Conversation method and electronic equipment

Abstract

The embodiment of the invention provides a dialogue method and electronic equipment, and the method comprises the steps: displaying an interface of a main session in a first application, the main session being a session between a user and a first intelligent assistant provided by the first application; in response to a first operation of the user in the interface of the main session, displaying an interface of at least one independent session in the first application, the at least one independent session including a first independent session, the first independent session being a session between the user and a second intelligent assistant, the second intelligent assistant calls the intelligent dialogue service for the first application aiming at the first scene. According to the dialogue method and the electronic equipment provided by the embodiment of the invention, the use efficiency of the intelligent voice assistant can be improved.

Description

[0001] This application claims priority to Chinese Patent Application No. 202410807790.8, filed on June 20, 2024, entitled "Method for Displaying an Interface, Display Device and Electronic Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of display technology, and more specifically, to a dialogue method and an electronic device. Background Technology

[0003] The dialogue interface of smart voice assistants on electronic devices is often easily interrupted by multi-turn mechanisms. For example, if a user's current question is about travel, and in the next dialogue the user asks about education, the travel question will be interrupted. This makes it difficult for the smart voice assistant to focus on providing answers in a single area. If a user needs to retrieve historical questions and answers in a specific area, they have to search through the history, impacting the efficiency of using the smart voice assistant. Summary of the Invention

[0004] This application provides a dialogue method and an electronic device that can improve the efficiency of using a smart assistant.

[0005] In a first aspect, a dialogue method is provided, the method comprising: displaying an interface of a main session in a first application, the main session being a dialogue between a user and a first intelligent assistant provided by the first application; and, in response to a first operation by the user in the interface of the main session, displaying an interface of at least one independent session in the first application, the at least one independent session including a first independent session, the first independent session being a dialogue between the user and a second intelligent assistant, the second intelligent assistant being an intelligent dialogue service invoked by the first application for a first scenario.

[0006] In the embodiments provided in this application, in the first application, the user enters the interface of the first independent session from the main session interface through the first operation. The interface of the first independent session is the session interface of the intelligent dialogue service invoked by the first application for the first scenario. In this way, the user can enjoy more focused services in the interface of the first independent session. For example, the user can ask questions to the second intelligent assistant for the first scenario. In addition, the user can search for the historical messages of the first independent session in the interface of the first independent session, which is conducive to information classification and thus can improve the efficiency of the first application, such as the intelligent voice assistant, and enhance the user experience.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the second intelligent assistant is an intelligent dialogue service invoked by the first application for the first scenario, including: the second intelligent assistant is an intelligent dialogue service provided by the first application for the first scenario, or the second intelligent assistant is an intelligent dialogue service provided by the second application for the first scenario, wherein the first application is different from the second application.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the first operation includes: the user inputting a question in the interface of the main session, the question being related to the first scenario.

[0009] In the embodiments provided in this application, by entering a question in the main conversation interface to enter the interface of an independent conversation, it is convenient to provide relevant intelligent dialogue services based on the questions that the user is concerned about, thereby further improving the user's experience with the first application.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, after the second intelligent assistant displays the answer to the question in the interface of the main session, the user performs a second operation on the answer, and in response to the second operation, the dialog box interface of the first independent session is displayed in the first application.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the second operation includes: the user clicking on the content indication area of ​​the answer or the indication area of ​​the second intelligent assistant.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the first operation includes: entering the name of the second smart assistant on the interface of the main session.

[0013] In the embodiments provided in this application, by entering the name of the smart assistant to enter the corresponding independent conversation interface, the user can be provided with the services they need more accurately, thereby further improving the user experience.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the first operation further includes: inputting a question to be asked to the second intelligent assistant at the interface of the main session.

[0015] In the embodiments provided in this application, by entering the name of the smart assistant and asking a question to the smart assistant, the user can enter the corresponding independent conversation interface, which can more accurately provide the services needed by the user, further improve the user experience, and facilitate providing the answer to the question to the user while providing the independent conversation interface, thereby improving the efficiency of the first application.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the first smart assistant recommends multiple smart assistants in the interface of the main session, and the second smart assistant is included among the multiple smart assistants. The first operation includes: selecting the second smart assistant recommended by the first smart assistant.

[0017] In the embodiments provided in this application, multiple smart assistants are directly displayed in the main conversation interface, which can present the intelligent dialogue services provided by the first application to the user in a more intuitive way, so that the user can make a selection and thus further improve the user experience.

[0018] In conjunction with the first aspect, in some implementations of the first aspect, the recommendation is determined based on the history of the main session and / or the history of the independent session.

[0019] In the embodiments provided in this application, the name of the smart assistant presented to the user is determined based on the history of the main session and / or the history of the independent session, which enables the recommended smart assistant to better meet the user's expectations.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the first intelligent assistant provides multiple scenario suggestions in the interface of the main session, the multiple scenario suggestions including questions about the first scenario; the first operation includes: the user selecting the question about the first scenario.

[0021] In the embodiments provided in this application, the first application directly presents multiple scenario suggestions to the user, including questions about the first scenario. The user can enter the corresponding independent conversation interface by selecting the question. The application can provide the user with corresponding intelligent dialogue services based on the question the user wants to ask, and the user does not need to manually input the question they want to ask, making the operation more convenient.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the scenario suggestion is determined based on the history of the main session and / or the history of the independent session.

[0023] In the embodiments provided in this application, the scenario suggestions are determined based on the history of the main session and / or the history of the independent session, which enables the recommended scenario suggestions to be closer to the questions that the user expects to understand.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: displaying an interface for a suggestion card in the first application, wherein the first smart assistant recommends multiple smart assistants in the interface for the suggestion card, and the second smart assistant is included among the multiple smart assistants; and displaying an interface for the first independent session in response to a user selecting the second smart assistant.

[0025] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: displaying an interface for a suggestion card in the first application, wherein the first intelligent assistant provides multiple scenario suggestions in the interface for the suggestion card, the multiple scenario suggestions including a question about the first scenario; and displaying an interface for the first independent session in response to a user selecting a question about the first scenario.

[0026] In the embodiments provided in this application, users can also select the smart assistant recommended in the suggestion card of the first application to enter the corresponding independent session interface, providing multiple ways for users to enter the independent session and further improving the efficiency of using the first application.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the first intelligent assistant's answers in the main session are related to the history of the first independent session.

[0028] In the embodiments provided in this application, the answers provided by the first intelligent assistant in the main session are related to the history of the first independent session, which can improve the relevance and accuracy of the answers provided by the first intelligent assistant, making the answers provided by the first intelligent assistant more in line with user expectations.

[0029] In conjunction with the first aspect, in some implementations of the first aspect, the second intelligent assistant's responses in the first independent session are related to the history of the main session.

[0030] In the embodiments provided in this application, the answers provided by the second intelligent assistant in the first independent session are related to the history of the main session, which can improve the relevance and accuracy of the answers provided by the second intelligent assistant, making the answers provided by the second intelligent assistant more in line with the user's expectations.

[0031] In conjunction with the first aspect, in some implementations of the first aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, which is an intelligent dialogue service invoked by the first application for the second scenario, and the answers of the second intelligent assistant in the first independent session are related to the history of the second independent session.

[0032] In the embodiments provided in this application, the answers of the second intelligent assistant in the first independent session are related to the history of the second independent session, which can improve the relevance and accuracy of the answers provided by the second intelligent assistant, making the answers provided by the second intelligent assistant more in line with the user's expectations.

[0033] In conjunction with the first aspect, in some implementations of the first aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, the third intelligent assistant being an intelligent dialogue service invoked by the first application for the second scenario, and the first independent session and the second independent session are displayed simultaneously in the first application.

[0034] In conjunction with the first aspect, in some implementations of the first aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, the third intelligent assistant being an intelligent dialogue service invoked by the first application for the second scenario, and the first independent session and the second independent session being switched and displayed in the first application through the user's third operation.

