Method, device, equipment and program product for interface interaction

Abstract

Provided are a method, device, equipment and program product for interface interaction. The method comprises: receiving a first input through an input component, the first input indicating that a smart system performs a first task; presenting at least one interaction item on the input component, the at least one interaction item being used to receive information for performing the first task; and receiving a second input through the at least one interaction item, the second input being used to provide first information, the first information being used to perform the first task. In this way, the efficiency of human-computer interaction can be effectively improved.

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 program products for user interface interaction. Background Technology

[0002] With the development of computer technology and continuous breakthroughs in the field of artificial intelligence, various models have emerged. Users can communicate continuously and fluently with these models through conversational text, completing various tasks such as information inquiry, logical thinking, and content interpretation without using complex commands. Optimizing the efficiency of user-model interaction has become a pressing issue. Summary of the Invention

[0003] In a first aspect, a method for interface interaction is provided. The method includes: receiving a first input via an input component, the first input instructing an intelligent system to perform a first task; presenting at least one interactive item on the input component, the at least one interactive item being used to receive information for performing the first task; and receiving a second input via the at least one interactive item, the second input being used to provide first information for performing the first task.

[0004] In a second aspect, an apparatus for interface interaction is provided. The apparatus includes: a first receiving module configured to receive a first input via an input component, the first input instructing an intelligent system to perform a first task; a first presenting module configured to present at least one interactive item on the input component, the at least one interactive item being used to receive information for performing the first task; and a second receiving module configured to receive a second input via the at least one interactive item, the second input being used to provide first information for performing the first task.

[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 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.

[0007] Through the above approach, users can supplement task information using interactive items within the conversation interface, reducing scattered plain text Q&A and thus effectively improving human-computer interaction efficiency. Electronic devices can directly associate interactive items with task parameter fields, reducing repetitive text parsing. This can reduce the number of edge-cloud interaction rounds, the amount of context data, and task response latency.

[0008] 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

[0009] 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; Figures 3A to 3C Example interfaces for some scenarios are shown; Figures 4A to 4C Example interfaces for some scenarios are shown; Figure 5 The flowcharts show example processes of interface interactions in some scenarios; Figure 6 Schematic block diagrams of example devices for interface interaction in some scenarios are shown; and Figure 7 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0010] The examples in this document 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.

[0011] 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.

[0012] 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.

[0013] The examples in this article may involve users' historical interaction data, the acquisition of historical interaction data, and / or the use of such data. All of these aspects comply with relevant laws, regulations, and provisions. In the examples presented here, all collection, acquisition, processing, manipulation, forwarding, and use of historical interaction data are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any historical interaction data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. 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.

[0014] As used in this article, the term "intelligent system" can refer to a system capable of autonomous control based on machine learning models. An intelligent system is, for example, a virtual object or physical entity that can make decisions and autonomously execute 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 cases, examples of intelligent systems may include, but are not limited to: intelligent agents, robot programs, chatbots, digital avatars, intelligent customer service, digital assistants, etc. Alternatively, an intelligent system can also be an intelligent role implemented based on a machine learning model. An "intelligent system" can process user requests based on generative models (e.g., language models, multimodal models) to perform specified types of tasks. In some cases, an intelligent system may also be associated with a virtual account, which may have a corresponding avatar or nickname.

[0015] As used in this document, the term "first task" refers to a computer processing task triggered by a first input and executed by an intelligent system. A first task may include content generation, information retrieval, object processing, communication processing, or other tasks that can be performed by electronic devices and servers.

[0016] As used in this document, the term "input component" refers to an interface component that receives input or performs tasks within the interface. Input components may include a session input area, and an interactive panel or overlay associated with that session input area. The interactive panel or overlay may be presented in a non-modal manner, allowing the user to view the session context while providing information.

[0017] As used in this document, the term "interactive item" refers to a UI element presented in an input component that displays content and / or receives user input. Interactive items may include, but are not limited to, selections, input boxes, file cards, user cards, image cards, or media input fields, and may receive input in a single selection, multiple selection, free input, or a combination thereof.

[0018] As used in this paper, the term "candidate information" refers to information that can be selected by the user and used to perform the primary task. Candidate information can be determined by the intelligent system based on the initial input, the session context, and available resources.

[0019] As used in this article, the term "content type" refers to type information used to characterize the common data category or task meaning of candidate content. Content types can include text, images, files, dates, numeric values, or task parameter types.

[0020] As used in this article, the term "first input" refers to the initial input used to instruct the intelligent system to perform a first task. The first input may include text, speech, media content, or a structured task request derived from it.

[0021] As used in this article, the term "second input" refers to supplementary input to the task provided through at least one interactive element. Second input may include candidate selections, free text, media content, or any combination thereof.

[0022] The term "third input" as used in this article refers to supplementary task input provided for another set of interactions. The third input may correspond to a different dimension of task information than the second input.

[0023] As used in this document, the term "first information" refers to information provided by the second input and used to perform the first task. First information may include task parameters, object identifiers, content descriptions, or candidate content identifiers.

[0024] The terms "first group of interactive items," "second group of interactive items," and "third group of interactive items" used in this article refer to the sets of interactive items presented in the input component. Different groups may correspond to different questions, different sets of candidate content, or different interface states.

[0025] The term "first text" as used in this article refers to the question text used to describe the content type of the candidate content or the information to be supplemented. The first text may be presented together with the corresponding interactive item group.

[0026] As used in this article, the term "first message" refers to a conversational message that includes at least one set of question and answer information. The first message may take the form of a structured card, a structured data block, or other format that maintains the correspondence between questions and answers.

[0027] As used in this document, the term "content component" refers to a UI component used to present content to be confirmed and obtain permission information. A content component may include text describing the action to be performed and one or more interactive items for receiving permission input.

[0028] As used in this document, "media content" refers to non-plain text content received by the input component. Media content may include images, audio, video, combinations of text and images, or corresponding resource identifiers.

[0029] As used in this article, a “session” refers to a set of messages and interaction states organized between a user and an intelligent system according to time or task relationships. A session can include user messages, intelligent system responses, structured messages, and input component states.

[0030] As used in this article, the term "first interface" refers to the interface used to present the session and host the input components. The first interface can be a session page within an application or any other interface that has a session area and an input area.

[0031] As mentioned above, with the development of computer technology and continuous breakthroughs in the field of artificial intelligence, various models have emerged. Users can communicate continuously and fluently with models through conversational text, completing various tasks such as information consultation, logical thinking, and content interpretation without using complex commands. How to optimize the interaction efficiency between users and models has become an urgent problem to be solved.

[0032] To address this, a scheme for interface interaction is proposed, comprising: receiving a first input via an input component, the first input instructing an intelligent system to perform a first task; presenting at least one interactive item via the input component, the at least one interactive item being used to receive information for performing the first task; and receiving a second input via the at least one interactive item, the second input being used to provide first information, the first information being used to perform the first task.

[0033] Through the above approach, users can supplement task information using interactive items within the conversation interface, reducing scattered plain text Q&A and thus effectively improving human-computer interaction efficiency. Electronic devices can directly associate interactive items with task parameter fields, reducing repetitive text parsing. This can reduce the number of edge-cloud interaction rounds, the amount of context data, and task response latency.

