etc.).

[0071] In some cases, the first resource may include resources that the participating parties have access to. For example, different participating parties may have different resource access permissions, and the electronic device 110 may determine the resources that can be referenced based on the participants' permission scope, thereby achieving resource sharing and reference while ensuring resource security.

[0072] In some cases, the first resource may include a data source accessible to the intelligent system or a resource generated by the intelligent system. For example, the first resource may include resources generated by the intelligent system, or resources in a second resource set associated with the intelligent system. For example, the second resource set may include resources in a data source or knowledge base accessed by the intelligent system. Resources may also be referenced to support the intelligent system in processing richer data, provided that permission or access control requirements are met.

[0073] In some cases, the first instruction may include text content. For example, the text content is a message the user wants to send in the session. In other words, resource matching and presentation can be triggered by entering natural language content into the input component, without explicitly performing a specific resource referencing operation. The electronic device 110 can identify resource-related information based on the text content and present at least one identifier accordingly, thereby indicating at least one resource related to the text content. In this way, resource retrieval capabilities can be integrated with the user's natural input process, allowing the user to discover and select relevant resources without additional operations, thereby improving the naturalness and convenience of the interaction.

[0074] In some cases, during the process of triggering the presentation of at least one identifier, the electronic device 110 may receive at least one keyword via an input component. The at least one keyword may be text content input by a user. Further, the electronic device 110 may present an updated at least one identifier. The updated at least one identifier corresponds to at least one resource obtained based on a search based on the at least one keyword.

[0075] As an example, refer to Figure 2F The electronic device 110 can receive the keyword "weekend" via the input component 210. Based on this keyword, the electronic device 110 can match or search within a set of relevant resources and present at least one identifier 265 of at least one resource related to "weekend". For example, it can search for at least one document resource whose content or title may include the keyword. By dynamically searching and updating resource identifiers based on input content, the presented resources can continuously match the semantics of the user's current input, thereby improving the accuracy and efficiency of resource selection.

[0076] In some cases, electronic device 110 may receive the first input via an input component. In other words, the natural language content entered by the user during a conversation may refer to a specific resource, such as by entering the name, title, or descriptive information related to the resource. Electronic device 110 can identify a first resource that matches the first input based on the first input, thereby determining the association between the first input and the first resource.

[0077] Furthermore, upon determining that the first input matches the first resource, the electronic device 110 can replace the first input in the input component with a first element. The first element is used to represent a reference to the first resource in a structured form, thereby enabling the resource to participate in subsequent processing in an explicit manner. Through this method, the conversion from natural text to structured reference identifiers can be achieved, allowing users to invoke resources without explicitly performing resource reference operations, thus improving interaction efficiency and reducing operational complexity.

[0078] In some cases, the aforementioned replacement process can be completed through prompts and guidance. For example, electronic device 110 can present a prompt indicating that the first input matches the first resource. Furthermore, in response to the prompt, electronic device 110 can replace the first input with the first element. By introducing a prompt mechanism, automation capabilities can be guaranteed while retaining user control over the replacement process, thereby improving the controllability and understandability of the interaction.

[0079] As an example, refer to Figure 2G The electronic device 110 can receive a first input via the input component 210 and determine the matching relationship between the first input and a first resource. For example, the user inputs content that is the same as or similar to the resource title. In this case, the electronic device 110 can present a prompt message 271 to indicate to the user that the current input can be associated with the corresponding resource. The specific presentation form of the prompt message is not limited; for example, it can be indicated by highlighting relevant text, adding an underline, or using other visual methods. By triggering the prompt message, the first input can be converted into a first element, thereby enabling flexible introduction of resource references.

[0080] In some cases, in response to an operation on the first element, the electronic device 110 can display a preview of the first resource, for example, display at least a portion of the content of the first resource. In other words, if the input content already contains a reference to the resource, the relevant content of the resource can be viewed directly by triggering an operation on the first element (e.g., clicking, hovering, or other forms of triggering) without leaving the current session interface.

[0081] In some scenarios, electronic device 110 can send a first message during a session, which triggers an action by the intelligent system. The first message may include input content, including a first element indicating a first resource, enabling the intelligent system to perform an action related to that resource based on the first resource indicated by the first element. The action can refer to a data processing operation or an interactive operation performed by the intelligent system. In other words, in a user chat session, by introducing a reference to a resource in the message, the message can not only be used for information exchange between users but also serve as a carrier to trigger a processing action by the intelligent system.

[0082] In some cases, electronic device 110 can combine the first element with other information from the input content to generate a processing request for the intelligent system. For example, electronic device 110 can construct prompt information to drive the intelligent system to perform actions related to the first resource based on the resource content, resource identification information, or resource address information indicated by the first element, and the text information input by the user. The prompt information may include reference information to the first resource and processing instructions for the first resource.