[0035] In conjunction with the first aspect, in some implementations of the first aspect, the history of the first independent session can be viewed in the interface of the first independent session.

[0036] In conjunction with the first aspect, in some implementations of the first aspect, the second interface includes at least one of the following: a welcome message, an icon or name of the second smart assistant, an icon or name of the service provider of the second smart assistant, a functional introduction of the first independent session, and an exit control for the first independent session.

[0037] In a second aspect, a dialogue device is provided, comprising: a processing module configured to display an interface of a main session in a first application, the main session being a conversation between a user and a first intelligent assistant provided by the first application; the processing module is further configured to, in response to a first operation by the user in the interface of the main session, display an interface of at least one independent session in the first application, the at least one independent session including a first independent session, the first independent session being a conversation between the user and a second intelligent assistant, the second intelligent assistant being an intelligent dialogue service invoked by the first application for a first scenario.

[0038] In conjunction with the second aspect, in some implementations of the second aspect, the second intelligent assistant is an intelligent dialogue service invoked by the first application for the first scenario, including: the second intelligent assistant is an intelligent dialogue service provided by the first application for the first scenario, or the second intelligent assistant is an intelligent dialogue service provided by the second application for the first scenario, wherein the first application is different from the second application.

[0039] In conjunction with the second aspect, in some implementations of the second aspect, the first operation includes: the user inputting a question in the interface of the main session, the question being related to the first scenario.

[0040] In conjunction with the second aspect, in some implementations of the second aspect, the processing module is further configured to, after the user performs a second operation on the answer provided by the second intelligent assistant for the question in the interface of the main session, display the dialog box interface of the first independent session in the first application in response to the second operation.

[0041] In conjunction with the second aspect, in some implementations of the second aspect, the second operation includes: the user clicking on the content indication area of ​​the answer or the indication area of ​​the second intelligent assistant.

[0042] In conjunction with the second aspect, in some implementations of the second aspect, the first operation includes: entering the name of the second smart assistant in the interface of the main session.

[0043] In conjunction with the second aspect, in some implementations of the second aspect, the first operation further includes: inputting a question to be asked to the second intelligent assistant at the interface of the main session.

[0044] In conjunction with the second aspect, in some implementations of the second aspect, the first smart assistant recommends multiple smart assistants in the interface of the main session, and the second smart assistant is included among the multiple smart assistants. The first operation includes: selecting the second smart assistant recommended by the first smart assistant.

[0045] In conjunction with the second aspect, in some implementations of the second aspect, the recommendation is determined based on the history of the main session and / or the history of the independent session.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the first intelligent assistant provides multiple scenario suggestions in the interface of the main session, the multiple scenario suggestions including questions about the first scenario; the first operation includes: the user selecting the question about the first scenario.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the processing module is further configured to: display an interface for a suggestion card in the first application, wherein the first smart assistant recommends multiple smart assistants in the interface for the suggestion card, and the second smart assistant is included among the multiple smart assistants; and display an interface for the first independent session in response to the user selecting the second smart assistant.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, the processing module is further configured to display an interface of suggestion cards in the first application, wherein the first intelligent assistant provides multiple scenario suggestions in the interface of suggestion cards, the multiple scenario suggestions including questions about the first scenario; and display an interface of the first independent session in response to the user selecting a question about the first scenario.

[0049] In conjunction with the second aspect, in some implementations of the second aspect, the first intelligent assistant's answers in the main session are related to the history of the first independent session.

[0050] In conjunction with the second aspect, in some implementations of the second aspect, the second intelligent assistant's answers in the first independent session are related to the history of the main session.

[0051] In conjunction with the second aspect, in some implementations of the second aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, the third intelligent assistant being an intelligent dialogue service invoked by the first application for the second scenario, and the second intelligent assistant's answers in the first independent session being related to the history of the second independent session.

[0052] In conjunction with the second aspect, in some implementations of the second aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, the third intelligent assistant being an intelligent dialogue service invoked by the first application for the second scenario, and the first independent session and the second independent session are displayed simultaneously in the first application.

[0053] In conjunction with the second aspect, in some implementations of the second aspect, the at least one independent session further includes a second independent session, which is a session between the user and a third intelligent assistant, the third intelligent assistant being an intelligent dialogue service invoked by the first application for the second scenario, and the first independent session and the second independent session are switched and displayed in the first application through the user's third operation.

[0054] In conjunction with the second aspect, in some implementations of the second aspect, the history of the first independent session can be viewed in the interface of the first independent session.

[0055] In conjunction with the second aspect, in some implementations of the second aspect, the interface of the first independent session includes at least one of the following: a welcome message, the icon or name of the second smart assistant, the icon or name of the service provider of the second smart assistant, a description of the functions of the first independent session, and an exit control for the first independent session.

[0056] Thirdly, an electronic device is provided, including a processor and a memory, the memory for storing program instructions, and the processor for executing the program instructions stored in the memory to implement the method as described in the first aspect or any possible implementation thereof.

[0057] Fourthly, a chip system is provided, including a processor for reading instructions stored in a memory, wherein when the processor executes the instructions, the method described in the first aspect or any possible implementation thereof is implemented.

[0058] Fifthly, a computer program product is provided, the computer program product storing program instructions that, when the program instructions are run on a computer, cause the method described in the first aspect or any possible implementation thereof to be executed.

[0059] In a sixth aspect, a readable storage medium is provided, the readable storage medium storing program instructions that, when executed on a computer, cause the method described in the first aspect or any possible implementation thereof to be performed. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application;

[0061] Figure 2 This is a schematic diagram of the software structure of an electronic device provided in an embodiment of this application;

[0062] Figure 3 This is a schematic diagram of a dialogue method provided in an embodiment of this application;

[0063] Figures 4 to 12 This is a schematic diagram of the user interface provided in an embodiment of this application;

[0064] Figure 13 This is a schematic structural block diagram of the system architecture provided in the embodiments of this application;

[0065] Figure 14 This is a schematic structural block diagram of the dialogue device provided in the embodiments of this application;

[0066] Figure 15 This is a schematic structural block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0067] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0068] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0069] In the various embodiments of this application, the terms "first," "second," etc., are merely to indicate that multiple objects are different. For example, "first smart assistant" and "second smart assistant" are simply to indicate different smart assistants. They should not have any impact on the smart assistants themselves or their number, and the aforementioned "first," "second," etc., should not impose any limitations on the embodiments of this application.

[0070] The terms “including,” “comprising,” “having,” and variations thereof all mean “including but not limited to,” unless otherwise specifically emphasized.

[0071] For example, Figure 1 This is a schematic diagram of the hardware structure of an electronic device 100. The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, antenna 1, antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, a compass 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0072] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0073] Processor 110 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). Different processing units may be independent components or integrated into one or more processors. In some embodiments, electronic device 100 may also include one or more processors 110. The controller can generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution. In other embodiments, processor 110 may also include a memory for storing instructions and data. For example, the memory in processor 110 may be a cache memory. This memory can store instructions or data that processor 110 has just used or is reusing. If processor 110 needs to reuse the instruction or data, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the electronic device 100 in processing data or executing instructions.

[0074] In some embodiments, the processor 110 may include one or more interfaces. These interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM card interface, and / or a USB interface, etc. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used for data transfer between the electronic device 100 and peripheral devices.

[0075] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 100.

[0076] The charging management module 140 receives charging input from a charger. The charger can be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 receives charging input from the wired charger via the USB interface 130. In some wireless charging embodiments, the charging management module 140 receives wireless charging input via the wireless charging coil of the electronic device 100. While charging the battery 142, the charging management module 140 can also power the wearable device via the power management module 141.

[0077] The power management module 141 connects the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, providing power to the processor 110, internal memory 121, external memory, display screen 194, camera 193, and wireless communication module 160, etc. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance).

[0078] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0079] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be reused to improve antenna utilization.

