AI interaction method and device, electronic equipment, storage medium and program product

Abstract

The invention discloses an AI interaction method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of intelligent control, and the method comprises the steps: responding to a triggering operation of AI interaction, and displaying a first interaction interface in a display interface; wherein the first interaction interface comprises a first area and a second area; a first cue word is displayed in the first area, and the first cue word is used for indicating AI skills which can be used; and displaying a second cue word in the second area, the second cue word being used for indicating a shortcut operation corresponding to the AI skill. According to the method, the interface definition and the operation efficiency of AI interaction are improved, so that the efficient use requirement of a user is met.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to AI interaction methods, devices, electronic devices, storage media and program products. Background Technology

[0002] With the widespread application of artificial intelligence technology in the smart home field, AI assistants have become the main entry point for users to interact with home appliances. Currently, AI assistant interfaces usually use a single list or grid layout to display various AI skills and their corresponding control commands at the same time. This results in a mixed presentation of information at different levels (such as skill categories and specific commands), a chaotic interface structure, and a lack of visual hierarchy. Users find it difficult to intuitively identify the current functional module during use and need to jump through multiple levels to trigger the target control command, which fails to meet users' needs for efficient use. Summary of the Invention

[0003] The main purpose of this application is to provide an AI interaction method, device, electronic device, storage medium, and program product, which aims to provide a simple and clear AI interaction interface to meet users' needs for efficient use.

[0004] To achieve the above objectives, this application proposes an AI interaction method, which includes: In response to the triggering operation of AI interaction, a first interactive interface is displayed in the display interface; wherein, the first interactive interface includes a first area and a second area; A first prompt word is displayed in the first area, wherein the first prompt word is used to indicate the AI ​​skills that can be used; A second prompt word is displayed in the second area, wherein the second prompt word is used to indicate a shortcut operation corresponding to the AI ​​skill.

[0005] In one embodiment, the AI ​​interaction method further includes: In response to the triggering operation of the second prompt word, the second prompt word is parsed to obtain the operation instruction corresponding to the second prompt word, and the operation instruction is sent to the corresponding target device; Display the execution result of the operation command.

[0006] In one embodiment, the first interactive interface further includes a third area; the AI ​​interaction method further includes: In response to the triggering operation of the second prompt word, obtain the parsing process and parsing result corresponding to the second prompt word; The third area displays the parsing process and the parsing result, and obtains the corresponding operation instructions based on the parsing result; and / or displays operation cards based on the parsing result, the operation cards being used to display recommended operations, and obtains the corresponding operation instructions based on operation confirmation.

[0007] In one embodiment, the first interactive interface further includes a fourth area, the fourth area displaying AI shortcut entries; the AI ​​interaction method further includes: In response to the triggering operation of the AI ​​shortcut entry, a second interactive interface corresponding to the AI ​​shortcut entry is displayed. In the second interactive interface, a third prompt word and a fourth prompt word are displayed. The third prompt word is used to indicate the AI ​​skills that can be used, and the fourth prompt word is used to indicate the shortcut operation corresponding to the AI ​​skill.

[0008] In one embodiment, the AI ​​interaction method further includes: The first area displays the target image corresponding to the AI ​​skill.

[0009] In one embodiment, the target image includes a base image and a marker image, wherein the marker image of the target image is a preset image corresponding to the AI ​​skill.

[0010] In one embodiment, the first area is located in a preset display area of ​​the first interactive interface, and the second area is located below the first area; and / or, The font size of the second prompt word is smaller than the font size of the first prompt word.

[0011] Furthermore, to achieve the above objectives, this application also proposes an AI interaction device, which includes: The display module is used to respond to the trigger operation of AI interaction and display a first interactive interface in the display interface; wherein, the first interactive interface includes a first area and a second area; The display module is further configured to display a first prompt word in the first area, wherein the first prompt word is used to indicate the available AI skills; The display module is further configured to display a second prompt word in the second area, wherein the second prompt word is used to indicate a shortcut operation corresponding to the AI ​​skill.

[0012] In addition, to achieve the above objectives, this application also proposes an electronic device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the AI ​​interaction method as described above.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the AI ​​interaction method described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the AI ​​interaction method described above.

[0015] This application provides an AI interaction method. In response to a trigger operation of AI interaction, the application displays a first interactive interface in a display interface. The first interactive interface includes a first area and a second area. A first prompt word is displayed in the first area, which is used to indicate the available AI skills. A second prompt word is displayed in the second area, which is used to indicate the shortcut operation corresponding to the AI ​​skill.

[0016] This application displays AI skills and their corresponding control commands in separate areas by setting up a first area and a second area on the interactive interface. The first area is used to display the first prompt word representing the AI ​​skill, and the second area is used to display the second prompt word representing the specific operation under the AI ​​skill. This achieves a hierarchical and structured presentation of skill categories and execution commands, enabling users to intuitively identify the current AI skill and its available control commands.