[0083] In some scenarios, the actions performed by the intelligent system can be associated with at least one user, who is a participant in the conversation. Unlike actions performed solely based on resource content, the electronic device 110 can perform correlation analysis between resource information and participant information within a conversational context to determine the target of the action.

[0084] In some cases, an action may include an interactive operation or task operation related to at least one user. For example, an action may include, based on a first resource, sending a message to at least one user, generating response content for at least one user, creating a task or schedule for at least one user, or generating a processing result based on content in the first resource related to at least one user.

[0085] In some cases, at least one user includes a first user. The first user can be indicated by the input received by the electronic device 110. For example, during the input process, the user can explicitly specify a participant, thereby making the first user the target or associated object of subsequent processing.

[0086] In some cases, at least one user includes a second user. The second user is associated with the first resource. For example, electronic device 110 can determine the second user based on the association between the first resource and the session participants. Exemplarily, the association may include creation, editing, commenting, or sharing relationships between the user and the resource, thereby enabling the system to automatically identify the participants associated with the resource without explicitly specifying the user.

[0087] In some scenarios, the electronic device 110 can perform actions based on at least a portion of the first message and the first resource, wherein the at least portion can be a part of the first resource related to at least one user. For example, if the first resource is a document, the at least portion may include edited content, comments, or annotations related to at least one user. The intelligent system can perform corresponding processing operations based on these resource contents related to a specific user, such as summarizing a user's modifications, extracting key points of a user's comments, or generating subsequent tasks based on the user's related content.

[0088] As an example, refer to Figure 2H In the session interface 200H, the electronic device 110 can send a first message 281 based on the input content received via the input component 210. The first message 281 may include a first element (e.g., a reference to a document) and an instruction to at least one user (e.g., user B).

[0089] The intelligent system can determine a target resource (e.g., a document) based on a first message, and further determine resource content related to at least one user (user B). If the first resource is a document, the electronic device 110 and / or the intelligent system can extract portions of the document related to user B, such as user B's comments, editing history, or annotation information, thereby obtaining at least a portion of the first resource.

[0090] Furthermore, the intelligent system can perform corresponding processing operations based on at least a portion of the first message and the first resource. For example, in Figure 2H In the scenario shown, the intelligent system can summarize or extract relevant content from user B in a document, thereby generating a summary result for user B, and returning the corresponding processing result in the session (e.g., message 282).

[0091] The above approach enables joint driving based on resource content and session participants, allowing intelligent systems to perform more targeted operations for specific users, thereby improving the intelligence of interaction and the accuracy of task execution.

[0092] In summary, by introducing a first element to indicate resource references during the session input process, users can directly associate target resources with their input and complete resource invocation in a concise and intuitive way. This achieves rapid resource identification and referencing, reduces user operation costs, and improves interaction efficiency. By automatically determining the target of actions based on the relationship between resources and users, the additional information required for users to explicitly input user identifiers is reduced, thereby shortening the length of input content and reducing the overhead of parsing redundant information in subsequent processing.

[0093] Furthermore, by dynamically determining and presenting resource types relevant to the current scenario based on the session context, resource selection remains consistent with the session context, thereby reducing interference from irrelevant resources and improving the accuracy of resource matching. In this way, the resource selection process can be contextualized and adaptive, enhancing the system's ability to understand user intent.

[0094] Furthermore, by integrating resource reference information into conversation messages and automatically constructing processing requests to drive the intelligent system based on user input, messages can trigger the intelligent system to execute resource-related actions. This not only enables efficient resource reuse but also supports resource-based analysis, summarization, and generation, thus achieving integrated resource retrieval and intelligent processing within user chat conversations, enhancing the overall intelligence and practical value of the system.

[0095] Figure 3 A flowchart of an example process 300 for a session is shown, based on some scenarios. Process 300 can be implemented at electronic device 110. See below for reference. Figure 1 To describe process 300.

[0096] like Figure 3 As shown, in box 310, electronic device 110 presents input components in a first interface. The first interface is used to display a session, in which at least two users participate.

[0097] In box 320, electronic device 110 receives input content via an input component, the input content including a first element indicating a reference to a first resource.

[0098] In box 330, electronic device 110 sends a first message in a session. The first message is used to trigger the intelligent system to perform an action. The first message includes input content, and the action is related to a first resource.

[0099] In some cases, receiving input includes: in response to a first instruction, presenting at least one identifier, the at least one identifier corresponding to at least one resource, the type of the at least one resource being related to the scenario of the session; and in response to the selection of the first identifier, presenting a first element in the input component, the first identifier corresponding to the first resource.

[0100] In some cases, presenting at least one identifier includes presenting identifiers corresponding to different resource types in different display components.