[0034] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0035] Example Environment Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, the example environment 100 may include an electronic device 110, an application 120, a server 130, a user 140, and an interface 150.

[0036] Electronic device 110 can run application 120 that supports user interface interaction. Application 120 can provide conversational functions, input components, and interactive items. User 140 can interact with application 120 through electronic device 110 and provide first input, second input, third input, or other operations.

[0037] Electronic device 110 can present interface 150 through application 120. Interface 150 can support conversations between the user and the intelligent system. Figures 2A to 4C The input components, interactive items, and conversation messages shown can be displayed in interface 150.

[0038] Electronic device 110 can communicate with server 130. Server 130 can provide the intelligent system with inference, task execution, and data access capabilities. Electronic device 110 can also provide at least some of the capabilities of the intelligent system locally.

[0039] 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, virtual reality (VR) / augmented reality (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 thereof, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 may also support any type of user-facing interface (such as "wearable" circuitry).

[0040] Server 130 can be a single 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 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 that support user interface interaction in electronic devices 110.

[0041] 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 (WiFi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0042] 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.

[0043] The following description of the example will continue with reference to the accompanying drawings.

[0044] Example Interaction The examples described herein can be implemented on electronic device 110. It should be noted that the operations described relative to electronic device 110 can be performed by a related application 120 running on electronic device 110. The interface described relative to electronic device 110 can be provided by application 120; for example, electronic device 110 presents the corresponding interface by running application 120. Furthermore, some operations described relative to electronic device 110 may require the assistance of server 130 to complete.

[0045] In one scenario, electronic device 110 can independently perform task processing for the intelligent system. Electronic device 110 locally parses the first input and generates an interaction configuration for the input component. Electronic device 110 can also locally execute a first task based on first information obtained through the interaction item.

[0046] In one scenario, server 130 can handle task processing for the intelligent system. Electronic device 110 sends a first input to server 130. Server 130 determines the information to be supplemented and returns an interaction configuration to electronic device 110. After obtaining the first information, electronic device 110 sends it to server 130, and server 130 executes the first task accordingly.

[0047] In one scenario, electronic device 110 and server 130 can collaborate to handle tasks within the intelligent system. Electronic device 110 can perform input preprocessing and interface state management locally. Server 130 can generate candidate information or execute tasks. Both can communicate to exchange task requests, interactive configurations, initial information, and task results.

[0048] Figures 2A to 2H This illustrates multiple interface states during the task information clarification process, depending on various scenarios. The following explanation uses the visual content planning task for a target activity as an example. This task is only used to illustrate the collaborative relationship between input components and clarification interactions. The first task could also be content generation, data processing, itinerary planning, or other tasks performed by an intelligent system.

[0049] In some cases, electronic device 110 receives a first input via an input component, which instructs the intelligent system to perform a first task. For example, such as... Figure 2A As shown, Figure 2A An interface 200A is shown that receives a first input via an input component. On the interface 200A, the electronic device 110 presents a user message 202 and an input component 204. The interface 200A also displays a conversation between the user and the intelligent system. The user can enter a task request in the input component 204, which serves as the first input and instructs the intelligent system to perform a first task.

[0050] After receiving the first input, electronic device 110 can present the first input as user message 202. Electronic device 110 can also convert the first input into a task request. When server 130 is required to provide intelligent system capabilities, electronic device 110 can send the task request to server 130.

[0051] In this way, electronic device 110 transmits task requests along the existing session channel and reuses the already loaded session context. This reduces page loading and session reconstruction, lowers client rendering overhead, and reduces end-to-cloud communication latency.

[0052] After receiving the first input, the intelligent system can analyze the first input and the current session context. The intelligent system can determine the information needed to perform the first task but not yet provided. The intelligent system can also determine the appropriate interaction type for each piece of information. Interaction types can include single-choice, multiple-choice, free text input, and media input. Interaction types can also include combinations of multiple questions.

[0053] Server 130 can return problem configuration data to electronic device 110. The problem configuration data may include problem text, candidate content, content type, and interaction mode. Based on the problem configuration data, electronic device 110 switches input component 204 to... Figure 2B The unfolded state shown.

[0054] In some cases, the electronic device 110 may present at least one interactive item in the input component. The at least one interactive item is used to receive information for performing a first task. For example, such as... Figure 2B As shown, Figure 2B An interface 200B is shown, in which an input component presents at least one interactive item. On the interface 200B, an electronic device 110 presents a user message 202 corresponding to the first input, an intelligent system response 206, and an expanded input component 204. The intelligent system response 206 prompts the user for additional information to perform the first task.

[0055] Input component 204 can be located at the bottom of interface 200B and can expand upwards from the input area used to receive session input. The expanded input component 204 can be in the form of a non-modal panel or a non-modal overlay, allowing the user to still view the session content while using the input component 204. The expanded height of input component 204 can be dynamically adjusted according to the number of questions, the number of candidate options, or the available area of ​​the interface. The expanded input component 204 can include at least one interactive item. At least one interactive item can present information for performing the first task, and the user can provide relevant information to the intelligent system through at least one interactive item.

[0056] In some scenarios, at least one interactive item includes a first set of interactive items, which displays multiple pieces of content corresponding to multiple candidate information for performing a first task. As an example, such as... Figure 2B As shown, input component 204 includes a first set of interactive items 208 and an input box 210. The first set of interactive items (e.g., interactive item set 208) displays multiple candidate information for performing the first task. In some cases, multiple contents correspond to the same content type, and input component 204 may also present first text (e.g., text 212) to describe that content type. As an example, Figure 2B As shown, the electronic device 110 can present first text (e.g., text 212) in the input component 204. The first text (e.g., text 212) can be referred to as a question. The first text (e.g., text 212) describes a corresponding content type, such as the question asking "What is the wedding venue?". Multiple contents presented in the first set of interactive items (e.g., interactive item set 208) can correspond to the content type described by the first text 212, that is, multiple candidate information can be different candidate answers to the same question.

[0057] Taking venue type as an example, the first text (e.g., text 212) can be used to ask "What is the wedding venue?" Interaction item 208-1 can display candidate information for the first venue type (e.g., urban indoor venues). Interaction item 208-2 can display candidate information for the second venue type (e.g., outdoor natural venues). Interaction item 208-3 can display candidate information for the third venue type (e.g., themed destination venues). Each candidate information can also include a description of the corresponding venue type.

[0058] In some cases, the content types of multiple pieces of content can be obtained based on the first input. For example, such as... Figure 2B As shown, the content types of multiple candidate information can be obtained based on the first input 202. The electronic device 110 or the server 130 can parse the first input 202 and determine that the first task requires supplementary site type information. The intelligent system can then generate the first text 212 and the first set of interactive items (e.g., interactive item set 208).

[0059] The intelligent system can also determine the order of candidate options based on session context, candidate relevance, and task status. Candidate options that better match the current task conditions can be ranked higher. The order of candidate options can also be updated in response to provided task information.

