Intelligent agent interaction method, electronic equipment and intelligent agent interaction equipment

Abstract

The embodiment of the invention discloses an agent interaction method, electronic equipment and agent interaction equipment, and belongs to the field of UI interaction. The agent interaction method comprises the steps that an agent interaction assembly is displayed in a screen window, the screen window is a window of a display screen, and the display modes of the agent interaction assembly comprise multiple display modes with different screen area proportions. And switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition. According to the embodiment of the invention, the intelligent agent interaction assembly has multiple display modes, and the multiple display modes can be switched after the switching condition is achieved, so that a user can watch the content in the screen window conveniently, and the technical effects of improving the interaction experience of the robot are achieved.

Description

Technical Field

[0001] This application relates to the field of UI interaction. Specifically, it relates to an agent interaction method, an electronic device, and an agent interaction device. Background Art

[0002] Currently, the interaction with intelligent robots usually involves displaying an input box at a fixed position. After the user places the content to be input into the input box and sends it, they will receive a reply from the intelligent robot, thus achieving interaction with the skill robot. However, this interaction method will affect the user's viewing of other interfaces in some cases, reducing the interaction experience of the intelligent robot. Summary of the Invention

[0003] Embodiments of this application provide an agent interaction method, an electronic device, and an agent interaction device to at least solve the technical problem of poor interaction experience.

[0004] According to the first aspect of the embodiments of this application, an agent interaction method is provided. The method includes:

[0005] Display an agent interaction component in a screen window. The screen window is a window of a display screen, and the display method of the agent interaction component includes various display methods with different screen area ratios;

[0006] In response to the achievement of a switching condition for the agent interaction component, switch the current display method of the intelligent interaction component to a target display method according to a switching logic corresponding to the switching condition. Among them, the switching condition includes a physical triggering method or an automatic triggering method according to the user operation rule.

[0007] With this embodiment, the agent interaction component has various display methods, and the various display methods can be switched after the switching condition is achieved, facilitating the user to view the content in the screen window and improving the interaction experience of the robot.

[0008] In combination with the first aspect, in an optional implementation manner of the embodiments of this application, a switching button is displayed in the screen window or the agent interaction component. The switching button is preset with the corresponding switching logic, and the switching logic includes the next display method of the current display method, and the next display method is the target display method.

[0009] With this implementation manner, a switching button is displayed, and the user can trigger the switching button to switch the display method of the agent interaction component, making the display method of the agent interaction component more in line with the user's needs and improving the display flexibility and interaction experience of the agent interaction component.

[0010] In an alternative implementation of the embodiment of the present application in combination with the first aspect, before, during, or after switching the current display mode of the intelligent interaction component to the target display mode, the method further includes:

[0011] Perform visual feedback display on the switching button, where the visual feedback display includes at least one of highlighting the switching button and triggering an animation display for the switching button.

[0012] With this implementation, visual feedback enables users to more clearly confirm that the operation has been executed, improving the user's interaction experience.

[0013] In an alternative implementation of the embodiment of the present application in combination with the first aspect, the switching button is displayed at the corner of the screen window, at the navigation bar in the bottom area of the screen window, or at the corner of the intelligent agent interaction component.

[0014] With this implementation, the switching button is less likely to affect the user's browsing, improving the user experience.

[0015] In an alternative implementation of the embodiment of the present application in combination with the first aspect, the response to the achievement of the switching condition for the intelligent agent interaction component, and switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition, includes:

[0016] After the switching button is triggered in the physical trigger mode, switch the current display mode to the target display mode according to the preset switching sequence, or switch the current display mode to the target display mode corresponding to the triggered position according to the position where the switching button is triggered, where different display modes correspond to different positions on the switching button.

[0017] With this implementation, the flexibility and diversity of switching the display mode of the intelligent agent interaction component are improved.

[0018] In an alternative implementation of the embodiment of the present application in combination with the first aspect, the response to the achievement of the switching condition for the intelligent agent interaction component, and switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition, includes:

[0019] In response to a switching instruction generated based on the physical trigger mode, switch the current display mode to the target display mode corresponding to the switching instruction, where the switching instruction is preset with the corresponding switching logic.