[0080] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves via antenna 1, and perform filtering, amplification, and other processing on the received electromagnetic waves before transmitting them to a modem processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation via antenna 1. In some embodiments, at least some functional modules of the mobile communication module 150 may be housed in the processor 110. In some embodiments, at least some functional modules of the mobile communication module 150 and at least some modules of the processor 110 may be housed in the same device.

[0081] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLAN) (such as wireless fidelity (WiFi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via antenna 2, performs frequency modulation and filtering of the electromagnetic wave signals, and sends the processed signal to processor 110. The wireless communication module 160 can also receive signals to be transmitted from processor 110, perform frequency modulation and amplification, and convert them into electromagnetic waves for radiation via antenna 2.

[0082] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0083] Display screen 194 is used to display images, videos, etc. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-OLED, a quantum dot light-emitting diode (QLED), etc. The display screen 194 of electronic device 100 can be a flexible screen.

[0084] Electronic device 100 can perform shooting functions through ISP, camera 193, video codec, GPU, display 194, and application processor. ISP is used to process data fed back by camera 193.

[0085] Camera 193 is used to capture still images or videos. An object passes through the lens, generating an optical image that is projected onto a photosensitive element. The photosensitive element converts the light signal into an electrical signal, which is then passed to the ISP (Image Signal Processor) for conversion into a digital image signal. The ISP outputs the digital image signal to the DSP (Digital Signal Processor) for further processing. The DSP converts the digital image signal into standard image signals in formats such as RGB and YUV.

[0086] A digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals.

[0087] Video codecs are used to compress or decompress digital video. Electronic device 100 may support one or more video codecs.

[0088] NPU stands for Neural-Network (NN) Computing Processor. By drawing inspiration from the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can quickly process input information and continuously learn on its own.

[0089] The external storage interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external storage interface 120 to perform data storage functions. For example, music, video, and other files can be saved on the external memory card.

[0090] Internal memory 121 can be used to store one or more computer programs, which include instructions. Processor 110 can execute the instructions stored in internal memory 121, thereby causing electronic device 100 to perform the methods provided in some embodiments of this application, as well as various applications and data processing. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system; the program storage area may also store one or more applications (such as a gallery, contacts, etc.). The data storage area may store data created during the use of electronic device 100 (such as photos, contacts, etc.). In addition, internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as one or more disk storage components, flash memory components, universal flash storage (UFS), etc. In some embodiments, processor 110 can execute instructions stored in internal memory 121 and / or instructions stored in memory disposed in processor 110, thereby causing electronic device 100 to perform the methods provided in embodiments of this application, as well as other applications and data processing. Electronic device 100 can implement audio functions such as music playback and recording through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0091] The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, a barometric pressure sensor 180C, a magnetic sensor 180D, an accelerometer sensor 180E, a distance sensor 180F, a proximity sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, and a bone conduction sensor 180M, etc. The touch sensor 180K can be integrated into the aforementioned display screen 194, enabling the display screen to have touch functionality and display corresponding functions or images in response to touch operations. This display screen 194 can also be referred to as a touchscreen.

[0092] Figure 2 This is a software structure block diagram of an electronic device 100 according to an embodiment of this application. The layered architecture divides the software into several layers, each with a clear role and function. Layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: the application layer, the application framework layer, the system runtime and system libraries, and the kernel layer. The application layer may include a series of application packages.

[0093] like Figure 2As shown, the application layer can include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, and SMS.

[0094] The application framework layer provides application programming interfaces (APIs) and a programming framework for applications in the application layer. The application framework layer includes some predefined functions.

[0095] like Figure 2 As shown, the application framework layer may include a window manager, content provider, view system, phone manager, resource manager, notification manager, etc.

[0096] The window manager is used to manage windowed applications. It can retrieve screen size, determine the presence of a status bar, lock the screen, and capture screenshots, among other things.

[0097] Content providers store and retrieve data, making that data accessible to applications. This data may include videos, images, audio, made and received phone calls, browsing history and bookmarks, phone books, etc.

[0098] A view system includes visual controls, such as controls for displaying text and controls for displaying images. View systems can be used to build applications. A display interface can consist of one or more views. For example, a display interface including a text notification icon could include views for displaying text and views for displaying images.

[0099] The phone manager is used to provide communication functions for electronic device 100. For example, it manages call status (including connection and disconnection).

[0100] The file explorer provides applications with various resources, such as localized strings, icons, images, layout files, video files, and more.

[0101] The notification manager allows applications to display notifications in the status bar. These notifications can be used to deliver informational messages and can disappear automatically after a short pause, requiring no user interaction. For example, the notification manager can be used to notify users of completed downloads or message alerts. The notification manager can also display notifications as icons or scrolling text in the top status bar, such as notifications from background applications, or as dialog boxes on the screen. Examples include displaying text messages in the status bar, emitting sounds, vibrating electronic devices, and flashing indicator lights.

[0102] The system runtime includes core libraries and a virtual machine. The system runtime is responsible for system scheduling and management. This system can be HarmonyOS, Android, Windows, or Linux, etc., and this application does not limit it to any particular system.

[0103] The core library consists of two parts: one part is the functionalities that the Java language needs to call, and the other part is the system's core library.

[0104] The application layer and application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and application framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0105] System libraries can include multiple functional modules. For example: surface manager, media libraries, 3D graphics processing libraries (e.g., OpenGL ES), 2D graphics engines (e.g., SGL), etc.

[0106] The Surface Manager is used to manage the display subsystem and provides the blending of 2D and 3D layers for multiple applications.

[0107] The media library supports playback and recording of various common audio and video formats, as well as still image files. It supports multiple audio and video encoding formats, such as MPEG4, H.264, MP3, AAC, AMR, JPG, and PNG.

[0108] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0109] A 2D graphics engine is a graphics engine for 2D drawing.

[0110] The kernel layer is the layer between hardware and software. It contains display drivers, THP drivers, camera drivers, audio drivers, and sensor drivers. The THP driver implements the communication interface between the touchscreen and the system-on-chip (SoC) and controls the touchscreen timing, such as controlling the Serial Peripheral Interface (SPI) and Universal Serial Bus (USB) interfaces.

[0111] Figure 3 This is a flowchart illustrating a dialogue method provided in an embodiment of this application, which may include steps S310 to S320.

[0112] S310, the interface of the main session is displayed in the first application, which is a session between the user and the first intelligent assistant provided by the first application.

[0113] S320, in response to a first operation by the user in the main session interface, displaying an interface for at least one independent session in the first application, the at least one independent session including a first independent session, the first independent session being a session between the user and a second intelligent assistant, the second intelligent assistant being an intelligent dialogue service invoked by the first application for a first scenario.

[0114] For example, the first application can be a smart voice assistant application, a built-in application of an electronic device, or a third-party application downloaded by the user, such as a third-party application that can provide knowledge-based Q&A. The first smart assistant can be the functional part of the first application itself used to provide intelligent dialogue services to the user, and the conversation between the first smart assistant and the user can be managed by the first application.

[0115] This second intelligent assistant differs from the first intelligent assistant; it can be an intelligent dialogue service invoked by the first application. In one possible example, the second intelligent assistant can be an intelligent dialogue service provided by the first application for a first scenario. The second intelligent assistant can be a service configured within the first application, and it can be configured as an intelligent agent within the first application. The first application can be configured with multiple intelligent agents, which can be service assistants for different scenarios, such as knowledge Q&A, travel services, shopping, and writing. In a knowledge Q&A scenario, the multiple intelligent agents can each answer questions posed by the user on different topics. These multiple services can also include different services related to the same scenario. The multiple intelligent agents can be configured with knowledge content specific to the corresponding scenario to provide users with knowledge Q&A or services related to that scenario. The first application can invoke the services configured within the first application to provide the corresponding services to the user.