[0060] In this way, users can make selections from a limited range of candidates, thereby effectively improving the efficiency of human-computer interaction. Furthermore, the electronic device 110 renders the first set of interaction items (e.g., interaction item set 208) based on structured configuration data. This reduces the number of irrelevant interaction items rendered and lowers the overhead of candidate information retrieval and sorting.

[0061] In some cases, electronic device 110 can receive a second input via at least one interactive item, the second input being used to provide first information, the first information being used to perform a first task. As an example, such as... Figure 2B As shown, a user can provide a second input through at least one interactive item (e.g., any interactive item in interactive item 208). For example, a user can click on interactive item 208-1 to provide the intelligent system with the first information corresponding to interactive item 208-1 (i.e., the content presented by interactive item 208-1), thereby triggering the intelligent system to perform a first task based on the first information. For example, the intelligent system can plan wedding materials based on the "indoor venue in the city" selected by the user.

[0062] In some cases, the electronic device 110 can receive a second input for selecting a first interactive item, which displays first content, and a first task is performed based on the first content. The first interactive item belongs to a first group of interactive items. As an example, such as... Figure 2B As shown, the user can select interactive item 208-2. In response to this selection, the electronic device 110 determines the content corresponding to interactive item 208-2 as the first content and causes the intelligent system to execute a first task based on the first content. In this way, the user can clarify the task parameters with a single selection operation, reducing ambiguity caused by free text expression, thereby improving the efficiency of human-computer interaction.

[0063] In some scenarios, input box 210 can serve as an appropriate interactive item in at least one interactive item, used to receive supplementary information in addition to the candidate items. Input box 210 can be displayed simultaneously with the first set of interactive items (e.g., interactive item set 208). Users can select only candidate items or use only input box 210. Users can also combine candidate selection and free input into a single second input.

[0064] In this way, users can provide supplementary information while viewing the session context, reducing back-and-forth operations between the clarification interface and the session interface. Electronic device 110 reuses the session data and rendering tree of interface 200B and incrementally renders input component 204 in localized areas. This reduces full page refreshes and redundant data loading, lowering client memory usage and rendering latency.

[0065] In some scenarios, electronic device 110 can present a second set of interactive items in an input component and receive a third input. The third input is used to select a second interactive item, which displays second content. The first task can also be performed based on the second content, and the second interactive item belongs to a second set of interactive items. As an example, such as... Figure 2C As shown, Figure 2C An interface 200C is shown where the input component presents a second set of interactive items. On interface 200C, the input component 204 presents a first set of text (e.g., text 214) and a second set of interactive items (e.g., set of interactive items 216). The first text (e.g., text 214) describes another type of content (i.e., another question, such as "Where is this design primarily used?"). The second set of interactive items (e.g., set of interactive items 216) may include interactive items 216-1 to 216-5, each of which can display content for a different task.

[0066] Electronic device 110 can present a second set of interactive items (e.g., set 208) after presenting a first set of interactive items. Electronic device 110 can receive a user's selection of a second interactive item from the second set (e.g., set 216) as a third input. For example, a user can select one or more interactive items from the second set (e.g., set 216). For instance, selecting interactive items 216-2, 216-4, and 216-5. The selected second interactive item can display second content, and the intelligent system can perform a first task based on the first and second content. For example, after interactive items 216-2, 216-4, and 216-5 are selected, electronic device 110 can provide the intelligent system with the second content corresponding to the aforementioned multiple interactive items to trigger the intelligent system to perform a wedding material planning task based on the first and second content. The first set of interactive items (e.g., interactive item set 208) and the second set of interactive items (e.g., interactive item set 216) can be presented simultaneously, or the second set of interactive items (e.g., interactive item set 216) can be presented after the first interactive item in the first set of interactive items (e.g., interactive item set 208) is selected.

[0067] In this way, users can provide multi-dimensional task information within a single clarification process, reducing operational interruptions caused by fragmented question-and-answer sessions. Electronic device 110 writes the selection results corresponding to each question into the same task parameter set and provides this set uniformly to the intelligent system. This reduces the number of edge-cloud interaction rounds and repeated model restarts, lowering communication overhead and inference latency.

[0068] In some cases, electronic device 110 can receive a first operation via an input component, stopping the presentation of the first set of interactive items and presenting a third set of interactive items in the input component, with the first and third sets of interactive items displaying different content. As an example, such as... Figure 2B and Figure 2C As shown, Figure 2B and Figure 2C This can represent switching between different question pages. The set of interactive items 216 can serve as a third set of interactive items. The first operation can be horizontal swiping, pagination selection, or other question switching operations. In response to the first operation, the electronic device 110 switches the first set of interactive items (e.g., set of interactive items 208) to the third set of interactive items (e.g., set of interactive items 216).

[0069] Electronic device 110 can synchronously update the problem page index and pagination indicator status. Figure 2B and Figure 2C Different question pages before and after the switch can be displayed. In some cases, the set of interactive items 216 can serve as a second set of interactive items presented after selecting any interactive item from the first set of interactive items; alternatively, the set of interactive items 216 can also serve as a third set of interactive items that replaces the first set of interactive items (e.g., the set of interactive items 208) in response to the question switching operation.

[0070] In this way, multiple questions can be presented page by page within a limited input area, eliminating the need for users to deal with a large number of interactive items simultaneously. The electronic device 110 can render only the interactive items corresponding to the current question page and save the configuration data and selected states of other question pages. This reduces the number of concurrent interface nodes, lowering peak client memory usage and interface refresh overhead.

[0071] In some scenarios, the first set of interactive items includes a third interactive item. The electronic device 110 can receive a second operation via an input component, which replaces the third interactive item with a fourth interactive item. The electronic device 110 can stop presenting the third interactive item and present the fourth interactive item in the input component. As an example, the second operation could be a click on any appropriate control in the first interface. Such a control could, for example, trigger the intelligent system to provide a new fourth interactive item. After receiving the second operation, the electronic device 110 can replace the third interactive item with the fourth interactive item. For example, the content presented by the third interactive item might be "natural outdoor venue," and the first text corresponding to the third interactive item (i.e., the question corresponding to the third interactive item) might be "What is a wedding venue?" After receiving the second operation, the electronic device 110 can trigger the intelligent system to generate a fourth interactive item based on the first text. The content presented in the fourth interactive item could correspond to "What is a wedding venue?", for example, the content presented in the fourth interactive item could be "palace solemn venue." After the fourth interactive item is generated, the electronic device 110 can replace the third interactive item with the fourth interactive item to present the option corresponding to "palace solemn venue."

[0072] Multiple questions may or may not have dependencies on each other. An intelligent system can generate candidates for the next question based on the answer to the previous question. The intelligent system can also use the previous answer to adjust the order of candidates in the next question. The objects determined by the previous question can be used to limit the scope of candidates for the next question.

[0073] Users can submit their completed question set. Processing the question set can include answering questions, skipping questions, or leaving questions blank. Electronic device 110 can determine necessary and optional questions based on the question configuration and generate structured answer data after the submission conditions are met.