[0020] With this implementation method, users can switch the display mode by triggering a switching instruction, which improves the flexibility and diversity of switching the display mode of the intelligent agent interaction component.

[0021] Combined with the first aspect, in an alternative implementation of the embodiment of the present application, the step of, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0022] Determine the high-frequency operation area of the intelligent agent interaction component based on the long short-term memory neural network model;

[0023] When the high-frequency operation area is the lower half area of the browsing page, switch the display mode of the intelligent agent interaction component to bottom display.

[0024] With this implementation method, it is possible to automatically switch the display mode of the interaction component to bottom display according to the high-frequency operation area of the intelligent agent interaction component, which improves the intelligence of the interaction and the user's interaction experience.

[0025] Combined with the first aspect, in an alternative implementation of the embodiment of the present application, the step of, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0026] Obtain the real-time heat topology map of the screen window;

[0027] Based on the real-time target detection algorithm, calculate the heat topology map to identify the triggering situation of each control displayed on the screen window, and obtain the interaction area of the screen window;

[0028] When the interaction area exceeds the preset area threshold, switch the display mode of the intelligent agent interaction component to floating display.

[0029] With this implementation method, when the interaction area exceeds the area threshold, it proves that the user mainly uses the intelligent agent interaction component. At this time, switching the display mode to floating display improves the interaction convenience between the user and the intelligent agent interaction component, thereby improving the user's interaction experience.

[0030] Combined with the first aspect, in an alternative implementation of the embodiment of the present application, the step of, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0031] Determine the target display mode of the browsing page according to the historical display data;

[0032] If the target display mode is determined, the agent interaction component is displayed in the screen window in the target display mode;

[0033] If the target display mode is not determined, the agent interaction component adapted to the window size of the browsing page is displayed in the screen window.

[0034] In this implementation, if the target display mode can be determined according to the historical display data, it proves that the user has browsed the current browsing page. At this time, switching to the target display mode helps to adopt the display mode used by the user and improve the interaction experience.

[0035] Combined with the first aspect, in an alternative implementation of the embodiments of the present application, the agent interaction component includes a custom slogan display area;

[0036] The method further includes:

[0037] Corresponding custom content is displayed in the custom slogan display area according to the type of the browsing page, where corresponding custom content is preset for different types of the browsing pages.

[0038] In this implementation, the user can customize the content for display, and when the browsing page changes, the corresponding custom content is displayed according to the type of the browsing page, improving the personalization degree of the interaction.

[0039] Combined with the first aspect, in an alternative implementation of the embodiments of the present application, the displaying of the agent interaction component in the screen window includes:

[0040] The agent interaction component adapted to the window size of the browsing page is displayed in the screen window, and the display modes include floating display, side display, embedded display in the browsing page, and full-screen display.

[0041] According to the second aspect of the embodiments of the present application, an electronic device is provided, and the electronic device includes a memory and a processor;

[0042] The memory is used to store a computer program;

[0043] The processor is used to execute the computer program to implement the steps of the above-mentioned method.

[0044] According to the third aspect of the embodiments of the present application, an agent interaction device is provided, including a display and the above-mentioned electronic device.

[0045] The technical effects obtained in the second and third aspects are similar to those obtained by the corresponding technical means in the first aspect, and will not be elaborated here. Description of the Drawings

[0046] Figure 1 is a flowchart of an agent interaction method provided by an embodiment of the present application;

[0047] Figure 2 is a schematic diagram of a side display agent interaction component provided by an embodiment of the present application;

[0048] Figure 3 is a schematic diagram of a floating display agent interaction component provided by an embodiment of the present application;

[0049] Figure 4 is a schematic diagram of an agent interaction component embedded in a browsing page for display provided by an embodiment of the present application;

[0050] Figure 5 is a schematic diagram of a full-screen display agent interaction component provided by an embodiment of the present application. Detailed Embodiments

[0051] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0052] It should be understood that the term "plurality" mentioned herein refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means "or", for example, A / B may mean A or B; the "and / or" herein is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different

[0053] In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0054] In the prior art, the interaction interface of intelligent agent robots is usually single, with a single interaction mode and a fixed interface layout, which cannot provide efficient use, cannot adapt to different user needs and device screen sizes, and limits the diversity and flexibility of the user experience.