[0116] In another possible example, the second intelligent assistant can be an intelligent dialogue service provided by a second application for the first scenario, and this second application is different from the first application. The second application can be a third-party application configured in an electronic device, and the first application can be configured with an application programming interface (API) that can be used for the first application to interact with other third-party applications. The first application can call the second application through the API, and the second intelligent assistant of the second application can provide corresponding services to the user and be presented in the interface of the first application.

[0117] In one possible implementation, the first operation may include: the user entering a question related to the first scenario in the main session's interface. That is, in response to the user entering a question related to the first scenario in the main session's interface, the main session's interface may display the interface of at least one independent session.

[0118] For example, such as Figure 4 As shown in (a), the first application can be the smart voice assistant Xiao E, and the interface 410 can be the conversation interface between the user and the first smart assistant of the Xiao E application, that is, the main conversation interface. The user can click the voice ball control 413 to input questions by voice input, or the user can click the keyboard control 412 to input questions by text input, or the user can click the extended control 414 to select photos or files as input content, and extract the text content from the photos or files as the question content.

[0119] Figure 4 In the example shown, a user asks Xiao E, "What is the use of ChatGPT?" Based on this question, Xiao E provides an answer, which may include the content "ChatGPT can understand the user's query," and the name of the assistant providing the answer, "Knowledge Q&A Assistant A" 411. "Knowledge Q&A Assistant A" can be a service for knowledge Q&A scenarios, and it can be the aforementioned second intelligent assistant. The answer may also include a prompt, "The following answer is provided by Knowledge Q&A Assistant A," which can be displayed above the answer content. The assistant name can be displayed below the question answer content. The user can click on the assistant name "Knowledge Q&A Assistant A" 411 to enter the conversation interface of "Knowledge Q&A Assistant A," or the dialog box interface of the first independent conversation, to view the specific answer content provided by "Knowledge Q&A Assistant A." The location corresponding to the assistant name can be called the indicator area of ​​the second intelligent assistant. In the conversation interface of "Knowledge Q&A Assistant A," the user can enter a new question to ask "Knowledge Q&A Assistant A."

[0120] In this example, the assistant's name, "Knowledge Q&A Assistant A," can be highlighted to distinguish it from other content on the interface. The XiaoE application determines the application scenario to which the user's question belongs based on the question's content and then invokes the appropriate service type to provide an answer.

[0121] In addition to providing users with answers to questions and the name of the assistant who answered them, Xiao E can also provide users with reference sources for the answers. These reference sources can include relevant links to the answers, which users can click on to expand the reference source (416) and view. The answers can be compiled by the second intelligent assistant based on the knowledge content in the relevant links. The answers and the relevant content in the reference sources can be knowledge content configured within the second intelligent assistant.

[0122] In some embodiments, users can also enter the conversation interface of "Knowledge Q&A Assistant A" by clicking on the answer provided by "Knowledge Q&A Assistant A" in the main conversation interface. When the answer provided by "Knowledge Q&A Assistant A" is long, an expansion control 415 can be provided after the answer. Users can also enter the conversation interface of "Knowledge Q&A Assistant A" by clicking on the expansion control 415 to view the specific content of the answer. The answer content and the expansion control 415 of the answer content can be referred to as the content indication area of ​​the answer.

[0123] The user's actions of clicking on the answer content, the answer content expansion control 415, or the assistant's name can also be referred to as the second action.

[0124] The conversation interface of the XiaoE application can be called the main conversation interface, and the dialogue between the user and the XiaoE application can be called the main conversation. The conversation interface of the "Knowledge Q&A Assistant A" can be called the independent conversation interface, and the dialogue between the user and the "Knowledge Q&A Assistant A" can be called the independent conversation. In other words, the independent conversation and the main conversation can be dialogues between the user and different objects. The independent conversation can be a conversation for a specific scenario. The independent conversation can be generated by the XiaoE application calling the corresponding service for a specific topic. On the main conversation interface, at least one independent conversation can be selected, retrieved, displayed, exited, or have its chat history managed.

[0125] In this application, the second intelligent assistant may also be referred to as an agent, service, etc., and this application does not limit the name of the second intelligent assistant.

[0126] Based on the user's question, the XiaoE app can provide one answer from a smart assistant, or multiple answers from smart assistants. For example... Figure 4As shown in interface 420 (b), based on the question content, Xiao E can provide not only the answer provided by "Knowledge Q&A Assistant A" but also the answer provided by "Knowledge Q&A Assistant B." "Knowledge Q&A Assistant A" and "Knowledge Q&A Assistant B" can be different intelligent assistants targeting the same scenario. Users can choose which answer content they want to view or further enter the independent conversation interface of that intelligent assistant. The way users enter the independent conversation interface of the intelligent assistant can be the same as described above. Figure 4 Similar to the method described in (a), for example, you can click on the name control 421A or 421B of "Knowledge Q&A Assistant A" or "Knowledge Q&A Assistant B" to enter the corresponding independent session interface, or you can click on the content of the answer to enter the corresponding independent session interface, or you can click on the expansion control 425A or 425B of the answer content to enter the corresponding independent session interface.

[0127] The main conversation interface can be displayed in full-screen or half-screen mode. Users can activate the voice assistant in any scenario using a wake word. For example, when the electronic device is on its desktop, the user can say the wake word "Xiao E Xiao E," or activate Xiao E by pressing and holding the power button or other shortcuts. The electronic device can then display the Xiao E application's conversation interface on the desktop in a half-screen mode, allowing the user to input their question via voice or text. Figure 4 Interface 430 is shown in (c). In response to the user clicking the assistant name "Knowledge Q&A Assistant A" 431, the answer content, or the answer content expansion control 432, the displayed interface can jump to the conversation interface of the intelligent dialogue service and display the service's conversation interface in full-screen mode. When the user activates the voice assistant in a locked screen state, a prompt to unlock can be made first, and after unlocking, the service's conversation interface can be displayed.

[0128] The XiaoE app's chat interface can also be accessed by clicking on the XiaoE app. For example, the desktop of an electronic device may include an icon for the XiaoE app. Users can click on the XiaoE app icon to enter the XiaoE app's chat interface and ask XiaoE questions (not shown in the figure).

[0129] The main session interface can display only the "Knowledge Q&A Assistant A's" answer to the current question, or it can display the historical messages from the "Knowledge Q&A Assistant A". For example... Figure 4As shown in (d) above, the main conversation interface 440, in response to a user's input question, can directly display a separate conversation interface 441 for "Knowledge Q&A Assistant A," which can be displayed in a partial area of ​​the main conversation interface 440, for example, below the user's input question. This separate conversation interface 441 can contain "Knowledge Q&A Assistant A's" answer to the current question "What is chatGPT?", as well as historical questions such as "What is AI?" and answers to those historical questions. When this separate conversation interface 441 is displayed in a partial area of ​​the main conversation interface 440, if the answer is too long, exceeding a preset word count or line count, the answer can be partially collapsed. In this separate conversation interface 441, the user can also scroll up and down to view historical messages between the user and "Knowledge Q&A Assistant A." (The last sentence appears to be a repetition of the previous one and can be omitted.) Figure 4 Similar to the examples described in (a) to (c), the standalone session interface 441 may also include an expand control 442. In response to the user clicking the expand control 442, the standalone session interface 441 may display the complete answer to the question from "Knowledge Q&A Assistant A," or, in response to the user clicking the expand control 442, the standalone session interface 441 may be displayed in full-screen mode within the first application. Alternatively, the user may also click on the answer content in the standalone session interface 441 to display it in full-screen mode. Alternatively, the user may also click on the name 443 of "Knowledge Q&A Assistant A" to display the standalone session interface 441 in full-screen mode. When the standalone session interface 441 is displayed in full-screen mode, the complete answer to the question from "Knowledge Q&A Assistant A" can be displayed in the standalone session interface 441.

[0130] The first operation mentioned above can be the click operation, or it can be a double-click or long-press operation, etc. This application does not limit it in this regard.