[0074] In this way, the subsequent question can narrow down the candidate range using the already determined task parameters, allowing users to locate the target content more quickly. The intelligent system writes the previous answer into the task status and retrieves the subsequent candidate set based on the updated task status. This reduces the candidate retrieval space and unnecessary sorting calculations, lowering the query load on server 130.

[0075] In some cases, the electronic device 110 may present a fifth interactive item in an input component, the fifth interactive item including an input box, through which a second input is received. As an example, such as... Figure 2D As shown, Figure 2DAn interface 200D is shown that receives a second input through an input box. On the interface 200D, an input component 204 presents first text (e.g., text 218) and an input box 210 as a fifth interaction item. The first text (e.g., text 218) may prompt the user to complete the name of the target object. The electronic device 110 receives the second input through the input box 210 and treats the second input as first information.

[0076] When suitable options are lacking for the information to be supplemented, the intelligent system allows users to select a free text input mode to supplement additional information. Users can enter names, values, times, or other descriptions in input box 210. Electronic device 110 can provide the input text along with the question type to server 130. Server 130 can then write the input text into the corresponding task parameters based on the question type.

[0077] In this way, users can provide information that cannot be fully expressed by preset candidates, avoiding task interruption due to an incomplete candidate set. Electronic device 110 associates the free text with the corresponding question type and transmits explicit parameter fields to the intelligent system. This reduces the number of requests to regenerate candidates, lowering the amount of interaction between the end and the cloud, and reducing task latency.

[0078] In some cases, electronic device 110 may present a first message, which includes first text and first information. For example, such as... Figure 2E As shown, Figure 2E An interface 200E showing multiple questions and answers in a structured format is displayed. On interface 200E, the electronic device 110 stops displaying the expanded input component 204 and presents a first message 220 in the session flow. The first message 220 may be a structured question-and-answer message, which includes first text and first information obtained through corresponding interactive items, and may also include multiple sets of question texts and answers.

[0079] Electronic device 110 can generate a first message 220 after the user has completed processing the set of questions. If the user skips some questions, the first message 220 can include only the answers already provided. Alternatively, the first message 220 can record an unanswered state. Electronic device 110 writes the first message 220 into the session context and provides the corresponding structured parameters to the intelligent system.

[0080] In this way, users can centrally verify submitted questions and answers, reducing the need for multiple rounds of information searching throughout the session. Electronic device 110 aggregates multiple answers into a structured message and updates the intelligent system's task context with a single data submission. This reduces redundant context transmissions and model parsing, lowering bandwidth usage and inference overhead.

[0081] In some cases, the input field included in the fifth interaction item can be presented together with the first set of interaction items. The second input may include candidate selections received through the first set of interaction items and supplementary text received through the input field. For example, Figure 2F As shown, Figure 2F An interface 200F is shown, which combines candidate selections with supplementary text input. On interface 200F, input component 204 simultaneously presents the selected interactive item 208-2 and input box 210. The user can first select interactive item 208-2, and then supplement it with a more specific description through input box 210. The second input can include both candidate identifiers and free text, and the intelligent system can use the free text as a further constraint on the first content.

[0082] Candidate selections and free input are not mutually exclusive. Alternatively, free text entered by the user can also serve as a standalone answer, replacing previously selected candidate content. The electronic device 110 can determine whether to use a combination mode or a substitution mode based on the interaction state at the time of submission. The electronic device 110 can also prompt the user with currently valid input content before submission.

[0083] In this way, users can both reduce input costs by utilizing candidate options and refine the generality of candidate options through free text. Electronic device 110 encapsulates candidate identifiers and supplementary text within the same parameter object and maintains their association. This reduces subsequent correction messages and repetitive task requests, lowers invalid inference overhead, and minimizes end-to-end cloud communication overhead.

[0084] In some cases, electronic device 110 may present a sixth interactive item in an input component, the sixth interactive item being used to receive a second operation of selecting the sixth interactive item; in response to the second input including media content, electronic device 110 may stop presenting the sixth interactive item. As an example, such as Figure 2G As shown, Figure 2G An interface 200G is shown that provides media content via an input component. On the interface 200G, the input component 204 presents a media input control 222 and media content 224. The media input control 222 can be used to receive operations such as selecting, capturing, or uploading media content. The media content 224 may include images, audio, video, or other multimedia data. The electronic device 110 can use the media content 224 as part of a second input.

[0085] Electronic device 110 can first obtain the local address or resource identifier of media content 224. Electronic device 110 can also generate a thumbnail of media content 224 and display the thumbnail in input component 204. When server 130 needs to process media content 224, electronic device 110 can upload media data or accessible resource identifiers. The intelligent system can extract content features from media content 224 and use the extraction results to perform the first task.

[0086] In some cases, electronic device 110 may present a sixth interactive item before media content 224 is added to input component 204. The sixth interactive item may be multiple options for the user to select the appropriate content. In response to the second input including media content 224, electronic device 110 may stop presenting the sixth interactive item and present media content 224 or a thumbnail thereof at the appropriate location.

[0087] The sixth interactive item can be hidden or replaced by media content 224. Alternatively, media input control 222 can continue to be displayed after media content 224 is added, so that the user can replace or supplement the media content.

[0088] In this way, users can use media content to express task information that is difficult to describe accurately in text, and directly confirm the added media content. Electronic device 110 associates media data or resource identifiers with the corresponding question and updates the display status of input component 204 after the media content is added. This avoids repeatedly presenting invalid interactive items, reducing the number of interface nodes and the transmission overhead caused by repeated media submissions.

[0089] In some cases, the multiple contents displayed in the first set of interactive items may include image content, and these multiple image contents correspond to multiple candidate information for performing the first task. As an example, such as... Figure 2H As shown, Figure 2H An interface 200H is shown, displaying candidate content in image form. On interface 200H, input component 204 presents question text and multiple image interaction items. Image interaction item 226-1 displays a first visual style, image interaction item 226-2 displays a second visual style, and image interaction item 226-3 displays a third visual style. Multiple image interaction items correspond to the same content type and each carries different candidate information.

[0090] Candidate content is not limited to text. Candidate content can also be images, combinations of text and images, or document cards. Additionally, candidate content can be a visual representation of a user card or other media object. The intelligent system can determine the type of candidate content based on the first input. The electronic device 110 selects the appropriate interactive item template based on the candidate content type and populates the template with the candidate content.

[0091] In this way, users can directly compare candidate content requiring visual judgment, reducing the need to convert visual features into textual descriptions. Electronic device 110 receives image candidate identifiers and maps them to corresponding task parameters. This reduces the need for repeated uploading of media content and text feature parsing, lowering the amount of data transmitted and the computational load on the model.

[0092] In some scenarios, electronic device 110 may present a content component for obtaining second information describing the permissions for the first task. As an example, the content component may share the same or adjacent input area as input component 204, or it may take the form of a dialog button or confirmation card presented in a session.

[0093] In this way, users can explicitly provide permission status before task execution, avoiding the intelligent system from performing restricted operations when permission status is uncertain. Electronic device 110 associates the permission status with the first task and verifies this permission status before executing restricted operations. This reduces invalid task requests and rollback of failed tasks, lowering the risk of invalid computation and data processing.