[0017] Compared to traditional technologies that mix various AI skills and their control commands in the same list or grid, resulting in a cluttered interface and unclear information hierarchy, this application maps information at different levels to different display areas. This avoids visual confusion and cognitive burden caused by interference between skill categories and specific commands, reducing the operational steps and time costs required for users to find and identify target control commands. Simultaneously, by displaying the association between the first and second prompts, users can intuitively understand the correspondence between the current AI skill and available control commands. This allows for quick location and triggering of target control commands in multi-skill scenarios, improving the clarity and efficiency of the AI ​​interaction interface and meeting users' needs for efficient use. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the AI ​​interaction method of this application. Figure 2 This is a schematic diagram of a first interactive interface provided in an embodiment of the AI ​​interaction method of this application; Figure 3 This is a schematic diagram of another first interactive interface provided in an embodiment of the AI ​​interaction method of this application; Figure 4 A schematic diagram of yet another first interactive interface provided in an embodiment of the AI ​​interaction method of this application; Figure 5 This is a schematic diagram of a second interactive interface provided in an embodiment of the AI ​​interaction method of this application; Figure 6 This is a schematic diagram of the target image provided in an embodiment of the AI ​​interaction method of this application; Figure 7 This is another schematic diagram of a target image provided in an embodiment of the AI ​​interaction method of this application; Figure 8 This is a schematic diagram of the module structure of the AI ​​interaction device according to an embodiment of this application; Figure 9 This is a schematic diagram of the device structure of the hardware operating environment involved in the AI ​​interaction method in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] Currently, AI assistant interfaces typically use a single list or grid layout to display various AI skills and their corresponding control commands simultaneously. This results in a jumbled mix of information at different levels, a chaotic interface structure, and a lack of visual hierarchy. Users find it difficult to intuitively identify the current functional module and need to navigate through multiple levels to trigger the target control command, which fails to meet users' needs for efficient use.

[0025] This application displays AI skills and their corresponding control commands in separate areas by setting up a first area and a second area on the interactive interface. The first area is used to display the first prompt word representing the AI ​​skill, and the second area is used to display the second prompt word representing the specific operation under the AI ​​skill. This achieves a hierarchical and structured presentation of skill categories and execution commands, enabling users to intuitively identify the current AI skill and its available control commands.

[0026] This application avoids visual confusion and cognitive burden caused by the interference between skill categories and specific instructions by mapping information at different levels to different display areas. It also reduces the operation steps and time costs required for users to find and identify target control instructions. At the same time, by displaying the first prompt word and the second prompt word in association, users can intuitively understand the correspondence between the current AI skill and the available control instructions. This allows them to quickly locate and trigger target control instructions in multi-skill scenarios, improving the clarity of the AI ​​interaction interface and the efficiency of operation, thereby meeting users' needs for efficient use.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions. The following description uses an electronic device as an example to illustrate this embodiment and the subsequent embodiments.

[0028] Based on this, the embodiments of this application provide an AI interaction method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the AI ​​interaction method of this application.

[0029] In this embodiment, the AI ​​interaction method includes steps S10 to S30: Step S10: In response to the triggering operation of AI interaction, a first interactive interface is displayed in the display interface; wherein, the first interactive interface includes a first area and a second area; Triggering an action is a specific action performed by a user on a smart terminal to start or activate a specific function. This action can take many forms, such as clicking a virtual button on the screen, long-pressing a specific area, inputting a voice wake-up command, or inputting a gesture recognition. Essentially, it sends a clear start signal to the AI ​​interaction system through the human-computer interaction interface, causing the AI ​​interaction system to switch from a standby state to an active processing state.

[0030] Triggering operations for AI interaction specifically refer to user operations used to initiate AI interaction sessions or functions, which are different from general application startup operations. This operation clearly instructs the AI ​​interaction system to enter AI processing mode, such as clicking the AI ​​control button on the APP (Application) display interface, saying a wake word, or using the AI ​​control floating ball.

[0031] The display interface is a visual area used to present information and receive user operations. It serves as the carrier for visual interaction between users and AI interaction systems and the physical medium for presenting digital information. The display interface can be displayed on a physical carrier, such as a smart terminal. If displayed on a physical carrier, the display interface can include all or part of the pixel area displayed on the physical screen. It can be a full-screen display or a partial display form such as a floating window, split screen, or pop-up window; there are no restrictions here. The display interface can also be presented directly through virtual imaging technologies, such as virtual reality, augmented reality, mixed reality, and extended reality, etc., and the specific settings can be configured according to actual needs.

[0032] The first interactive interface is the initial main interface presented in response to AI interaction triggers. As the primary medium for user interaction with AI, this interface contains multiple skill-specific functional zones to centrally display AI skills. It serves as the starting point for users to select and operate AI functions, and is also the main control center in multi-skill scenarios. The first interactive interface includes a first area and a second area, used to display different information for user operation.