[0101] In some cases, the scenario is associated with at least one of the following: the type of conversation, the topic of the conversation, or the interaction mode of the conversation.

[0102] In some cases, the scenario is a first scenario, and presenting at least one identifier further includes: in response to a session being associated with a second scenario, presenting at least one second identifier, the at least one second identifier indicating at least one second resource, the at least one second resource being associated with the second scenario.

[0103] In some cases, process 300 may also include: in response to receiving a second instruction, triggering a session association to a second scenario.

[0104] In some cases, process 300 also includes triggering a connection of the session to a second scenario in response to a change in a session attribute, said attribute including at least one of the following: the topic of the session or the participants in the session.

[0105] In some cases, the first resource includes at least one of the following: resources sent in the session, resources in the first resource set, resources associated with the first resource set, or resources that the participants have access to.

[0106] In some cases, the first resource includes at least one of the following: resources generated by the intelligent system, or resources in a second set of resources associated with the intelligent system.

[0107] In some cases, receiving input includes: receiving a first input via an input component; and replacing the first input in the input component with a first element.

[0108] In some cases, replacing a first input in an input component with a first element includes: presenting a prompt message indicating that the first input matches a first resource; and replacing the first input with the first element in response to triggering the prompt message.

[0109] In some cases, process 300 also includes: in response to an operation on the first element, presenting a preview of the first resource.

[0110] In some cases, the action is associated with at least one user, who is a participant in the session.

[0111] In some cases, at least one user includes: a first user, indicated by the input content; or a second user, associated with the first resource.

[0112] In some cases, performing an action includes: performing an action based on at least a portion of a first message and a first resource, the at least portion of which includes a portion of the first resource related to at least one user.

[0113] In some cases, at least one identifier has a presentation order, which is related to the degree of matching between at least one resource and the scene.

[0114] In some cases, at least one identifier has a presentation order, which is related to the historical access time or historical access frequency of at least one resource.

[0115] In some cases, the first instruction includes predefined characters and / or text content, and at least one resource matches the text content.

[0116] In some cases, process 300 further includes: receiving at least one keyword via an input component; and presenting at least one updated identifier, the updated identifier corresponding to at least one resource obtained based on the search based on at least one keyword.

[0117] In some cases, process 300 also includes: using an intelligent system to determine the scenario based on the context information of the session.

[0118] A corresponding apparatus for implementing the above methods or processes is also provided.

[0119] Figure 4 A schematic structural block diagram of an example device 400 for use in a session is shown, depending on several scenarios. Device 400 may be implemented as or included in electronic device 110. The various modules / components in device 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0120] like Figure 4 As shown, the device 400 includes: a presentation module 410 configured to present an input component in a first interface for displaying a session, the session involving at least two users; a receiving module 420 configured to receive input content via the input component, the input content including a first element indicating a reference to a first resource; and a sending module 430 configured to send a first message in the session, the first message for triggering an action performed by the intelligent system, the first message including input content and the action being related to the first resource.

[0121] In some cases, the receiving module 420 is further configured to: in response to a first instruction, present at least one identifier, the at least one identifier corresponding to at least one resource, the type of the at least one resource being related to the scenario of the session; and in response to the selection of the first identifier, present a first element in the input component, the first identifier corresponding to the first resource.

[0122] In some cases, the receiving module 420 is further configured to present identifiers corresponding to different resource types in different display components.

[0123] In some cases, the scenario is associated with at least one of the following: the type of conversation, the topic of the conversation, or the interaction mode of the conversation.

[0124] In some cases, the scenario is a first scenario, and the receiving module 420 is further configured to: in response to a session being associated with a second scenario, present at least one second identifier, the at least one second identifier indicating at least one second resource, the at least one second resource being associated with the second scenario.

[0125] In some cases, the device 400 also includes a scene switching module configured to trigger a session association to a second scene in response to receiving a second instruction.

[0126] In some cases, the scene switching module is further configured to: trigger the association of the session with a second scene in response to a change in the attributes of the session, wherein the attributes include at least one of the following: the topic of the session or the participants in the session.

[0127] In some cases, the first resource includes at least one of the following: resources sent in the session, resources in the first resource set, resources associated with the first resource set, or resources that the participants have access to.

[0128] In some cases, the first resource includes at least one of the following: resources generated by the intelligent system, or resources in a second set of resources associated with the intelligent system.

[0129] In some cases, the receiving module 420 is further configured to: receive a first input via an input component; and replace the first input in the input component with a first element.

[0130] In some cases, the receiving module 420 is further configured to: present a prompt message indicating that the first input matches the first resource; and, in response to the triggering of the prompt message, replace the first input with the first element.

[0131] In some cases, the presentation module 410 is further configured to: present a preview of the first resource in response to an operation on the first element.