[0094] In some cases, the content component may also include second text describing at least one action, which the content component uses to grant the intelligent system permission to perform at least one action. As an example, the second text may further describe the action object, the scope of the action, and the possible results. After providing input to the content component, the user can grant the intelligent system permission to perform the corresponding action.

[0095] In this way, users can make clear authorization confirmations for specific actions, reducing erroneous operations caused by unclear authorization objects or scopes. Electronic device 110 combines action identifiers, object identifiers, and authorization results into authorization data and sets authorization verification nodes in the task execution path. This narrows the scope of authorization data application and reduces the risk of erroneous data operations.

[0096] Intelligent systems can select appropriate interaction methods based on the type of information to be acquired. For example, input components can be used to supplement information that can affect the task outcome, such as key facts, result direction, or task boundaries; content components can be used for confirmation of permissions, risks, action scope, or external actions. Intelligent systems can categorize the information to be acquired and map the categorization results to corresponding interaction component configurations.

[0097] Specifically, when the information to be acquired pertains to user needs, key facts, or task boundaries, the intelligent system can present clarifying content in the input component. User needs may include itinerary pacing, design style, writing tone, or content type; key facts may include deadlines, error messages, etc.; task boundaries may include the range of files to be processed or the number of result versions. This information is used to express user needs and influence the execution outcome of the first task, and is therefore suitable for submission as a user message and entry into the session context associated with the first task.

[0098] When an intelligent system can identify more than two candidate pieces of information based on the initial input, the session context, or accessible resources, it can present multiple interactive items in the input component. These multiple interactive items can correspond to the same content type and each carry candidate information obtained through matching, filtering, or sorting. The intelligent system can configure single-selection or multi-selection methods based on whether candidate information can coexist; when candidate information cannot fully cover the requirements, it can also simultaneously present free text, files, images, or other media inputs to receive supplementary or alternative candidate information.

[0099] When the primary task requires authorization from the intelligent system or necessitates the execution of actions that may be irreversible or have external impacts, the intelligent system can display an authorization button within the content component. The prompt message corresponding to the authorization button can describe the action to be executed, the object of the action, the scope of its effect, and the possible consequences; the intelligent system can pause the corresponding action until confirmation is received.

[0100] In this way, the electronic device 110 can match appropriate interaction patterns to different clarification targets, reducing the user's need to judge the meaning of the question. The intelligent system converts the classification results into interaction component configurations and provides these configurations to the electronic device 110. This reduces invalid input and repeated clarifications caused by incompatible components, and lowers the computational overhead of regenerating interactive content.

[0101] Input component 204 may also have a close option. When a user triggers the close option, the electronic device 110 can stop displaying the current clarification component, and the close operation can be defined as the user not providing information using the clarification component. However, the user can still supplement the information through regular input boxes.

[0102] In some situations, electronic device 110 can wait for the user to supplement information through a regular input box, and continue performing the first task after obtaining the supplementary information. Alternatively, clarifying the question may not be a blocking condition for the first task. The intelligent system can continue performing the first task based on the information already obtained, and use preset values ​​or inferred results for missing information. The user can also add information after obtaining the task result.

[0103] In this way, users can actively end unnecessary clarifying interactions while retaining the path to continue input. The electronic device 110 responds to the close operation, terminating the current component state and releasing the corresponding temporary interface data or rendering nodes. This avoids maintaining inactive interactive components for extended periods, reducing client-side memory usage and background state maintenance overhead.

[0104] In some cases, the first input describes at least one object, and the multiple contents include multiple candidate objects. For example, such as... Figures 3A to 3C As shown, Figures 3A to 3C The process of candidate object disambiguation and displaying the results is illustrated. This process uses file objects and user objects as examples; candidate objects can also be images, videos, or other data objects with resource identifiers.

[0105] In some scenarios, the first input describes at least one file, multiple contents correspond to multiple candidate files, and a first set of interactive items is used to select at least one candidate file to trigger the intelligent system to process at least one candidate file. As an example, such as... Figure 3A As shown, Figure 3A An interface 300A is shown with files as candidate objects. On interface 300A, electronic device 110 presents a first input 302, an intelligent system response 304, and an input component 306. The first input 302 describes the file to be processed and the user. The intelligent system response 304 prompts the user to confirm the ambiguous object in the first input 302. The input component 306 presents question text describing the file type and candidate file interaction items 308-1 to 308-3.

[0106] Figure 3A The intelligent system response 304 can raise multiple questions to be clarified. Input component 306 currently displays questions about candidate files. Therefore, the user questions raised in the intelligent system response 304 and the file questions displayed in input component 306 can belong to the same group of questions to be clarified, but a direct one-to-one reference relationship between them is not required.

[0107] In some scenarios, such as Figure 3A As shown, the first input 302 describes at least one file object, and the multiple candidate contents include multiple candidate files. The object can also be a user, an image, a video, or other digital resource that the user has the right to access.

[0108] The intelligent system can determine the content type of the candidate content as a file based on the first input 302, and generate the corresponding question text and a set of candidate files. Candidate files can be determined based on filename matching results and access permissions. Candidate files can also be determined based on task relevance or recent access status. Server 130 can query the set of accessible files and perform fuzzy matching on filenames.

[0109] Electronic device 110 can receive the identifier and summary information of candidate files and present interactive items 308-1 to 308-3 accordingly. When the user selects interactive item 308-1, electronic device 110 receives a second input to select a candidate file. Electronic device 110 provides the file identifier corresponding to interactive item 308-1 to the intelligent system. This selection can trigger the intelligent system to read, organize, or otherwise process the target file.

[0110] In this way, users can confirm the actual target file before file processing begins, reducing the probability of misprocessing caused by files with the same or similar names. The electronic device 110 writes the selected file identifier into the task parameters and directs subsequent processing operations to that file identifier. This reduces erroneous file readings and duplicate file processing, lowers the number of storage accesses, and reduces the server's computational load.

[0111] In some scenarios, the first input describes at least one user, multiple pieces of content correspond to multiple candidate users, and a first set of interactive items is used to select at least one candidate user to trigger the intelligent system to establish communication with at least one candidate user. As an example, such as... Figure 3B As shown, Figure 3B A clarification interface 300B with users as candidates is shown. On interface 300B, input component 306 presents question text describing the user type and interactive items 310-1 to 310-5 indicating candidate users. Each candidate user interactive item may include a user identifier and appropriate descriptive information, and the user can select interactive item 310-1 as the target user.

[0112] Candidate users can come from a set of users who have established communication relationships with the current user, or from a set of users across an organization. Candidate users can also come from a set of users who have established resource relationships with the target file. For example, candidate users can include the creator, co-editors, or historical recipients of the target file. Server 130 can perform name matching based on the user description in the first input 302 and combine it with resource relationships to generate a set of candidate users.

[0113] After the user selects interaction item 310-1, the electronic device 110 provides the corresponding user identifier to the intelligent system. This selection can trigger the intelligent system to establish communication with the target user. Establishing communication may include sending content, initiating a session, or sending task processing results. The intelligent system can verify the target user and corresponding permissions before executing the communication action.