[0055] Based on this, the present invention proposes a method for the interaction UI of an intelligent agent robot. Through an innovative four-dimensional interactive UI design, it realizes adaptive response to different screen sizes and diverse interactive experiences. The method includes a floating window dialogue component (an intelligent agent interaction component with a floating display mode), a bottom dialogue component (an intelligent agent interaction component with a side display mode), an embedded dialogue component (an intelligent agent interaction component embedded in a browsing page for display), and a full-screen dialogue component (an intelligent agent interaction component with a full-screen display mode) to meet the interaction needs of different users in different scenarios. In addition, the method also integrates various advanced functions such as voice input, robot image display, picture upload, interaction switching, command invocation, and opening a new dialogue, enabling users to interact with the intelligent agent robot in a more natural and convenient way. The innovation of this technical solution lies in its multi-modal interaction ability and high degree of personalized customization, which not only improves the user experience but also expands the application scope of the intelligent agent robot. By real-time monitoring of user behavior and environmental changes, this system can provide more accurate and personalized services, thus realizing intelligent and personalized interaction management.

[0056] Next, a further description is made of an intelligent agent interaction method provided by an embodiment of the present application. Refer to Figure 1 the flow schematic diagram of the intelligent agent interaction method shown, the method includes the following processing procedures.

[0057] S100. Display an intelligent agent interaction component in a screen window, where the screen window is a window of a display screen.

[0058] The display mode of the intelligent agent interaction component includes various display modes with different screen area ratios. Specifically, the display mode of the intelligent agent interaction component includes floating display, side display, embedded display in a browsing page, and full-screen display. The intelligent agent interaction component includes a dialogue box and an input box; among them, in the display modes, the window sizes adapted by the full-screen display, embedded display in a browsing window, floating display, and side display gradually decrease.

[0059] Among them, floating display means that the intelligent agent interaction component is displayed floating above the browsing page. Preferably, when floating, the intelligent agent interaction component can be minimized and moved. Edge display means that the intelligent agent interaction component is displayed on the edge of the screen window or browsing page. The edge includes the left, right, upper, and bottom sides, that is, edge display includes left display, right display, upper display, and bottom display. Embedded display in the browsing page means that the intelligent agent interaction component is embedded in the browsing page for display. Full-screen display means that the intelligent agent interaction component is displayed full-screen.

[0060] Among them, the content entered by the user will be displayed in the input box, and the content sent by the user and the content replied by the robot will be displayed in the dialog box.

[0061] S102. In response to the achievement of the switching condition for the intelligent agent interaction component, switch the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition.

[0062] Among them, the switching condition includes a physical triggering method or an automatic triggering method according to the user operation rule. That is to say, the physical triggering method has corresponding switching logic, and the automatic triggering method also has corresponding switching logic. When the switching condition of the physical triggering method is achieved, switch to the target display mode according to the switching logic of the physical triggering method, and the same applies to the automatic triggering method.

[0063] In one embodiment, the physical triggering method can be that the user interacts with the touch screen, or the user uses an external device such as a keyboard for interaction. The automatic triggering method, for example, as the content displayed in the screen window changes, the automatic triggering method is achieved. For example, when the user opens a browsing page, in order not to affect the user's viewing of the browsing page, the automatic triggering method is achieved.

[0064] Adopting this embodiment, the intelligent agent interaction component has multiple display modes, and the multiple display modes can be switched after the switching condition is achieved, which is convenient for the user to view the content in the screen window and improves the interaction experience of the robot.

[0065] Optionally, in an implementation manner of this embodiment, a switching button is displayed in the screen window or the intelligent agent interaction component, and the switching button is preset with the corresponding switching logic. The switching logic includes the next display mode of the current display mode, and the next display mode is the target display mode.

[0066] In one embodiment, the switching button is a virtual button, and the user can trigger the switching button by touching the touch screen or operating the external device.

[0067] With this implementation method, a switching button is displayed, and the user can trigger the switching button to switch the display mode of the agent interaction component, making the display mode of the agent interaction component more in line with the user's needs and improving the display flexibility and interaction experience of the agent interaction component.