[0033] Step S20: Display a first prompt word in the first area, wherein the first prompt word is used to indicate the AI ​​skills that can be used; The first area is a specific display space in the first interactive interface. The specific display position of the first area in the first interactive interface is not limited. In this embodiment, the first area can be located in a prominent position at the top or center of the interface, and is used to display the first prompt word, representing the currently available AI skills.

[0034] The first prompt is a text message displayed in the first area that indicates the available AI skills. This prompt clearly informs the user of the currently available AI capability category in natural language. AI skills are specific functions or service types possessed by an AI interaction system, typically corresponding to specific application scenarios and processing logic, such as different functional dimensions like natural language deep reasoning, automatic generation of smart home scenes, control of home appliances, recipe recommendations, and device problem consultation.

[0035] In this embodiment, the first prompt word displayed in the first area can be intelligently recommended based on the user's usage habits or the current environment. For example, when the user returns home, skill prompts related to "home mode" can be displayed first.

[0036] Step S30: Display a second prompt in the second area, wherein the second prompt is used to indicate a shortcut operation corresponding to the AI ​​skill.

[0037] The second area is another display space within the first interactive interface. Its display position within the first interactive interface is not limited. In this embodiment, it can be located below or adjacent to the first area and is used to display a second prompt word associated with the AI ​​skill indicated by the first area.

[0038] The second prompt word is text information displayed in the second area that indicates the specific quick action corresponding to the AI ​​skill prompted by the first prompt word. This prompt word is usually a natural language command example or function entry label that the user can directly trigger, such as "The air conditioner is a bit cold," "Generate a home mode," or "Analyze today's energy consumption," etc., which are operable and instructive. The quick action is a pre-configured set of standardized operation instructions. Users do not need to manually enter complex instructions or perform multiple steps of settings. They can execute them with one click by triggering the second prompt word, such as adjusting the air conditioner temperature with one click, generating a smart scene with one click, or checking the device status with one click.

[0039] In one implementation, the second prompt word can be preset as a fixed list of operations that corresponds one-to-one with each first prompt word; in another implementation, the second prompt word can be dynamically generated based on the context information of the current AI skill. For example, when the AI ​​skill is "weather query", the second area can display quick operations such as "today's weather" and "weather for the next three days".

[0040] The following specific example illustrates this embodiment: When user A invokes the AI ​​interaction interface through a preset trigger operation, a first interaction interface is displayed on the screen. This first interaction interface is divided into two main areas: a first area and a second area. For example... Figure 2 The first area shown can be located at the top of the first interactive interface, displaying the first prompt "Device control too troublesome? One sentence does it all", and the AI ​​skill corresponding to the first prompt is device control; the second area is located below the first area, displaying second prompts such as "Turn the air conditioner down" and "Please turn on the air conditioner", providing specific instructions that user A may want to execute without requiring user A to perform additional hierarchical jumps or input.

[0041] This embodiment achieves hierarchical information display by showcasing a first interactive interface comprising a first area and a second area on the display screen. The first area displays a first prompt to indicate an AI skill, while the second area displays a second prompt to indicate a shortcut operation corresponding to the AI ​​skill. This design clearly separates skill categories and specific operation instructions on the same screen, allowing users to intuitively distinguish information levels by area location and avoiding confusion caused by information clutter.

[0042] In one feasible embodiment, to further enhance the distinction between the information hierarchy of the first and second areas, the hierarchical design of the spatial layout and visual specifications is used to ensure that the hierarchical relationship between AI skills (primary information) and quick operations (secondary information) is more clearly perceived visually, reducing user confusion. Specifically, the first area is located in the preset display area of ​​the first interactive interface, and the second area is located below the first area; and / or, the font size of the second prompt is smaller than the font size of the first prompt.

[0043] In this embodiment, the preset display area refers to the display range that is pre-planned, allocated and fixed for specific information content in the display interface. The specific preset display area is not limited. It can be located in the top area of ​​the display interface, for example, occupying the first third of the screen height, in order to conform to the user's top-down reading habits; or, the preset display area can also be located in the center area of ​​the display interface as a visual focus, ensuring that the position of the first area in the interface is relatively fixed and prominent, making it easy for users to quickly locate AI skill information.

[0044] The second area is located below the first area, meaning that in the vertical direction, the visual position of the second area is lower than that of the first area. The second area can be arranged close to the bottom edge of the first area to form a close visual connection; or, there can be a certain vertical distance between the second area and the first area to maintain visual separation, while the spatial subordinate relationship implies that the information displayed in the second area is a supplement or refinement of the information in the first area.

[0045] Font size refers to the visual size of text characters when displayed. The font size of the second prompt word is smaller than that of the first prompt word. The specific method is not limited here. For example, the font size of the second prompt word can be set to 0.7 to 0.9 times that of the first prompt word to create a clear visual difference. Alternatively, the second prompt word can use a preset secondary text font size, such as the body text font size, while the first prompt word uses the main title font size. By using the difference in visual weight of font size, the primary and secondary relationship of information can be conveyed intuitively, guiding users to pay priority to the first prompt word.