[0131] In one possible implementation, the first operation may include entering the name of the second smart assistant. That is, in response to the user entering the name of the second smart assistant, the first application may display a separate session interface for the second smart assistant.

[0132] For example, such as Figure 5As shown in (a), interface 510 can be the main conversation interface of the XiaoE application. Users can click the keyboard control 511 to activate the keyboard and input the name of the second intelligent assistant via text input. For example, in response to the user clicking the keyboard control 511, the keyboard can pop up on the conversation interface. Furthermore, candidate options can be displayed below the text input box, which may include a list of intelligent dialogue services, that is, it may include one or more assistant names, for example, it may include... Figure 5 The interface 520 shown in (b) features intelligent assistants for different application scenarios, such as "Knowledge Q&A Assistant A," "Travel Assistant," and "Conference Assistant." "Knowledge Q&A Assistant A" can be an intelligent dialogue service related to knowledge Q&A, "Travel Assistant" can be an intelligent dialogue service related to travel, and "Conference Assistant" can be an intelligent dialogue service related to the Huawei Developer Conference (HDC). Multiple different intelligent dialogue services can be recommended for the same application scenario. For example, in the knowledge Q&A service scenario, two different intelligent dialogue services, "Knowledge Q&A Assistant A" and "Knowledge Q&A Assistant B" (not shown in the figure), can be recommended.

[0133] Optionally, the candidate list can display the names of all intelligent dialogue services configured in the XiaoE application. If the number of intelligent dialogue services exceeds the display area on one screen, the user can swipe up and down in the candidate list to view the intelligent dialogue services not currently displayed, and the user can select the desired intelligent dialogue service from the candidate list. Alternatively, the candidate list can only display the names of intelligent dialogue services used in the XiaoE application's historical conversation messages, such as intelligent dialogue services that answered user questions in the main conversation interface of the XiaoE application, or intelligent dialogue services that the user has entered into independent conversation interfaces.

[0134] For example, in response to a user activating the keyboard and clicking the text input box 521, a list of intelligent dialogue services is displayed. Another example, such as... Figure 5 The interface 530 shown in (c) displays the intelligent dialogue service list in response to the user activating the keyboard and entering “@” in the text input box 531. This application does not limit the operation of calling up the intelligent dialogue service list.

[0135] In some embodiments, the intelligent assistants included in the list of intelligent dialogue services may be determined by the first application based on the history of the main session and / or the history of independent sessions.

[0136] For example, the smart assistant in the smart dialogue service list can be a smart assistant included in the history of the first application, or the smart assistant in the smart dialogue service list can be a smart assistant that the user has entered the independent conversation interface corresponding to that smart assistant.

[0137] When the list of intelligent dialogue services includes multiple intelligent dialogue services, these services can be provided by the first application based on the historical usage time of each intelligent assistant. For example, Figure 5 In the intelligent dialogue services shown in (b) or (c), "Knowledge Q&A Assistant A" can be the most recently used intelligent dialogue service, while the most recently used time of "Travel Assistant" can be before the most recently used time of "Knowledge Q&A Assistant A", the most recently used time of "Meeting Assistant" can be before the most recently used time of "Travel Assistant", and so on.

[0138] When the list of intelligent dialogue services includes multiple intelligent dialogue services, these multiple intelligent dialogue services can also be provided to the first application based on the historical access frequency of each intelligent assistant. For example, Figure 5 In the intelligent dialogue services shown in (b) or (c), "Knowledge Q&A Assistant A" can be the intelligent dialogue service with the highest historical access frequency, "Travel Assistant" can have a lower historical access frequency than "Knowledge Q&A Assistant A", "Meeting Assistant" can have a lower historical access frequency than "Travel Assistant", and so on.

[0139] When a user brings up the list of intelligent dialogue services by enabling the keyboard, the order of each intelligent dialogue service in the brought-up list can be updated based on information such as the historical usage time or historical access frequency of each intelligent dialogue service.

[0140] It should be understood that when the list of intelligent dialogue services includes multiple intelligent dialogue services, these multiple intelligent dialogue services can also be arranged in other orders. For example, these multiple intelligent dialogue services can be recommended by the XiaoE application based on historical message content within a certain period.

[0141] In some embodiments, the number of intelligent dialogue services included in the list of intelligent dialogue services may be less than or equal to 12, for example, 10, 8, 5, 3, etc.

[0142] Furthermore, users can select the desired intelligent dialogue service from the options, and the name of the selected intelligent dialogue service can be automatically filled into the text input box.

[0143] As an example, such as Figure 6 In interfaces 610 and 620 shown in (a) and (b), after the user selects the desired intelligent dialogue service, they can directly click the send control 611. In response to the user entering the name "Knowledge Q&A Assistant A," a separate dialogue interface 621 for "Knowledge Q&A Assistant A" can be displayed in the main dialogue interface. This separate dialogue interface 621 can be connected to the aforementioned... Figure 4Similar to the independent conversation interface 441 described in (d) above, it will not be repeated here. When the user does not enter a question for "Knowledge Q&A Assistant A", the conversation content displayed in this independent conversation interface 621 can be a historical conversation record.

[0144] As another example, such as Figure 6 In interfaces 630 and 640 shown in (c) and (d), after the user selects the desired intelligent dialogue service, such as "Knowledge Q&A Assistant A," they can further enter the content they want to ask "Knowledge Q&A Assistant A" in the input box. In response to the user clicking the send control 631, the content in the text input box is sent to the conversation interface. That is, this first operation allows the user to enter the name of a second intelligent assistant and the question to be asked of that assistant. Correspondingly, "Knowledge Q&A Assistant A" can provide the user with the answer to that question. Figure 6 The interface shown in (d) can be used with Figure 4 Similar to interface 410 shown in (a), users can click on the name 642 of "Knowledge Q&A Assistant A" on interface 640 to enter the independent session interface of "Knowledge Q&A Assistant A," or they can click on the specific content of the answer to enter the independent session interface of "Knowledge Q&A Assistant A," or they can click on the expansion control 641 of the answer content to enter the independent session interface of "Knowledge Q&A Assistant A." In this example, in response to the user entering the name of "Knowledge Q&A Assistant A" and the question to ask "Knowledge Q&A Assistant A," the main session interface can also be similar to... Figure 6 The interface shown in (b) is not limited in this application.

[0145] It should be understood that Figure 5 The candidate options shown may include the name of the intelligent dialogue service, or may display both the name of the intelligent dialogue service and the icon of each intelligent dialogue service. Users can select the intelligent dialogue service by clicking the name of the intelligent dialogue service or by clicking the icon of the intelligent dialogue service. This application does not limit this.

[0146] In one possible implementation, the first smart assistant can recommend multiple smart assistants in the main session interface, and the second smart assistant is included among the multiple smart assistants. The first operation can include: selecting the second smart assistant recommended by the first smart assistant.

[0147] For example, such as Figure 7 The interface 710 shown in (a) can be the main conversation interface, which can directly display the intelligent dialogue services recommended by Xiao E to the user, without needing to go through... Figure 5The method of waking up the keyboard shown displays a list of intelligent dialogue services. This interface 710 includes, for example, "Knowledge Q&A Assistant A" 711, "Knowledge Q&A Assistant B" 712, etc. The recommended intelligent dialogue services can be displayed at the bottom of this conversation interface 710. Users can swipe left and right to display intelligent dialogue services not currently displayed on the screen. Users can select the desired intelligent dialogue service. In response to the user clicking on the intelligent dialogue service name, the interface jumps to the corresponding independent conversation interface. This list of intelligent dialogue service names can also be displayed in the middle area of ​​the interface 710 in a top-to-bottom arrangement, for example, below the conversation bubble "Want to chat with Xiao E?" shown in the illustration. Figure 7 As shown in interface 720 in (b) of this application, the display position of the list of intelligent dialogue service names is not limited.