[0068] Optionally, in an implementation method of this embodiment, when, before, or after switching the current display mode of the intelligent interaction component to the target display mode, the method further includes:

[0069] Performing visual feedback display on the switching button, where the visual feedback display includes at least one of highlighting the switching button and performing trigger animation display on the switching button.

[0070] With this implementation method, visual feedback can enable the user to more clearly confirm that the operation has been executed and improve the user's interaction experience.

[0071] Optionally, in an implementation method of this embodiment, the switching button is displayed at the corner of the screen window, at the navigation bar in the bottom area of the screen window, or at the corner of the agent interaction component.

[0072] In one embodiment, the corner refers to the four top corners or the areas near the top corners.

[0073] With this implementation method, the switching button is not likely to affect the user's browsing, improving the user experience.

[0074] Optionally, in an implementation method of this embodiment, in response to the achievement of the switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0075] After the switching button is triggered in the physical trigger manner, switching the current display mode to the target display mode according to the preset switching order or switching the current display mode to the target display mode corresponding to the triggered position according to the position where the switching button is triggered, where different display modes correspond to different positions on the switching button.

[0076] The switching order refers to the switching order of four display modes. For example, the switching order can be floating display, side display, embedded in the browsing page display, and full-screen display.

[0077] The switching button can be divided into four areas, and each area corresponds to a triggered position. For example, the four areas can be upper left, upper right, lower left, and lower right. When the user triggers the upper left, it switches to floating display.

[0078] By adopting this implementation method, the flexibility and diversity of switching the display mode of the intelligent agent interaction component are improved.

[0079] Optionally, in an implementation manner of this embodiment, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0080] In response to a switching instruction generated based on the physical triggering method, switching the current display mode to the target display mode corresponding to the switching instruction, where the switching instruction is preset with the corresponding switching logic.

[0081] In one embodiment, the switching instruction can be generated by using an external device such as a keyboard or a mouse.

[0082] By adopting this implementation method, the user can switch the display mode by triggering the switching instruction, improving the flexibility and diversity of switching the display mode of the intelligent agent interaction component.

[0083] Optionally, in an implementation manner of this embodiment, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0084] Determine the high-frequency operation area of the intelligent agent interaction component based on the long short-term memory neural network model;

[0085] When the high-frequency operation area is the lower half area of the browsing page, switch the display mode of the intelligent agent interaction component to bottom display.

[0086] In one embodiment, the long short-term memory neural network model can be an LSTM neural network model.

[0087] By adopting this implementation method, it is possible to automatically switch the display mode of the interaction component to bottom display according to the high-frequency operation area of the intelligent agent interaction component, improving the intelligence of robot interaction and the user's interaction experience.

[0088] Optionally, in an implementation manner of this embodiment, in response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0089] Obtain the real-time heat topology map of the screen window;

[0090] Calculate the thermal topology map based on a real-time object detection algorithm to identify the triggering conditions of each control displayed in the screen window, and obtain the interaction area of the screen window;

[0091] When the interaction area exceeds a preset area threshold, switch the display mode of the intelligent agent interaction component to floating display.

[0092] In one embodiment, the object detection algorithm can be the YOLOv8 algorithm. The area threshold is set according to actual requirements, for example, 65%.

[0093] Using this implementation method, when the interaction area exceeds the area threshold, it proves that the user mainly uses the intelligent agent interaction component. At this time, switching the display mode to floating display improves the interaction convenience between the user and the intelligent agent interaction component, thereby enhancing the user's interaction experience.

[0094] Optionally, in one implementation of this embodiment, the response to the achievement of the switching condition for the intelligent agent interaction component, and switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes:

[0095] Determine the target display mode of the browsing page according to historical display data;

[0096] If the target display mode is determined, display the intelligent agent interaction component in the screen window in the target display mode;

[0097] If the target display mode is not determined, execute the display of the intelligent agent interaction component adapted to the window size of the browsing page in the screen window.

[0098] In one embodiment, the historical display data may include the display mode used when closing the current browsing page last time. If there is such data, the target display mode can be determined; if not, the target display mode cannot be determined.