[0046] This embodiment transforms the logical abstract relationship into a perceptible visual geometric relationship by differentiating the spatial layout and visual specifications of the first and second regions, thereby improving the user's cognitive fluency and facilitating user operation.

[0047] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description and will not be repeated hereafter. In addition, the AI ​​interaction method further includes steps S40-S50: Step S40: In response to the triggering operation of the second prompt word, the second prompt word is parsed to obtain the operation instruction corresponding to the second prompt word, and the operation instruction is sent to the corresponding target device; When a user triggers an action on the second prompt word displayed in the second area of ​​the display interface, the action is captured. This action may include, but is not limited to, the user's click, long press, voice command confirmation, or gesture operation. Its purpose is to provide the user with an intuitive and convenient entry point to launch the shortcut function associated with the second prompt word.

[0048] The second prompt word is parsed to accurately extract the user's intent and related entity information from its natural language form. The specific parsing process is not limited here and can be implemented using various technologies. For example, a built-in natural language processing module can perform lexical analysis, syntactic analysis, and semantic understanding on the prompt word to extract the user's intent and relevant entity information; alternatively, a preset rule engine can be used to directly map specific second prompt words to predefined instruction templates or parameter sets. For instance, when the second prompt word is "turn on the living room light," the parsing process will identify "turn on" as the intent and "living room light" as the target device.

[0049] After parsing the second prompt word, based on the parsing result, an operation instruction corresponding to the second prompt word is obtained from a preset instruction library or through a dynamic generation mechanism. This operation instruction is a standardized machine language command that can be directly recognized and executed by the target device, containing information such as the specific operation type, target object, and execution parameters. The method of generating the operation instruction is not limited here. In one feasible implementation, the corresponding executable operation instruction can be matched and obtained from a preset instruction library based on the intent and entity identified in the parsing result. For example, the parsing result of "turn on the living room light" can be converted into an API call instruction. In another feasible implementation, the parameters in the parsing result can be filled into a predefined instruction template to dynamically generate a specific operation instruction.

[0050] Based on the device information in the second prompt or a pre-established device binding relationship, the system identifies and determines the target device for the operation and sends the operation command to the target device. The target device is a specific physical or virtual device instance located in the smart home environment capable of receiving and executing operation commands. This includes, but is not limited to, home appliances such as air conditioners, refrigerators, washing machines, smart lights, and smart curtains. It is the ultimate executor of the operation command and can establish a connection with the AI ​​interaction system through IoT communication protocols. Command transmission can be based on various communication protocols and network topologies, without limitation. For example, commands can be sent to smart home devices via wireless communication protocols such as Wi-Fi, Bluetooth, and Zigbee; or commands can be sent to a cloud server via a local area network (LAN) or wide area network (WAN), and then forwarded to the target device by the server.

[0051] Step S50: Display the execution result of the operation command.

[0052] After receiving the operation command, the target device executes the corresponding device action and feeds back the result of the action to the AI ​​interaction system. The execution result of the operation command is displayed on the screen, providing the user with real-time feedback so that the user knows whether the operation was successful and the current status of the device.

[0053] The execution result can be a success or failure message, or a real-time update of the device status; there are no restrictions on this. The display method of the execution result can be diverse. For example, a pop-up message such as "Living room lights are on" can appear on the display interface; or, the color and icon status of interface elements can be changed to indicate changes in device status; the result can also be announced to the user via voice broadcast; there are no restrictions on this either.

[0054] This embodiment simplifies the entire process from triggering a shortcut to executing the command and receiving feedback from a traditional multi-step operation into a single-point triggered closed-loop process, improving interaction efficiency. Moreover, by pre-setting the parsing logic and device binding relationship during the prompt display stage, users can easily control smart devices without having to remember complex device names or command formats.

[0055] As a specific implementation, when a user taps the second prompt word "Increase Temperature" in the second area, the system responds to this trigger by parsing "Increase Temperature," identifying "Increase" as the intent (to increase) and "Temperature" as the entity (target parameter). Combining this with the context information that the current AI skill is "Smart Air Conditioner," the system determines that the user's intent is to increase the air conditioner's temperature. Based on this parsing result, a corresponding operation command is generated. Simultaneously, based on the user's preset device binding relationship or through device discovery services, the system automatically identifies the "corresponding target device" in the current scenario as the smart air conditioner in the living room. Subsequently, this operation command is sent to the smart air conditioner, which receives and executes the command, for example, increasing the set temperature by 1 degree Celsius. After the command is executed, the smart air conditioner returns an execution status to the AI ​​interaction system. Upon receiving this status, a brief prompt message will pop up on the display interface, such as "Air conditioner temperature increased by 1 degree," or the current temperature value of the air conditioner displayed on the interface will be updated, thus showing the execution result of the operation command.