[0148] and Figure 5 The list of intelligent dialogue services described in [the document] is similar. Figure 7 The intelligent dialogue services included in the described list can be determined by the XiaoE application based on the history of the main session and / or the history of independent sessions. For example, the intelligent assistants included in the intelligent dialogue service list can be intelligent assistants included in the historical messages of the main session, or the intelligent assistants included in the intelligent dialogue service list can be intelligent assistants whose independent session interfaces the user has accessed. Furthermore, the intelligent assistants included in the intelligent dialogue service list can be those displayed by the XiaoE application based on the most recent access time, for example... Figure 7 In (a) of the diagram, the timestamps of the most recent use of the intelligent dialogue services, arranged from left to right, are progressively longer than the current time. Figure 7 In (b) of the above, the most recent usage time of the intelligent dialogue services, arranged from top to bottom, is increasingly further back than the current time. Alternatively, Figure 7 The intelligent dialogue services included in the described list can be displayed based on historical access frequency, for example, Figure 7 In (a) of the chart, the historical access frequency of the intelligent dialogue service, arranged from left to right, decreases. Figure 7 In (b) of the data, the historical access frequency of the intelligent dialogue service, arranged from top to bottom, is decreasing.

[0149] It should be understood that the list of intelligent dialogue services may also include the service's icon, and this application does not limit this.

[0150] In one possible implementation, the first intelligent assistant can provide multiple scenario suggestions in the interface of the main session, which may include questions about the first scenario, and the first operation may include: the user selecting a question about the first scenario.

[0151] For example, such as Figure 8 The interface 810 shown can be the main chat interface for Xiao E. This interface displays questions recommended by Xiao E to the user. These recommended questions can be associated with intelligent service assistants supported by the Xiao E application. For example, "How to write a high-scoring essay" 811 can be associated with the writing-related service "Essay Tutor Assistant," "Introduction to the HDC Conference" 812 can be associated with the HDC-related service "Conference Assistant," and "What is the use of chatGPT?" 813 can be associated with the knowledge-based Q&A service "Knowledge Q&A Assistant A." When the recommended questions include questions the user wants to ask, the user can directly click on the corresponding question to ask. The recommended questions can include questions for different scenarios or different questions for the same scenario.

[0152] In some embodiments, the multiple scenario suggestions recommended by the XiaoE application can be determined by the XiaoE application based on the history of the main session and / or the history of independent sessions. For example, the questions included in the multiple scenario suggestions can be questions recommended based on the user's recent questions in the main session interface. If the user recently searched for AI-related topics while using XiaoE, the multiple scenario suggestions can include questions related to the AI ​​topic content of the question. Alternatively, the questions included in the multiple scenario suggestions can be questions recommended based on the frequency of questions asked by the user in the main session interface. If the user asks many questions about AI topics, questions can be recommended based on the content of questions asked more frequently. Similarly, the questions included in the multiple scenario suggestions can also be questions recommended based on the user's recent questions in the independent session interface, or questions recommended based on the content of questions asked more frequently by the user in the independent session interface.

[0153] In one example, in response to a user clicking on the recommended question, the user can be directly redirected to a separate conversation interface of the intelligent dialogue service corresponding to that question. In this separate conversation interface, the user's selected question and the answer to that question can be displayed.

[0154] In another example, in response to a user clicking on the recommended question, the question can also be displayed on Xiao E's main conversation interface, along with the answer and the corresponding intelligent dialogue assistant name. For instance, after a user clicks "What is the use of chatGPT?", the redirected interface could be similar to... Figure 4 The interface 410 shown in (a) responds to the user clicking the intelligent dialogue service name, the answer content, or the answer content expansion control to enter the independent conversation interface of the intelligent dialogue service. Alternatively, the interface that is redirected may be similar to... Figure 4 The interface shown in (d) is shown in the image.

[0155] In one possible implementation, users can also access a separate session interface through the suggestion card interface.

[0156] As an example, the first application may display a suggestion card interface, the first smart assistant may recommend multiple smart assistants on the suggestion card interface, the second smart assistant may be included among the multiple smart assistants, and in response to the user selecting the second smart assistant, the interface of the first independent session is displayed.

[0157] like Figure 9 The interface 910 shown in (a) can be the desktop of an electronic device. On this desktop, a suggestion card 911 of Xiao E can be displayed, for example, as "Xiao E Suggestions". The suggestion card 911 can display the names of multiple smart assistants recommended by the primary smart assistant of the Xiao E application, such as "Knowledge Q&A Assistant A" 912, "Knowledge Q&A Assistant B" 913, and "Travel Assistant" 914 as shown in the illustration. Users can directly select the name of the smart assistant in the suggestion card 911 to enter the corresponding independent conversation interface.

[0158] With the above Figure 7 Similarly, the smart assistant recommended in suggestion card 911 can also be determined based on the history of the main conversation and / or the history of individual conversations, as described in the example.

[0159] As another example, the first intelligent assistant can provide multiple scenario suggestions on the interface of the suggestion card, which include a question about the first scenario. In response to the user selecting a question about the first scenario, the interface of the first independent session is displayed.

[0160] like Figure 9 Interface 920 shown in (b) is similar to... Figure 9 Similar to the example shown in (a), suggestion card 921 could display recommended questions for the user. These recommended questions could be associated with the intelligent service assistant that Xiao E supports. In response to the user clicking on the recommended question 922, 923, or 924, the user could be redirected to the independent session interface of the intelligent dialogue service corresponding to that question. Alternatively, in response to the user clicking on the recommended question 922, 923, or 924, the user could be redirected to Xiao E's main session interface, where the question answer and the name of the intelligent dialogue service would be displayed.

[0161] When a user clicks on the blank area of ​​"Little E's Suggestions"—that is, the area other than the recommended questions—they can enter Little E's conversation interface, for example, they can be redirected to... Figure 5 The interface shown in (a) is shown in the image.

[0162] With the above Figure 8 Similarly, the questions recommended in suggestion card 921 can also be determined based on the history of the main conversation and / or the history of individual sessions, as described in the example.

[0163] In some embodiments, when the currently displayed interface is the main session interface of the first application, the user can exit the main session interface and return to the interface of suggestion card 911 or suggestion card 921, and enter an independent session interface through the options in suggestion card 911 or suggestion card 921. For example, the user can swipe up from the bottom edge of the screen to return to the desktop of the electronic device and enter the interface of suggestion card 911 or suggestion card 921.

[0164] Xiao E's suggestion card can be displayed in a window on the desktop, or it can be displayed in full-screen mode within the Xiao E application. This application does not limit this.

[0165] The dialogue method provided in this application provides users with an independent dialogue entry point on the main dialogue interface. Users can enter the independent dialogue entry point to enjoy more focused services or dialogues to solve problems on topics of interest. Users can view historical messages on specific topics in the corresponding independent dialogue, which can improve the user experience and efficiency of the smart voice assistant, and is conducive to user retention and user activity growth. For developers, independent dialogues can be used to build private domain service experience and data, and convey brand identity through the assistant's image.

[0166] The above combination Figures 4 to 9 This application describes the method of entering an independent session from the main dialog. The following describes the independent session interface. Figure 10 The interface shown is the interface of the second intelligent assistant's independent session, responding to user clicks. Figure 4 (a) to (c) Figure 6 The intelligent dialogue service name, answer content, or answer content expansion control shown in (d) above, or, in response to a user click... Figures 7-9 The recommended intelligent dialogue service or recommended questions can be accessed through the display interface. Figure 10 The independent conversation interface 1010 shown in (a) can be a full-screen independent conversation interface. Even when the independent conversation interface is partially displayed within the main conversation interface, the user can still access the full-screen independent conversation interface by clicking on the answer content, the answer content expansion control, or the name of the smart assistant within the partially displayed independent conversation interface. For example, the user can click... Figure 4 (d) in Figure 6(b) The answer content, the answer content expansion control, or the name of the smart assistant in the text can be used to access... Figure 10 The independent conversation interface shown in (a) is an example. Both the partially displayed independent conversation interface and the full-screen independent conversation interface are interfaces for independent conversations. When the independent conversation interface is displayed in partial mode, the user can view historical messages in the independent conversation interface. When the independent conversation interface is displayed in full-screen mode, the user can both view historical messages in the independent conversation interface and ask questions to the smart assistant corresponding to the independent conversation in the independent conversation interface.