[0114] In this way, users can eliminate target user ambiguity before communication actions are executed, reducing the probability of content being sent to the wrong recipient. Electronic device 110 maps interaction item 310-1 to a unique user identifier and writes this identifier into the communication task parameters. This reduces transmission failures and duplicate acknowledgments, lowering the amount of redundant communication and server processing load.

[0115] The answer to the previous clarification question can also have an impact Figure 3B The set of candidate users. For example, a user first in Figure 3A After selecting a target file, server 130 can query the users associated with that target file. Server 130 can also recommend additional users based on resource relationships. Electronic device 110 can present the recommendations in input component 306 and allow the user to confirm whether to add additional users.

[0116] In this way, users can identify communication targets by leveraging the association between target files and candidate users, reducing the need to re-enter user information. Server 130... Figure 3A The file identifiers obtained are used as query criteria, and candidate users are filtered from the relational data. This can narrow down the user search space and sorting range, and reduce the amount of database queries and candidate list transmission.

[0117] In some cases, electronic device 110 may present a first message, which includes first text and first information. For example, such as... Figure 3C As shown, Figure 3C An interface 300C is shown displaying a structured presentation of documents and user clarification results. On interface 300C, electronic device 110 presents a first message 312. The first message 312 includes a document question and a user question as first text, and includes corresponding document answers and user answers as first information, thereby maintaining the correspondence between different questions and corresponding answers.

[0118] Electronic device 110 can organize the question text, object type, and object identifier into structured question-and-answer data. First message 312 can be entered into the intelligent system context as a task parameter for the first task. The intelligent system can determine the file to be processed based on the file response and identify the communication target based on the user's response. After completing file processing, the intelligent system can send the processing result to the selected communication target.

[0119] In this way, users can centrally verify file objects and communication objects before task execution, reducing the need to search for task parameters across messages. Electronic device 110 aggregates the answers to the two questions into a single structured submission, allowing the intelligent system to directly read the object identifier. This reduces natural language entity extraction and multi-round parameter confirmation, lowering model inference load and edge-cloud interaction latency.

[0120] In some cases, the electronic device 110 may present an input component on a first interface, which displays a conversation with the intelligent system and receives first input through the input component. As an example, such as... Figures 4A to 4C As shown, Figures 4A to 4C The session context scrolling process is shown. Figure 4A The initial interface 400A for the swipe operation is shown. On interface 400A, the electronic device 110 presents session messages 402 and an expanded input component 404, which displays questions and interactive items for receiving supplementary task information. The user can perform a swipe operation on interface 400A to view session messages at different locations.

[0121] After receiving a swipe operation, the electronic device 110 can generate a scrolling event and determine the scrolling distance. The electronic device 110 can also select a scrolling method based on the hierarchical relationship between the session message 402 and the input component 404. One scrolling method causes both the session message 402 and the input component 404 to move together. Another scrolling method causes the session message 402 to move while keeping the input component 404 in a predetermined display position. These two scrolling methods are parallel alternative implementations.

[0122] In some cases, the session includes a third message, and the electronic device 110 can receive a second swipe operation through a first interface and move the third message and input component based on the second swipe operation. As an example, such as... Figure 4B As shown, Figure 4B An interface 400B is shown where a session message and an input component move together. In interface 400B, session message 402 and input component 404 are located on the same scrollable layer. After receiving a second swipe operation through interface 400A, electronic device 110 updates the scroll offset of the scrollable layer and moves a third message (e.g., session message 402) and input component 404.

[0123] After the input component 404 is moved out of the visible area, the user can swipe in the opposite direction to bring the input component 404 back into the visible area. The electronic device 110 can save the selected state and input content of the input component 404 and restore its appearance when it re-enters the visible area.

[0124] In this way, users can continuously scroll through the entire session and input component 404, understanding their relationship based on their spatial positions within the session. Electronic device 110 updates session messages 402 and input component 404 using the same scroll offset. This reduces the need for separate overlay position synchronization calculations, lowering graphics processing overhead and the probability of scrolling stutters.

[0125] In some scenarios, the session includes a second message, and the electronic device 110 can receive a first swipe operation through a first interface and move the second message based on the first swipe operation, while maintaining the display position of at least one interactive item unchanged. As an example, such as... Figure 4C As shown, Figure 4C An interface 400C is shown where the session message moves while the input component remains in the same display position. In interface 400C, session message 402 is located in a scrollable session content layer, and input component 404 is located above the session content layer and remains in a predetermined display position. After receiving a first swipe operation through interface 400A, electronic device 110 updates the scroll offset of the session content layer.

[0126] Electronic device 110 moves a second message (e.g., session message 402) based on a first swipe operation, while keeping the position of at least one interactive item in input component 404 unchanged. Electronic device 110 can keep the selected state and input content in input component 404 unchanged during session content scrolling.

[0127] In this way, users can continue to access input component 404 while scrolling through historical messages, reducing the number of times they need to relocate to clarify questions and access action points. Electronic device 110 only updates the scrolling state of the session content layer and maintains the interface state of input component 404. This avoids repeated layout and redrawing of input component 404, reducing client-side rendering overhead and interaction response latency.

[0128] Example process Figure 5 A flowchart of an example process 500 for interface interaction is shown, based on some scenarios. Process 500 can be implemented at electronic device 110. See below for reference. Figure 5 To describe process 500.

[0129] like Figure 5 As shown, in block 510, electronic device 110 receives a first input via an input component. The first input instructs the intelligent system to perform a first task.

[0130] In box 520, electronic device 110 presents at least one interactive item in the input component. The at least one interactive item is used to receive information for performing a first task.

[0131] In box 530, electronic device 110 receives a second input via at least one interactive item. The second input is used to provide first information, which is used to perform a first task.

[0132] In this way, users can directly supplement the information needed to perform the task in the input component, reducing the switching between session messages and pages. The electronic device 110 converts the interactive input into structured task parameters and reduces repetitive clarification processing. This can reduce the number of interface renderings, the amount of data exchanged between the end and cloud, and the task execution latency.

[0133] In some cases, at least one interactive item includes a first set of interactive items that display multiple pieces of content, which correspond to multiple candidate information for performing the first task.

[0134] In this way, users can directly compare and select candidate information, reducing the length of free input and the number of modifications. Electronic device 110 can reuse the structured data of candidate information, reducing text parsing overhead and the amount of invalid task requests transmitted.

[0135] In some cases, receiving a second input via the at least one interactive item includes: receiving the second input for selecting a first interactive item, the first interactive item displaying the first content, the first interactive item belonging to a first group of interactive items, and the first task being performed based on the first content.

[0136] In this way, the user's first selected content can be directly associated with the parameters of the first task, reducing ambiguity and redundant confirmation operations. The intelligent system does not need to identify the first content again from longer free text, thus reducing the computational load of content recognition and redundant calculations.

[0137] In some cases, process 500 further includes: presenting a second set of interactive items in the input component; and receiving a third input for selecting a second interactive item, the second interactive item displaying second content, the second interactive item belonging to the second set of interactive items, the first task also being performed based on the second content.