[0056] In one feasible embodiment, the first interactive interface further includes a third area; the AI ​​interaction method further includes: Step S60: In response to the triggering operation of the second prompt word, obtain the parsing process and parsing result corresponding to the second prompt word; In this embodiment, the first interactive interface also includes a third area. This third area is a dedicated visualization area within the first interactive interface for displaying the AI ​​analysis process and results. It typically presents the AI's thought process and reasoning in real-time using text, icons, or a timeline, providing users with visual feedback on the AI ​​analysis process and results. In this embodiment, the third area can be a fixed panel within the first interactive interface, for example, located below or to the side of the first or second area, and always visible; alternatively, it can be implemented as a dynamic overlay or collapsible area, expanding as needed only after the user triggers a specific operation. No specific limitations are imposed here.

[0057] The parsing process is a visual representation of the intermediate processing steps that convert the second prompt word into an operation command. This includes, but is not limited to, the display of the intent recognition result, entity matching process, semantic disambiguation logic, and other internal reasoning chains, enabling users to understand how AI derives specific operation intentions from natural language input. The parsing result is structured information output after the parsing process is completed, including the identified user intent type, extracted key entity parameters, and generated operation suggestions.

[0058] In this embodiment, in response to a trigger operation on the second prompt word, the parsing process and parsing result corresponding to the second prompt word are obtained. The trigger operation may include, but is not limited to, user interaction behaviors such as clicking, long-pressing, swiping, or voice commands on the second prompt word. When such a trigger operation is received, the text content of the second prompt word or its associated semantic information is sent as input to a preset model for processing. The preset model processes the input data, and the specific processing steps are not limited here. For example, they may include, but are not limited to, natural language understanding, intent recognition, entity extraction, semantic disambiguation, etc., to obtain the processing steps (i.e., the parsing process) and the final understanding result.

[0059] Step S70: Display the parsing process and parsing results in the third area, and obtain the corresponding operation instructions based on the parsing results; and / or display operation cards based on the parsing results. The operation cards are used to display recommended operations, and obtain the corresponding operation instructions based on the operation confirmation.

[0060] The third area displays the analysis process and results. The specific display format is not limited here. For example, the analysis process can be presented in the form of a structured text chain, such as "Intent recognition: Adjust temperature; Entity recognition: Living room air conditioner; Parameter extraction: 26 degrees", clearly showing the AI's thinking path. The analysis results can be directly displayed as the AI's final understanding of the user's command, such as "Target device: Living room air conditioner, Operation: Set temperature 26 degrees", or highlight key recognition information.

[0061] And / or, based on the parsing results, operation cards are displayed. Operation cards are visual interactive elements displayed in card form within a third area or a specific pop-up window. They are used to centrally present key information about recommended operations (such as operation name, target device, and expected effect) and provide confirmation or cancellation entry points. The corresponding operation instruction is obtained based on the user's confirmation of the operation card. For example, one or more operation cards may be displayed in the third area, each clearly listing a recommended operation, such as "turn on the living room air conditioner" or "turn on the bedroom air conditioner." In specific implementations, these operation cards may also include detailed information such as the target device icon and a preview of the expected effect of the operation. The corresponding operation instruction is only obtained and generated after the user confirms one of the cards by clicking, selecting, or swiping.

[0062] The following is a specific example to illustrate this embodiment. When a user clicks on the second prompt word "increase air conditioning temperature" in the second area, in response to this trigger operation, the system first obtains the AI's parsing process and result for the instruction "increase air conditioning temperature". For example, the AI ​​parsing module may identify the user's intent as "adjust device parameters", the entity as "air conditioner", and the operation as "increase temperature", ultimately obtaining the result "increase air conditioning temperature". The parsing process and result are displayed in real time in the third area of ​​the first interactive interface. For example, the third area may display: "AI parsing: intent recognition: adjust temperature; entity recognition: air conditioner; operation: increase". In one feasible embodiment, after obtaining the parsing result, the operation instruction "increase air conditioning temperature" can be obtained based on the parsing result; in another feasible embodiment, such as Figure 3 As shown, if a user has multiple air conditioners in their home (such as a living room air conditioner and a bedroom air conditioner), the AI ​​may not be able to determine which one it is. Based on the analysis results, it will display operation cards in the third area. Two operation cards will be displayed in the third area: one showing "Raise the living room air conditioner temperature" and the other showing "Raise the bedroom air conditioner temperature". The user can click to select the operation card "Raise the living room air conditioner temperature" to confirm and obtain the corresponding operation command. For example, it can send a command to the living room air conditioner to raise the temperature and prepare to execute it.

[0063] In this embodiment, the parsing process and results corresponding to the second prompt word are displayed in a third area within the first interactive interface. This makes the AI's internal decision-making logic transparent to the user, significantly enhancing interpretability and allowing users to intuitively understand how the AI ​​maps natural language prompt words to specific operational intentions, thereby increasing user trust in the AI ​​interaction system. The third area coexists with the first and second areas within the same interactive interface, eliminating the need for users to switch interfaces when viewing the parsing results, maintaining the continuity and contextual consistency of the interaction, and optimizing the user experience.