[0099] Using this implementation method, if the target display mode can be determined according to the historical display data, it proves that the user has browsed the current browsing page. At this time, switching to the target display mode helps to adopt the display mode that the user is used to and improves the interaction experience.

[0100] Optionally, in one implementation of this embodiment, the intelligent agent interaction component includes a custom slogan display area;

[0101] The method further includes:

[0102] Display corresponding custom content in the custom slogan display area according to the type of the browsing page, where corresponding custom content is preset for different types of the browsing page.

[0103] In one embodiment, the type can be set according to actual needs. For example, it can be classified according to the functions of the browsing page. If the browsing page belongs to a development page, it is of the development type. The browsing page can also be a page of other types such as task type, rules and regulations type, etc.

[0104] With this implementation method, users can customize the content for display, and when the browsing page changes, the corresponding customized content is displayed according to the type of the browsing page, improving the personalization degree of robot interaction.

[0105] Optionally, in one implementation of this embodiment, the agent interaction component includes a copy button;

[0106] The method further includes:

[0107] In response to a trigger operation on the copy button, at least part of the content in the dialog box is copied to the clipboard.

[0108] With this implementation method, a copy button is displayed, facilitating users to copy the content in the dialog box and improving the interaction convenience of users.

[0109] Optionally, in one implementation of this embodiment, the displaying of the agent interaction component in the screen window includes:

[0110] Displaying an agent interaction component adapted to the window size of the browsing page in the screen window, and the display methods include floating display, side display, embedded display in the browsing page, and full-screen display.

[0111] In one embodiment, the adaptation to the window size can be achieved through a preset adaptation rule. For example, the larger the window size, the display method with a larger usage area is used.

[0112] This embodiment also provides an electronic device, which includes a memory and a processor;

[0113] The memory is used to store a computer program;

[0114] The processor is used to execute the computer program to implement the steps of the above-mentioned method.

[0115] This embodiment also provides an agent interaction device, which includes a display and the above-mentioned electronic device.

[0116] In a specific application scenario, as Figures 2-5 shown, the interaction method includes the following content:

[0117] Interactive UI Responsive to Different Screen Sizes: The system can automatically adjust the UI layout according to the device screen size and supports four types of interactive UIs: floating window dialogue component, bottom dialogue component, embedded dialogue component, and full-screen dialogue component.

[0118] The specific process of adjusting the layout according to the browser size is achieved by buttons and keyboard shortcuts. Users can quickly switch between different UI layout modes by clicking the corresponding buttons on the interface or using the preset keyboard shortcuts. For example, in a desktop browser, when the user detects that the screen size is small, they can click a "Switch Layout" button, and the system will automatically switch from the full-screen dialogue component to the floating window dialogue component that is more suitable for small screens. Similarly, if the user wants to use the keyboard for operation, they can preset a shortcut key combination, such as "Ctrl+Shift+L". Each time this combination key is pressed, the system will cycle through the four layout modes.

[0119] Through the screen element capture technology combined with the multi-dimensional perception algorithm, the system can achieve dynamic UI form adjustment. Using computer vision technology to construct a screen heat topology map in real time, identifying the current active controls (input box / player / navigation bar, etc.) through the YOLOv8 model, and calculating the effective interaction area. When it is detected that the core operation area occupies more than 65% of the screen, the embedded mode is triggered, and the new information is displayed in a floating form in the non-heat area.

[0120] Based on the LSTM neural network, a user behavior prediction engine is constructed to analyze the characteristics of recent operation trajectories: high-frequency click areas and gesture stay durations. When it is detected that the user continuously swipes in the lower half of the screen, it automatically switches to the bottom layout.

[0121] Based on the long-term usage behavior habits of users, different metrics such as the usage frequency records of different components, the records before the last shutdown, the switching records at the first access on the same day, and the switching records between different business pages are used for modeling to determine which component to use when switching the first access and different pages, including the bottom dialogue component, embedded dialogue mode, floating window component, and full-screen component. The habit model is dynamically calibrated every 72 hours, and the behavior weights of the most recent 30 days are retained at 70%.