[0138] In this way, users can provide information from different dimensions in a single clarification interaction, reducing operational interruptions caused by fragmented question-and-answer sessions. Multiple answers can be provided to the intelligent system as related structured data, thereby reducing context splicing processing and edge-cloud data exchange.

[0139] In some cases, the content types of multiple contents are obtained based on the first input.

[0140] In this way, the input component can present candidate content relevant to the first input, reducing the need for users to browse irrelevant content. Limiting the scope of candidate content based on content type reduces the computational load of candidate information retrieval, filtering, and sorting.

[0141] In some cases, the first input describes at least one object, and the plurality of contents includes a plurality of candidate objects.

[0142] In this way, users can directly select the target object based on the object reference in the first input, reducing the number of times additional text is added to resolve object ambiguity. The candidate object set can narrow down the object matching range, thereby reducing the computational overhead of repeated searches and context matching.

[0143] In some cases, the first input describes at least one user, the multiple contents correspond to multiple candidate users, and the first set of interactive items is used to select at least one candidate user to trigger the intelligent system to establish communication with the at least one candidate user.

[0144] In this way, users can directly confirm the communication object, reducing errors in object identification and redundant confirmation operations. The identified candidate user identifiers can be directly used to generate communication requests, thereby reducing the number of object searches and invalid communication requests.

[0145] In some cases, the first input describes at least one file, the multiple contents correspond to multiple candidate files, and the first set of interactive items is used to select at least one candidate file to trigger the intelligent system to process the at least one candidate file.

[0146] In this way, users can directly identify the files that need to be processed, reducing repetitive selection operations caused by unclear file references. Identified candidate file identifiers can be directly used to access the target file, thereby reducing the computational overhead caused by repeated storage accesses and error file handling.

[0147] In some cases, multiple contents correspond to the same content type, and process 500 further includes: in the input component, presenting first text that describes the content type.

[0148] In some cases, process 500 further includes: presenting a first message, the first message including the first text and the first information.

[0149] In this way, users can centrally view the correspondence between questions and answers within a conversation, reducing the need to manually review each message. The intelligent system can directly parse groups of questions and answers, thereby reducing the computational load of context association and the amount of redundant information requests.

[0150] In some cases, process 500 further includes: receiving a first operation through the input component; and stopping the presentation of the first set of interactive items and presenting a third set of interactive items on the input component, wherein the first set of interactive items and the third set of interactive items display different content.

[0151] In this way, users can switch between different question pages within the same input component, reducing interface navigation and input position changes. The electronic device 110 can reuse the display container of the input component, thereby reducing the processing overhead of creating, destroying, and rearranging page components.

[0152] In some cases, the first set of interactive items may include a third interactive item. Process 500 further includes: receiving a second operation via the input component, the second operation being used to replace the third interactive item with a fourth interactive item; and stopping the presentation of the third interactive item and presenting the fourth interactive item on the input component.

[0153] In this way, users can browse more candidate content within a limited display area, reducing the need to navigate to other interfaces to find candidate content. The electronic device 110 does not need to render all candidate interactive items simultaneously, thus reducing the number of active interface nodes and display cache usage.

[0154] In some cases, process 500 further includes: presenting a content component, the content component being used to obtain second information describing the permissions of the first task.

[0155] In this way, users can confirm the scope of permissions before task execution, reducing errors caused by unclear permission meanings. Structured permission information can be directly verified by intelligent systems, thereby reducing invalid task execution and duplicate permission requests.

[0156] In some cases, the content component includes second text describing at least one action, the content component being used to provide the intelligent system with the permission to perform the at least one action.

[0157] In this way, users can confirm the permitted actions based on the second text, reducing inconsistencies between the selected permission and the target action. The structured correspondence between actions and permissions can be directly invoked by the intelligent system, thereby reducing the number of repetitive action parsing and permission verifications.

[0158] In some cases, presenting at least one interactive item in the input component includes: presenting a fifth interactive item in the input component, the fifth interactive item including an input box, and receiving a second input through the at least one interactive item includes: receiving the second input through the input box.

[0159] In this way, users can provide supplementary content beyond the candidate information, reducing additional questions and answers caused by incomplete candidate information. Electronic device 110 does not need to pre-generate candidate interaction items for each possible answer, thus reducing the overhead of candidate content generation and interface rendering.

[0160] In some cases, process 500 further includes: presenting a sixth interactive item in the input component, the sixth interactive item being used to receive a second operation, the second operation being used to select the sixth interactive item; and stopping the presentation of the sixth interactive item in response to the second input including media content.

[0161] In this way, adding media content frees up the display area in the input component, reducing the risk of accidental duplicate media content additions. Stopping the rendering of unnecessary interactive items also reduces the number of active controls, thereby lowering the overhead of UI rendering and input event handling.

[0162] In some cases, receiving the first input via the input component includes: presenting the input component on a first interface, the first interface displaying a conversation with the intelligent system; and receiving the first input via the input component.

[0163] In this way, users can initiate the first task and continue to supplement information within the session interface, reducing the need to switch between the session interface and the task input page. Electronic device 110 can reuse the loaded session context and interface resources, thereby reducing the overhead of context retransmission, page loading, and resource initialization.

[0164] In some cases, the session includes a second message, and process 500 further includes: receiving a first swipe operation through the first interface; and moving the second message based on the first swipe operation while keeping the display position of the at least one interactive item unchanged.

[0165] In this way, users can continue to access interactive items while viewing different session content, reducing the need for swiping to find input entry points again. Since interactive items do not need to be re-laid out with the session content, the electronic device 110 can reduce the number of times interactive items are redrawn and the state restoration processing.

[0166] In some cases, the session includes a third message, and process 500 further includes: receiving a second swipe operation through the first interface; and moving the third message and the input component based on the second swipe operation.

[0167] In this way, users can view third messages and input components in the order of the conversation content, maintaining their spatial association. Electronic device 110 can handle the movement of both through a single scrolling container, thereby reducing the overhead of position synchronization and layer compositing between different display layers.

[0168] Example devices and equipment A corresponding apparatus for implementing the above methods or processes is also provided. Figure 6A schematic structural block diagram of an example device 600 for interface interaction is shown, according to some scenarios. Device 600 can be implemented as or included in electronic device 110. The various modules / components in device 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0169] like Figure 6 As shown, the device 600 includes: a first receiving module 610, a first presentation module 620, and a second receiving module 630. The first receiving module 610 is configured to receive a first input via an input component, the first input instructing the intelligent system to perform a first task. The first presentation module 620 is configured to present at least one interactive item in the input component, the at least one interactive item being used to receive information for performing the first task. The second receiving module 630 is configured to receive a second input via at least one interactive item. The second input is used to provide first information, the first information being used to perform the first task.

[0170] In some cases, at least one interactive item includes a first set of interactive items that display multiple pieces of content, which correspond to multiple candidate information for performing the first task.

[0171] In some cases, the second receiving module 630 is also configured to receive the second input, which is used to select a first interactive item, the first interactive item displays the first content, the first interactive item belongs to the first group of interactive items, and the first task is executed based on the first content.