[0064] Based on the first and / or second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the first and / or second embodiments described above can be referred to the above description and will not be repeated hereafter. In addition, the AI ​​interaction method further includes step S80: In step S80, in response to the triggering operation of the AI ​​shortcut entry, the second interactive interface corresponding to the AI ​​shortcut entry is displayed. The second interactive interface displays a third prompt word and a fourth prompt word. The third prompt word is used to indicate the AI ​​skills that can be used, and the fourth prompt word is used to indicate the shortcut operation corresponding to the AI ​​skills.

[0065] The fourth area is a dedicated section of the first interactive interface for displaying AI shortcuts. It serves as a navigation area supporting quick switching between multiple skills. This area can be located in a fixed position on the first interactive interface, such as the bottom navigation bar, sidebar, or top toolbar, or it can be a collapsible or expandable floating window that appears when needed and hides when not. The purpose of the fourth area is to provide a unified and easily accessible entry point, enabling users to quickly switch between different AI skills.

[0066] AI shortcuts, displayed in the fourth area, are triggerable elements used to quickly access the dedicated interfaces of specific AI skills. Each shortcut corresponds to a specific AI skill (such as "Deep Thinking" or "Scene Generation"). Once triggered, users can directly jump to the dedicated interactive interface for that skill, without having to navigate through hierarchical menus. This serves as an interactive node for rapid context switching between multiple skills. These shortcuts can be presented as icons, text links, buttons, or cards, for example, corresponding to AI skills such as "Smart Home Control," "Schedule Management," and "Information Query." AI shortcuts can also be dynamically generated shortcuts intelligently recommended based on user frequency or preferences, providing users with a quick channel to access specific AI skills and simplifying navigation.

[0067] In response to the triggering of the AI ​​shortcut, a completely new and independent interactive interface, namely the second interactive interface, is generated and displayed based on the triggered AI shortcut. The second interactive interface can be a full-screen view, or a pop-up window whose content is entirely focused on the selected AI skill. Alternatively, it can be a part of the current interface with content replaced, but it still maintains its logical independence, for example, through animated transitions or hierarchical switching.

[0068] The third prompt is text information displayed in the second interactive interface that indicates the AI ​​skill corresponding to the current dedicated interface. In the second interactive interface, it is used to clearly identify the specific skill context. This prompt can be the name of the skill, such as "Smart Home Control" or "Deep Thinking," or it can be an icon representing the skill, or a brief description of the skill's function, to help users quickly understand the purpose of the current interface. The fourth prompt is text information displayed in the second interactive interface that indicates the specific shortcut operation corresponding to the current dedicated AI skill. It is customized for the specific skill scenario of the second interactive interface, reflecting the dedicated operation options within that skill domain. This prompt can be commonly used, high-frequency operation commands under that skill, such as "Turn on the living room lights," "Play music," or "Set an alarm clock," or it can be a list of function options provided by the skill, such as "Generate an image," "Compose an email," or "Check the weather."

[0069] The following is an illustration using a specific example. Assume a user is using a smart home AI assistant application. The application displays its first interactive interface, as shown in the attached image. Figure 4 As shown, at the bottom of the first interactive interface, there is a fourth area that displays multiple AI shortcuts, such as... Figure 4 The page displays quick access links at the bottom such as "Deep Thinking," "Scenario Generation," and "Product Documentation." When a user clicks the "Product Q&A" AI quick access link in the fourth area, the system responds to this trigger and immediately displays a brand-new second interactive interface. This second interactive interface is specifically designed for the "Product Q&A" skill, such as... Figure 5 As shown, in this second interactive interface, the third prompt is displayed as "Do you have any questions during product use?", which clearly indicates that the AI ​​skill focused on by the current interface is to answer product-related questions. At the same time, the fourth prompt will display quick operations related to smart home, such as "How to save electricity when the air conditioner is heating" and "How to turn on the air conditioner".

[0070] This embodiment achieves rapid and intuitive switching between multiple AI skills by adding a fourth area to the first interactive interface to display AI shortcuts and responding to trigger operations to display a structurally isomorphic second interactive interface. This shortens the operation path and improves interaction efficiency. Simultaneously, because the second interactive interface provides an independent display space for specific AI skills, it ensures clear isolation of skill context, avoids confusion between different skill commands, and reduces the user's cognitive load and learning cost.

[0071] Based on the first, second, and / or third embodiments of this application, in the fourth embodiment of this application, the content that is the same as or similar to the first, second, and / or third embodiments described above can be referred to the above description and will not be repeated hereafter. In addition, the AI ​​interaction method further includes step S90: Step S90: Display the target image corresponding to the AI ​​skill in the first area.