[0167] For example, the independent session interface 1010 of the second smart assistant may include an icon 1012 of the second smart assistant and the name of the second smart assistant, "Meeting Assistant". The icon 1012 and the name of the second smart assistant may be displayed in the top function area 1011 of the independent session interface 1010 to prompt the user that the current interface is an independent session interface about "Meeting Assistant".

[0168] Optionally, the conversation interface 1010 may also include a welcome message, which can be displayed in the guide bubble 1013. The welcome message could be, for example, "Hello, I am the meeting assistant" as shown in the illustration. This welcome message can appear when the user first opens the independent conversation interface, or it can appear every time the user opens the independent conversation interface. The welcome message can be part of the history messages of the independent conversation; that is, the welcome message can be stored together with the conversation content of the second smart assistant's conversation interface in the server corresponding to the second smart assistant. The number of characters in the welcome message can be related to the device type; for example, when the display device is a tablet, the corresponding welcome message can have more characters than when the display device is a mobile phone.

[0169] Optionally, the guide bubble 1013 may also include a description of the features of the standalone session, such as the illustrated "You can ask me about technology / AI / chip-related topics." In some embodiments, this description may also be displayed in the top function area of ​​the standalone session, for example... Figure 10 In the interface 1020 shown in (b), the top function area 1021 may include an expand control 1022, which can display a description of the functions of the standalone session in response to the user clicking the expand control 1022.

[0170] Optionally, see [link to relevant documentation] Figure 10As shown in (a) of the interface, the independent session interface 1010 may further include a question list 1014, which may include questions recommended to the user. The user can directly click on a question displayed in the question list to quickly ask a question without manually entering the question content. The question list 1014 allows the user to ask questions quickly by clicking on the questions displayed in the question list. Figure 7 When accessing the independent conversation interface as shown, the question list 1014 may not be displayed on the independent conversation interface if the user obtains access by entering a specific question. The number of questions included in the question list 1014 can be the three shown in the illustration, or it can be one, two, or more. The number of questions included in the question list 1014 can be related to the type of display device; for example, the number of questions can be more when the display device is a tablet than when it is a mobile phone. The questions in this intelligent dialogue service list can be obtained by the electronic device from the cloud, or they can be determined by the electronic device based on the historical messages of the independent conversation and presented on the conversation interface.

[0171] For example, the number of characters in the recommendation question can be less than or equal to 20, including punctuation marks. If the number of characters in the recommendation question exceeds the number of characters that an electronic device can display in one line, the remaining characters can be displayed as ellipses.

[0172] When a user clicks on any question in the question list 1014, that question is displayed as a question in the separate session interface. Correspondingly, the guide bubble 1013 can be removed from the separate session interface. Figure 10 Interface 1030 is shown in (c). Alternatively, if there are no questions the user wants to ask in the recommended questions, the user can also enter a question via voice or text input. In response to the user's input of a question, the guide bubble can be removed from the standalone session interface.

[0173] In this independent conversation interface, it is not necessary to display "The following answer is provided by XXX" before the question and answer content provided to the user, nor is it necessary to display the name of the intelligent dialogue service that provides the question and answer below the answer content.

[0174] Optionally, such as Figure 10 As shown, the top function area can also include an "Exit" control. In response to the user clicking the "Exit" control, the user can exit this standalone session and return to the main session interface of the small E. Alternatively, the user can swipe right or left from the left or right edge of the screen, as shown... Figure 10As shown in (d), exit the independent session interface and return to the main session interface of Xiao E. Alternatively, the user can actively trigger the session content to exit the independent session interface, for example, the user can enter "Session ended" in the independent session interface to exit the current session interface. After returning to the main session interface of Xiao E, the bottom of Xiao E's session interface can display "The conversation with the meeting assistant has ended" (not shown in the figure).

[0175] The content displayed on the interface of this independent session can be subject to risk control. For example, the icon, name, function description, recommended questions, and answers of the intelligent dialogue service corresponding to this independent session can all be risk-controlled content to ensure that the displayed content complies with legal regulations and ethical constraints.

[0176] In some embodiments, the content of an independent session and the content of the main session can be stored independently. For example, the content of the main session can be stored on the server of the independent session service provider (e.g., the XiaoE application), while the content of the independent session can be stored on the server of the intelligent dialogue service (e.g., a third-party application).

[0177] The interface of a standalone session can display the history of multiple rounds of conversation. After entering the interface of a standalone session, users can swipe to view the historical message records within the scope of that standalone session, but cannot see the historical messages of other standalone sessions.

[0178] The main session application can manage multiple independent sessions, and users can view these independent sessions based on multiple intelligent dialogue services by swiping left or right. For example... Figure 11 As shown, the Figure 11 The interface 1110 shown in (a) can be a standalone session interface for the "Meeting Assistant". Figure 11 The interface 1120 shown in (b) can be a standalone session interface for the "Essay Tutoring Assistant". Both the "Meeting Assistant" and the "Essay Tutoring Assistant" can be intelligent service assistants that the main session application can invoke, for example, through... Figure 4 or Figures 5-6 The described method is displayed in the main conversation interface's intelligent dialogue service, or it can be used by users through... Figures 7-9 The described method accesses the intelligent dialogue service through the independent conversation interface. A left swipe on interface 1110 switches to interface 1120. The user can also swipe right on interface 1120 to switch back to interface 1110, and can further swipe left or right to view other independent conversation interfaces. This swipe operation for switching services can be a swipe starting from the middle area of ​​the interface. In this example, the user's left or right swipe operations can be referred to as a third operation.

[0179] Alternatively, users can click Figure 11 In (a) of the diagram, the intelligent dialogue service name is "Meeting Assistant". Below this name, a dropdown menu can be displayed showing the intelligent dialogue services historically invoked in the main session, allowing the user to select the independent session interface they wish to switch to. Figure 11 Interface 1130 is shown in (c) in the example. In this example, the user's action of clicking the name of the intelligent dialogue service and selecting the intelligent dialogue service from the drop-down box can be referred to as the third action.

[0180] In some embodiments, multiple independent sessions can also be displayed simultaneously in the first application. For example... Figure 11 As shown in (d) in the figure, with Figure 4 (d) and Figure 6 Similar to (b) above, the main session interface can simultaneously display multiple independent session interfaces, and these independent session interfaces can be displayed partially within the main session interface. When a user has entered the corresponding dialog box interface or the full-screen independent session interface, or when the user has invoked the corresponding intelligent service assistant for that independent session within the main session interface to provide an answer, the main session interface can display one or more of the independent session interfaces. For example, when a user... Figure 11 When the interface described in (a) to (c) returns to the main session interface, the main session interface can display the independent session interface of the most recently exited smart conversational assistant, or, as described above. Figure 4 (d) or Figure 6 In the example described in (b), in response to the user entering a question or the name of the smart assistant in the main session's interface, the main session's interface can also display the interface of the corresponding independent session. The content displayed in the interfaces of these one or more independent sessions can be related to... Figure 11 The content displayed in the full-screen independent session interface described in (a) to (c) is similar to that in the above-mentioned top function area. Users can swipe up and down in the corresponding area of ​​the independent session interface to reveal the content.

[0181] When a user enters a standalone session the next time, they can swipe through the main session to find the target standalone session and click on the answer content, the expand control of the answer content, or the assistant's name in that standalone session to display the standalone session in full-screen mode.

[0182] It should be understood that, Figure 11 In the example shown in (d), the user can also enter the dialog box interface of the independent session by clicking anywhere in the independent session interface, so that the independent session interface is displayed in full screen. For example, the user can also click on the question in the independent session interface or the blank area in the independent session interface to make the independent session interface full screen. Figure 11The manner described in (a) to (c) is shown.