[0172] In some cases, device 600 further includes a third receiving module configured to present a second set of interactive items in the input component; and to receive a third input for selecting a second interactive item, the second interactive item displaying second content, the second interactive item belonging to the second set of interactive items, the first task also being performed based on the second content.

[0173] In some cases, the content types of multiple contents are obtained based on the first input.

[0174] In some cases, the first input describes at least one object, and the plurality of contents includes a plurality of candidate objects.

[0175] In some cases, the first input describes at least one user, the multiple contents correspond to multiple candidate users, and the first set of interactive items is used to select at least one candidate user to trigger the intelligent system to establish communication with the at least one candidate user.

[0176] In some cases, the first input describes at least one file, the multiple contents correspond to multiple candidate files, and the first set of interactive items is used to select at least one candidate file to trigger the intelligent system to process the at least one candidate file.

[0177] In some cases, multiple contents correspond to the same content type, and the device 600 also includes a second presentation module configured to present first text on the input component, the first text describing the content type.

[0178] In some cases, device 600 also includes a third presentation module configured to present a first message, the first message including the first text and the first information.

[0179] In some cases, device 600 further includes a first stop module configured to receive a first operation via the input component; and to stop presenting the first set of interactive items and present a third set of interactive items on the input component, wherein the first set of interactive items and the third set of interactive items display different content.

[0180] In some cases, the first set of interactive items includes a third interactive item, and the device 600 further includes a second stop module configured to receive a second operation via the input component, the second operation being used to replace the third interactive item with a fourth interactive item; and to stop presenting the third interactive item and present the fourth interactive item on the input component.

[0181] In some cases, device 600 further includes a fourth presentation module configured to present a content component, the content component being used to acquire second information describing the permissions of the first task.

[0182] In some cases, the content component includes second text describing at least one action, the content component being used to provide the intelligent system with the permission to perform the at least one action.

[0183] In some cases, the first presentation module 620 is further configured to present a fifth interactive item, including an input box, in the input component, and the second receiving module 630 is further configured to receive the second input through the input box.

[0184] In some cases, device 600 further includes a third stop module configured to, on the input component, present a sixth interactive item for receiving a second operation for selecting the sixth interactive item; and, in response to the second input including media content, stop presenting the sixth interactive item.

[0185] In some cases, the first receiving module 610 is also configured to: present the input component on a first interface, the first interface displaying a conversation with the intelligent system; and receive the first input through the input component.

[0186] In some cases, the session includes a second message, and the device 600 further includes a first movement module configured to receive a first swipe operation through the first interface; and based on the first swipe operation, move the second message while keeping the display position of the at least one interactive item unchanged.

[0187] In some cases, the session includes a third message, and the device 600 also includes a second movement module configured to receive a second swipe operation through the first interface; and to move the third message and the input component based on the second swipe operation.

[0188] The modules included in device 600 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 600 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.

[0189] Figure 7 A block diagram of an electronic device 700 in which one or more examples may be implemented is shown. It should be understood that... Figure 7 The electronic device 700 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 7 The illustrated electronic device 700 can be used to implement the electronic device 110 discussed above.

[0190] like Figure 7As shown, electronic device 700 is in the form of a general-purpose electronic device. Components of electronic device 700 may include, but are not limited to, one or more processing units or processors 710, memory 720, storage devices 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processor 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 700.

[0191] Electronic device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 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 730 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 700.

[0192] Electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 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 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various examples.

[0193] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0194] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 700 can also communicate with one or more external devices (not shown) via communication unit 740 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 700, or with any device that enables electronic device 700 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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 interface interaction, comprising: The system receives a first input via an input component, which instructs the intelligent system to perform a first task. In the input component, at least one interactive item is presented, the at least one interactive item being used to receive information for performing the first task; as well as Through the at least one interactive item, a second input is received, the second input being used to provide first information, the first information being used to perform the first task.

2. The method according to claim 1, wherein the at least one interactive item includes a first group of interactive items, the first group of interactive items displaying multiple contents, the multiple contents corresponding to multiple candidate information for performing the first task.

3. The method of claim 2, wherein receiving the second input through the at least one interaction item comprises: The system receives a second input, which is used to select a first interactive item. The first interactive item displays the first content. The first interactive item belongs to the first group of interactive items. The first task is executed based on the first content.

4. The method according to claim 3, further comprising: The input component presents a second set of interactive items; as well as The system receives a third input, which is used to select a second interactive item. The second interactive item displays second content and belongs to a second group of interactive items. The first task is also executed based on the second content.

5. The method according to claim 2, wherein the content type of the plurality of contents is obtained based on the first input.

6. The method of claim 5, wherein the first input describes at least one object, and the plurality of contents includes a plurality of candidate objects.

7. The method of claim 6, wherein the first input describes at least one user, the plurality of contents correspond to a plurality of candidate users, and the first set of interactive items is used to select at least one candidate user to trigger the intelligent system to establish communication with the at least one candidate user.

8. The method of claim 6, wherein the first input describes at least one file, the plurality of contents correspond to a plurality of candidate files, and the first set of interactive items is used to select at least one candidate file to trigger the intelligent system to process the at least one candidate file.

9. The method of claim 2, wherein the plurality of contents correspond to the same content type, the method further comprising: The input component presents first text that describes the content type.

10. The method of claim 9, further comprising: The first message is presented, which includes the first text and the first information.

11. The method of claim 2, further comprising: The first operation is received through the input component; as well as Stop displaying the first set of interactive items and display a third set of interactive items in the input component, with the first set of interactive items and the third set of interactive items displaying different content.

12. The method of claim 2, wherein the first set of interactive items includes a third interactive item, and the method further comprises: The input component receives a second operation, which is used to replace the third interaction item with a fourth interaction item. as well as Stop presenting the third interactive item and present the fourth interactive item in the input component.

13. The method of claim 1, wherein presenting at least one interactive item in the input component comprises: The input component presents a fifth interactive item, which includes an input box. And receiving the second input through the at least one interaction item includes: The second input is received through the input box.

14. The method of claim 13, further comprising: In the input component, a sixth interactive item is presented, which is used to receive a second operation, and the second operation is used to select the sixth interactive item. as well as In response to the second input including media content, the presentation of the sixth interactive item is stopped.

15. The method of claim 1, wherein receiving the first input via the input component comprises: The input component is presented on the first interface, which displays a conversation with the intelligent system. as well as The first input is received through the input component.

16. The method of claim 15, wherein the session includes a second message, and the method further comprises: Receive the first swipe operation through the first interface; as well as Based on the first swipe operation, the second message is moved while the display position of the at least one interactive item remains unchanged.

17. The method of claim 15, wherein the session includes a third message, and the method further comprises: The second swipe operation is received through the first interface; as well as Based on the second sliding operation, move the third message and the input component.

18. A device for interface interaction, comprising: The first receiving module is configured to receive a first input through an input component, the first input instructing the intelligent system to perform a first task; A first presentation module is configured to present at least one interactive item in the input component, the at least one interactive item being used to receive information for performing the first task; as well as The second receiving module is configured to receive a second input through the at least one interactive item, the second input being used to provide first information, the first information being used to perform the first task.

19. 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 17 when executed by the at least one processor.

20. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 17.

Images