[0072] The target image is a visual graphic identifier displayed in the first area that corresponds to the AI ​​skill. It is used to represent the type of AI skill in a non-textual form and typically includes visual elements such as a person, abstract icon, or animated character. It works in conjunction with the first cue word to enhance the skill's recognizability and memorability. The specific form and content of the target image are not limited here. It can be an icon, abstract graphic, cartoonish character head, or a miniature scene related to the skill theme. For example, for an AI skill of "weather query," the target image could be a combination icon of clouds and the sun; for an AI skill of "intelligent schedule management," the target image could be a calendar or clock graphic.

[0073] The target image is presented in a visible form in the first area of ​​the first interactive interface. The specific display position is not limited here and can be achieved in a variety of ways. For example, the target image can be used as the background image of the first prompt word, placed to the left or right of the first prompt word, or it can be integrated with the first prompt word to form a unified visual element.

[0074] This embodiment displays the target image corresponding to the AI ​​skill in the first area, which enhances the user's recognition efficiency and memory accuracy of the AI ​​skill. It utilizes the advantages of human visual processing, enabling users to locate the target skill more quickly in multi-skill scenarios, and reduces the confusion that may be caused by pure text prompts. It enhances the universality and adaptability of the AI ​​interaction system and improves the overall user experience.

[0075] In one feasible embodiment, the target image includes a base image and a marker image, wherein the marker image of the target image is a preset image corresponding to the AI ​​skill.

[0076] A base image is an image element that serves as the visual foundation or common part of a target image. This base image can be a unified human silhouette, the main body of a brand mascot, or a standardized headshot frame. It can also be a background pattern or texture with a unified color scheme or style characteristics, providing a unified visual style and identity recognition.

[0077] Iconic images are specific visual identifiers (i.e., preset images corresponding to different AI skills) used to distinguish different AI skills within a target image. Preset images can be fixed image resources that have been pre-bound to a specific AI skill. Iconic images can be small icons superimposed on a base image as additional elements, such as a brain or light bulb icon to indicate the "deep thinking" skill, or a house or scene icon to indicate the "scene generation" skill.

[0078] As one specific implementation method, see the attached document. Figure 6 As shown, the base image can be a circular image. When displaying the AI ​​skill of "recipe recommendation," the first area will display the first prompt, "Always burning the recipes I find online?". To the right of the first prompt in this first area, an image as shown in the attached image will be displayed. Figure 6 The target image corresponding to the "Recipe Recommendation" skill shown is as follows: Figure 6 As shown, the icon images corresponding to the recipe recommendation skill are a hat and a spoon, which are superimposed to form the image shown in the attached image. Figure 6 The target image shown. The symbolic image corresponding to after-sales service skills is a wrench, which is superimposed on the base image to obtain the image shown in the attached figure. Figure 7 The target image shown.

[0079] This embodiment adopts a modular design of basic elements and markers. When new AI skills are needed, only new marker images need to be designed or configured and combined with existing basic images, without redesigning the entire image, thus reducing the visual design cost and iteration cycle for multiple skills. In addition, the basic image serves as the background image, which is quickly recognized and categorized by the user as the AI ​​assistant image, while the marker image serves as the foreground image, which the user uses to distinguish specific functions. This hierarchical visual information architecture reduces the number of information units that the user needs to process at the same time, thus reducing cognitive load.

[0080] This application also provides an AI interaction device, please refer to... Figure 8 The AI ​​interaction device includes: The display module 10 is used to display a first interactive interface in the display interface in response to the trigger operation of AI interaction; wherein the first interactive interface includes a first area and a second area; The display module 10 is further configured to display a first prompt word in the first area, wherein the first prompt word is used to indicate the available AI skills; The display module 10 is further configured to display a second prompt word in the second area, wherein the second prompt word is used to indicate a shortcut operation corresponding to the AI ​​skill.

[0081] Optionally, the AI ​​interaction device further includes: The parsing module is used to respond to the triggering operation of the second prompt word, parse the second prompt word, obtain the operation instruction corresponding to the second prompt word, and send the operation instruction to the corresponding target device; The display module 10 is also used to display the execution result of the operation instruction.

[0082] Optionally, the first interactive interface further includes a third area; the AI ​​interactive device further includes: The acquisition module is used to acquire the parsing process and parsing result corresponding to the second prompt word in response to the triggering operation of the second prompt word; The display module 10 is also used to display the parsing process and the parsing result in the third area, obtain the corresponding operation instructions based on the parsing result; and / or display an operation card based on the parsing result, the operation card being used to display recommended operations, and obtain the corresponding operation instructions based on operation confirmation.

[0083] Optionally, the first interactive interface further includes a fourth area, which displays AI shortcuts; the AI ​​interactive device further includes: The display module 10 is also used to respond to the triggering operation of the AI ​​shortcut entry by displaying a second interactive interface corresponding to the AI ​​shortcut entry, and displaying a third prompt word and a fourth prompt word in the second interactive interface. The third prompt word is used to indicate the AI ​​skill that can be used, and the fourth prompt word is used to indicate the shortcut operation corresponding to the AI ​​skill.