[0122] Floating Window Dialogue Component: Provides a dialogue window that floats at any position on the screen, allowing users to interact with the robot at any time while performing other operations.

[0123] Bottom Dialogue Component: The dialogue window is fixed at the bottom of the screen, enabling users to conveniently conduct dialogue interactions at the bottom of the screen.

[0124] Embedded Dialogue Component: The dialogue window is embedded in the application interface, integrating with the application content and providing an immersive interaction experience.

[0125] Full-screen dialogue component: Displays the dialogue interface in full screen, suitable for scenarios where the robot needs to interact with full concentration.

[0126] One-key switching: Users can click the switching button on the interface to instantly switch from the floating window dialogue style, bottom dialogue style, embedded dialogue style to the full-screen dialogue style.

[0127] Prominent switching position: The switching button is designed in a position that is easy for users to notice and operate, such as the corner of the interface or the bottom navigation bar, ensuring that users can quickly access and switch styles.

[0128] Visual feedback: Each time the switching button is clicked, the system provides visual feedback, such as button highlighting or a short animation effect, to confirm that the user's switching operation has been executed.

[0129] Memory function: The system will remember the last interaction style selected by the user and automatically apply it when the user starts the interaction next time, unless the user selects a different style.

[0130] Adaptive layout: The presence of the switching button does not affect the layout and functions of other UI components, ensuring a good user experience on different devices and screen sizes.

[0131] Instruction invocation function: Users can quickly invoke robot skills for interaction through specific instructions.

[0132] Voice input function: Users can interact with the robot through voice input, and the system will convert the voice into text and respond.

[0133] Robot image display: The system provides a customizable robot image to enhance the intimacy of user interaction.

[0134] Picture upload function: Users can upload pictures, and the robot can analyze the picture content and give feedback.

[0135] Conversation history function: The system can automatically record all interaction sessions between the user and the intelligent robot, including various forms of communication content such as text, voice, and pictures.

[0136] Context restoration: In a new session, the system can restore the previous session context according to the user's needs, making the interaction more coherent and natural.

[0137] Scene trigger: The system allows users to customize the welcome message and can automatically trigger the corresponding welcome message according to the user's usage scenario.

[0138] Interaction feedback: Users can evaluate the robot's response by giving a like or a dislike, helping the system optimize and execute interaction instructions.

[0139] Text copying: In text interaction, users can easily copy the robot's responses or suggestions for use in other applications.

[0140] New conversation function: Users can start a new conversation thread at any time to communicate with the robot in multiple threads.

[0141] The above interaction method has at least one of the following characteristics:

[0142] 1. Agent robot interaction UI design that responds to different screen sizes;

[0143] 2. Implementation of four interaction UI components and their applications in different scenarios;

[0144] 3. Integration of advanced interaction functions such as voice input, robot image display, and picture upload;

[0145] 4. Functions that enhance the user experience, such as interaction switching, command invocation, and starting a new conversation;

[0146] 5. Allowing users to instantly switch with one click by clicking on prominent positions on the interface;

[0147] 6. Remembering and automatically applying the user-preferred interaction according to the user's usage habits.

[0148] The above interaction method has at least one of the following effects:

[0149] 1. Providing an adaptive interaction UI for different screen sizes and enhancing the user experience;

[0150] 2. Integrating multiple interaction methods to meet the needs of different users;

[0151] 3. Improving the naturalness and intimacy of interaction through functions such as voice input and robot image display;

[0152] 4. Improving the flexibility and efficiency of interaction through functions such as interaction switching and command invocation;

[0153] 5. Automatically applying the user-preferred interaction style through remembering the user's usage habits and enhancing the personalized experience.

[0154] Specifically, it not only improves the flexibility and adaptability of agent robot interaction, but also enhances the naturalness and personalization of interaction, providing users with a richer and more convenient interaction experience.

[0155] The serial numbers of the embodiments in this application or the order of introduction are only for description and do not represent the superiority or inferiority of the embodiments.