[0132] In some cases, the action is associated with at least one user, who is a participant in the session.

[0133] In some cases, at least one user includes: a first user, indicated by the input content; or a second user, associated with the first resource.

[0134] In some cases, the apparatus 400 further includes an execution module configured to perform an action based on at least a portion of the first message and the first resource, the at least portion of which includes the portion of the first resource relating to at least one user.

[0135] In some cases, at least one identifier has a presentation order, which is related to the degree of matching between at least one resource and the scene.

[0136] In some cases, at least one identifier has a presentation order, which is related to the historical access time or historical access frequency of at least one resource.

[0137] In some cases, the first instruction includes predefined characters and / or text content, and at least one resource matches the text content.

[0138] In some cases, the receiving module 420 is further configured to: receive at least one keyword via an input component; and present at least one updated identifier corresponding to at least one resource obtained based on the search for at least one keyword.

[0139] In some cases, the receiving module 420 is further configured to: use an intelligent system to determine the scenario based on the context information of the session.

[0140] The modules included in device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some cases, one or more modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 400 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0141] Figure 5 A block diagram of an electronic device 500 in which multiple illustrative scenarios can be implemented is shown. It should be understood that... Figure 5 The electronic device 500 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 5 The illustrated electronic device 500 can be used to implement the electronic device 110 or device 400 discussed above.

[0142] like Figure 5 As shown, electronic device 500 is in the form of a general-purpose electronic device. Components of electronic device 500 may include, but are not limited to, one or more processing units or processors 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. Processor 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 520. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 500.

[0143] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0144] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 5 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various examples.

[0145] The communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 500 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0146] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0147] A computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. A computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0148] The flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products referred to herein describe various aspects. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0149] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0150] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0151] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products under various scenarios. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0152] Various examples have been described above. The foregoing descriptions are exemplary and not exhaustive, nor are they 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 chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for use in a session, comprising: The first interface presents an input component and is used to display a session, in which at least two users participate. Input content is received via the input component, the input content including a first element, the first element indicating a reference to a first resource; as well as In the session, a first message is sent, which triggers the intelligent system to perform an action. The first message includes the input content, and the action is related to the first resource.

2. The method according to claim 1, wherein receiving input content includes: In response to a first instruction, at least one identifier is presented, the at least one identifier corresponding to at least one resource, the type of the at least one resource being related to the scenario of the session; as well as In response to the selection of a first identifier, the first element is presented in the input component, the first identifier corresponding to the first resource.

3. The method of claim 2, wherein presenting at least one identifier comprises: Different display components present identifiers corresponding to different resource types.

4. The method of claim 2, wherein the scenario is associated with at least one of the following: The type of the session, The topic of the session, or The interaction mode of the session.

5. The method of claim 2, wherein the scenario is a first scenario, and the presentation of the at least one identifier further includes: In response to the session being associated with a second scenario, at least one second identifier is presented, the at least one second identifier indicating at least one second resource associated with the second scenario.

6. The method according to claim 5, further comprising: In response to receiving the second instruction, the session is associated with the second scenario.

7. The method according to claim 5, further comprising: In response to a change in the attributes of the session, the session is triggered to be associated with the second scenario, wherein the attributes include at least one of the following: the topic of the session, or the participants in the session.

8. The method of claim 1, wherein the first resource comprises at least one of the following: Resources that have been sent in the session, Resources in a resource set, which is associated with the session. The participating parties have access to the resources.

9. The method according to claim 1, wherein receiving input content includes: The first input is received via the input component; as well as Replace the first input in the input component with the first element.

10. The method of claim 9, wherein replacing the first input in the input component with the first element comprises: A prompt message is displayed, indicating that the first input matches the first resource; as well as In response to the triggering of the prompt message, the first input is replaced with the first element.

11. The method according to claim 1, further comprising: In response to an operation on the first element, a preview of the first resource is displayed.

12. The method of claim 1, wherein the action is associated with at least one user, the at least one user being a participant in the session.

13. The method of claim 11, wherein the at least one user comprises: The first user, as indicated by the input content; or The second user is associated with the first resource.

14. The method of claim 11, wherein performing the action comprises: The action is performed based on at least a portion of the first message and the first resource, the at least a portion including the portion of the first resource related to the at least one user.

15. An apparatus for conversation, comprising: The presentation module is configured to present an input component in a first interface, the first interface being used to display a session in which at least two users participate. A receiving module is configured to receive input content via the input component, the input content including a first element indicating a reference to a first resource; as well as The sending module is configured to send a first message in the session, the first message being used to trigger the intelligent system to perform an action, the first message including the input content, and the action being related to the first resource.

16. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processor.

17. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 14.

18. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 14.

Images