[0084] Optionally, the AI ​​interaction device further includes: The display module 10 is also used to display the target image corresponding to the AI ​​skill in the first area.

[0085] Optionally, the target image includes a base image and a marker image, wherein the marker image of the target image is a preset image corresponding to the AI ​​skill.

[0086] Optionally, the first area is located in a preset display area of ​​the first interactive interface, and the second area is located below the first area; and / or, The font size of the second prompt word is smaller than the font size of the first prompt word.

[0087] The AI ​​interaction device provided in this application, employing the AI ​​interaction method in the above embodiments, can provide a concise and clear AI interaction interface to meet users' needs for efficient use. Compared with the prior art, the beneficial effects of the AI ​​interaction device provided in this application are the same as those of the AI ​​interaction method provided in the above embodiments, and other technical features in the AI ​​interaction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0088] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the AI ​​interaction method in Embodiment 1 above.

[0089] The following is for reference. Figure 9 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of this application. The electronic devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0090] like Figure 9 As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. The communication device 1009 allows the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the diagrams show electronic devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0091] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0092] The electronic device provided in this application, employing the AI ​​interaction method in the above embodiments, can provide a concise and clear AI interaction interface to meet users' needs for efficient use. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the AI ​​interaction method provided in the above embodiments, and other technical features of this electronic device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0093] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0094] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0095] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the AI ​​interaction method in the above embodiments.

[0096] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0097] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0098] The aforementioned computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to implement the AI ​​interaction methods described in the various embodiments above.

[0099] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 operation, or using a combination of dedicated hardware and computer instructions.

[0101] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0102] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described AI interaction method. This provides a concise and clear AI interaction interface to meet users' needs for efficient use. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the AI ​​interaction method provided in the above embodiments, and will not be repeated here.

[0103] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the AI ​​interaction method described above.

[0104] The computer program product provided in this application can provide a simple and clear AI interactive interface to meet users' needs for efficient use. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the AI ​​interaction method provided in the above embodiments, and will not be repeated here.

[0105] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. An AI interaction method, characterized in that, The AI ​​interaction method includes: In response to the triggering operation of AI interaction, a first interactive interface is displayed in the display interface; wherein, the first interactive interface includes a first area and a second area; A first prompt word is displayed in the first area, wherein the first prompt word is used to indicate the AI ​​skills that can be used; A second prompt word is displayed in the second area, wherein the second prompt word is used to indicate a shortcut operation corresponding to the AI ​​skill.

2. The AI ​​interaction method as described in claim 1, characterized in that, The AI ​​interaction method also includes: In response to the triggering operation of the second prompt word, the second prompt word is parsed to obtain the operation instruction corresponding to the second prompt word, and the operation instruction is sent to the corresponding target device; Display the execution result of the operation command.

3. The AI ​​interaction method as described in claim 1, characterized in that, The first interactive interface further includes a third area; the AI ​​interaction method further includes: In response to the triggering operation of the second prompt word, obtain the parsing process and parsing result corresponding to the second prompt word; The third area displays the parsing process and the parsing result, and obtains the corresponding operation instructions based on the parsing result; and / or displays operation cards based on the parsing result, the operation cards being used to display recommended operations, and obtains the corresponding operation instructions based on operation confirmation.

4. The AI ​​interaction method as described in claim 1, characterized in that, The first interactive interface also includes a fourth area, which displays AI shortcuts; the AI ​​interaction method further includes: In response to the triggering operation of the AI ​​shortcut entry, a second interactive interface corresponding to the AI ​​shortcut entry is displayed. In the second interactive interface, a third prompt word and a fourth prompt word are displayed. The third prompt word is used to indicate the AI ​​skills that can be used, and the fourth prompt word is used to indicate the shortcut operation corresponding to the AI ​​skill.

5. The AI ​​interaction method as described in claim 1, characterized in that, The AI ​​interaction method also includes: The first area displays the target image corresponding to the AI ​​skill.

6. The AI ​​interaction method as described in claim 5, characterized in that, The target image includes a base image and a landmark image, wherein the landmark image of the target image is a preset image corresponding to the AI ​​skill.

7. The AI ​​interaction method as described in claim 1, characterized in that, The first area is located in the preset display area of ​​the first interactive interface, and the second area is located below the first area; and / or, The font size of the second prompt word is smaller than the font size of the first prompt word.

8. An AI interactive device, characterized in that, The AI ​​interaction device includes: The display module is used to respond to the trigger operation of AI interaction and display a first interactive interface in the display interface; wherein, the first interactive interface includes a first area and a second area; The display module is further configured to display a first prompt word in the first area, wherein the first prompt word is used to indicate the available AI skills; The display module is further configured to display a second prompt word in the second area, wherein the second prompt word is used to indicate a shortcut operation corresponding to the AI ​​skill.

9. An electronic device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the AI ​​interaction method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the AI ​​interaction method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the AI ​​interaction method as described in any one of claims 1 to 7.

Images