[0156] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0157] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0159] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital versatile disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc. It should be noted that the computer-readable storage medium mentioned in the embodiments of the present application can be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0160] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.), and signals involved in the embodiments of the present application are all authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions. For example, the scene data of the current frame in the three-dimensional virtual scene, the device information of the client, and the scene interaction information involved in the embodiments of the present application are all obtained under full authorization.

[0161] The above are only the preferred embodiments of the present application. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. An agent interaction method, characterized in that, The method includes: Displaying an agent interaction component in a screen window, where the screen window is a window of a display screen, and the display mode of the agent interaction component includes multiple display modes with different screen area ratios; In response to the achievement of a switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition, where the switching condition includes a physical triggering mode or an automatic triggering mode according to user operation rules.

2. The intelligent agent interaction method according to claim 1, wherein A switching button is displayed in the screen window or the agent interaction component, and the switching button is preset with the corresponding switching logic, and the switching logic includes the next display mode of the current display mode, and the next display mode is the target display mode.

3. The intelligent agent interaction method according to claim 2, wherein When, before, or after switching the current display mode of the intelligent interaction component to the target display mode, the method further includes: Performing visual feedback display on the switching button, where the visual feedback display includes at least one of highlighting the switching button and performing trigger animation display on the switching button.

4. The intelligent agent interaction method according to claim 2 or 3, wherein The switching button is displayed at the corner of the screen window, at the navigation bar in the bottom area of the screen window, or at the corner of the agent interaction component.

5. The agent interaction method according to claim 2, wherein The step of, in response to the achievement of a switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition includes: After the switching button is triggered in the physical triggering mode, switching the current display mode to the target display mode according to a preset switching order or switching the current display mode to the target display mode corresponding to the triggered position according to the position where the switching button is triggered, where different display modes correspond to different positions on the switching button.

6. The intelligent agent interaction method according to claim 1, wherein The step of, in response to the achievement of a switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition includes: In response to a switching instruction generated based on the physical triggering mode, switching the current display mode to the target display mode corresponding to the switching instruction, where the switching instruction is preset with the corresponding switching logic.

7. The intelligent agent interaction method according to claim 1, characterized in that, The step of, in response to the achievement of a switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition includes: Determining a high-frequency operation area of the agent interaction component based on a long short-term memory neural network model; When the high-frequency operation area is the lower half area of the browsing page, switching the display mode of the agent interaction component to bottom display.

8. The intelligent agent interaction method according to claim 1, wherein The step of, in response to the achievement of a switching condition for the agent interaction component, switching the current display mode of the intelligent interaction component to a target display mode according to a switching logic corresponding to the switching condition includes: Obtaining a real-time heat topology map of the screen window; Calculate the thermal topology map based on a real-time object detection algorithm to identify the triggering conditions of each control displayed in the screen window, and obtain the interaction area of the screen window; When the interaction area exceeds a preset area threshold, switch the display mode of the intelligent agent interaction component to floating display.

9. The intelligent agent interaction method according to claim 1, wherein In response to the achievement of the switching condition for the intelligent agent interaction component, switching the current display mode of the intelligent interaction component to the target display mode according to the switching logic corresponding to the switching condition includes: Determine the target display mode of the browsing page according to historical display data; If the target display mode is determined, display the intelligent agent interaction component in the screen window in the target display mode; If the target display mode is not determined, execute displaying the intelligent agent interaction component adapted to the window size of the browsing page in the screen window.

10. The intelligent agent interaction method according to claim 1, wherein, The intelligent agent interaction component includes a custom slogan display area; The method further includes: Display corresponding custom content in the custom slogan display area according to the type of the browsing page, where corresponding custom content is preset for different types of the browsing pages.

11. The intelligent agent interaction method according to any one of claims 1-10, characterized in that, Displaying the intelligent agent interaction component in the screen window includes: Display the intelligent agent interaction component adapted to the window size of the browsing page in the screen window, and the display modes include floating display, side display, embedded display in the browsing page, and full-screen display.

12. An electronic device, characterized in that, The electronic device includes a memory and a processor; The memory is used to store a computer program; The processor is used to execute the computer program to implement the steps of the method according to any one of claims 1-11.

13. An intelligent agent interaction device, characterized in that, It includes a display and the electronic device according to claim 12.

Images