[0183] In some embodiments, in response to entering a second round of questions within the independent session on the independent session interface, an answer to the second round of questions is displayed, which may be an answer generated based on the content of the first round of questions and the content of the second round of questions.

[0184] like Figure 12 As shown in interface 1210, the user first enters the first round of questions: "What's the weather like in Beijing on June 20th?" The "Travel Assistant" answers, "The weather in Beijing on June 20th is sunny." Then, the user enters the second round of questions: "What about Shanghai?" The "Travel Assistant" answers, "The weather in Shanghai on June 20th is sunny." In this example, the second round of questions does not include weather or date information. The "Travel Assistant" second intelligent assistant can determine the specific question the user wants to ask in the second round based on historical conversation content and provide a corresponding answer to improve the accuracy of the response.

[0185] Generating answers to the current question based on the content of historical questions within an independent session and the content of the current question can improve the relevance and accuracy of the answers provided by the independent session, and better meet user expectations.

[0186] In some embodiments, the first intelligent assistant's answer in the main session may be related to the history of the first independent session. The first intelligent assistant's answer in the main session may refer to the answer to the question in the main session interface. This answer can be provided by the first intelligent assistant itself, or it can be an answer retrieved by the first application from the second intelligent assistant. For example, a user asks the second intelligent assistant "What's the weather like in Beijing on June 20th?" in the "Weather Assistant" session interface. After returning to the main session interface, the user enters the question "What about Shanghai?" in the main session interface. Based on the historical messages in the first independent session, the main session interface can display the answer "The weather in Shanghai is sunny on June 20th." The first intelligent assistant's answer in the main session is related to the history of the first independent session, which makes the answer in the main session more in line with the user's expectations and makes the answer to the question more accurate.

[0187] In some embodiments, the second intelligent assistant's answers in the first independent session can be related to the history of the main session. For example, in the history of the main session, the user asked the question "What's the weather like in Shanghai on June 20th?", and the "Weather Assistant" provided the answer. When the user enters the interface of the first independent session, such as the independent session interface with the "Travel Assistant," and the user enters the question "Looking for train tickets from Beijing to Shanghai" into the "Travel Assistant," the "Travel Assistant" can provide the user with train ticket information for June 20th from Beijing to Shanghai. The answer provided by the "Travel Assistant" can be based on the question asked by the user in the main session. The fact that the second intelligent assistant's answers in the first independent session are related to the history of the main session can improve the accuracy of the answers in the first independent session.

[0188] In some embodiments, the content of conversations between different independent conversations is associated. For example, the answer to a user's question in independent conversation B can be generated based on historical messages from a previous independent conversation A. Independent conversation A is provided by intelligent dialogue service A, which can be invoked by the application in the main conversation, and independent conversation B is provided by intelligent dialogue service B, which can be invoked by the application in the main conversation. The two may target the same or different application scenarios. For example, a user asks "What is the weather like in Shanghai on June 20th?" in the independent conversation interface of "Weather Assistant," and "Weather Assistant" provides the user with a weather answer. Then, the user returns to the main conversation interface of the Xiao E application to inquire about ticket booking services, and "Travel Assistant" provides the user with ticket information. For example, if the user enters "Tickets from Beijing to Shanghai," "Travel Assistant" can provide the user with ticket information from Beijing to Shanghai, and this "Travel Assistant" can provide the user with ticket information from Beijing to Shanghai on June 20th based on historical messages in the independent conversation of "Weather Assistant."

[0189] Providing answers in the current independent session based on historical messages from other independent sessions or the main session can make the answers more in line with user expectations, reduce the need for users to ask further detailed questions, and further improve the efficiency of using the smart voice assistant.

[0190] It should be noted that the above Figures 4 to 12 The interface shown is only an example to introduce the dialogue method provided in the embodiments of this application, and should not be used to limit the specific display content and display position of the electronic device interface.

[0191] The above combination Figures 3 to 12 The dialogue method provided in the embodiments of this application has been described below. Figures 13 to 15 The system architecture, dialogue device, and electronic device provided in the embodiments of this application are described.

[0192] like Figure 13As shown, the system architecture may include a terminal, a development front-end, and a nine-question framework. The development front-end can be used to establish the aforementioned first service. For example, the development front-end can be used to generate and optimize models to establish the intelligent dialogue service and save the information corresponding to the intelligent dialogue service. The terminal can be used to call and run the intelligent dialogue service. The nine-question framework is a software architecture based on a large model that interacts with the terminal. The nine-question framework can be used to call the resources of the intelligent dialogue service so that the intelligent dialogue service can run on the terminal side and interact with the first application.

[0193] like Figure 14 As shown, the dialogue device 1400 may include a processing module 1410, which can be used to perform the processing operations in the above method embodiments, such as displaying the main dialogue interface, independent dialogue interfaces, and providing corresponding answers based on user questions. The dialogue device 1400 may also include an acquisition module 1420, which can be used to acquire input operations applied to the interface, such as acquiring a first operation, a second operation, and a third operation.

[0194] Figure 15 This is a schematic structural block diagram of an electronic device provided in this application, such as... Figure 15 As shown, the electronic device 1500 may include at least one processor 1510, which is configured to execute instructions stored in a memory to control the display device 1500 to perform the dialogue method described in the above method embodiments.

[0195] Optionally, the device 1500 also includes a memory 1520 for storing instructions, and the processor 1510 may be coupled to the memory 1520.

[0196] In some embodiments, the processor 1510 and the memory 1520 can be combined into a single processing device, with the processor 1510 executing program code stored in the memory 1520 to achieve the aforementioned functions. Specifically, the memory 1520 can be integrated into the processor 1510 or independent of it.

[0197] The electronic device can be a mobile phone, tablet computer, laptop computer, smart screen, wearable device, etc. The embodiments of this application do not limit the type of electronic device.

[0198] This application also provides a computer program product that stores program instructions that, when run on a computer, cause the methods described in the above method embodiments to be executed.

[0199] This application also provides a readable storage medium storing program instructions that, when run on a computer, cause the methods described in the above method embodiments to be executed.

[0200] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0201] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0202] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0203] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0204] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0205] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0206] 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.

Claims

1. A dialogue method applied to an electronic device, characterized in that, include: The interface of the main session is displayed in the first application, which is the session between the user and the first intelligent assistant provided by the first application; In response to a user’s first operation in the main session’s interface, at least one independent session’s interface is displayed in the first application, the at least one independent session including a first independent session, the first independent session being a session between the user and a second intelligent assistant, the second intelligent assistant being an intelligent dialogue service invoked by the first application for a first scenario.

2. The method according to claim 1, characterized in that, The second intelligent assistant is an intelligent dialogue service invoked by the first application for the first scenario, including: The second intelligent assistant is an intelligent dialogue service provided by the first application for the first scenario, or... The second intelligent assistant is an intelligent dialogue service provided by the second application for the first scenario, and the first application is different from the second application.

3. The method according to claim 1 or 2, characterized in that, The first operation includes: The user enters a question in the interface of the main session, and the question is related to the first scenario.

4. The method according to claim 3, characterized in that, The method further includes: After the second intelligent assistant's answer to the question is displayed in the main session interface, the user performs a second operation on the answer. In response to the second operation, the dialog box interface of the first independent session is displayed in the first application.

5. The method according to claim 4, characterized in that, The second operation includes: The user clicks on the content indication area of ​​the answer or the indication area of ​​the second smart assistant.

6. The method according to claim 1 or 2, characterized in that, The first operation includes: entering the name of the second smart assistant in the interface of the main session.

7. The method according to claim 6, characterized in that, The first operation also includes: entering a question to ask the second smart assistant on the interface of the main session.

8. The method according to claim 1 or 2, characterized in that, The first smart assistant recommends multiple smart assistants in the interface of the main session, and the second smart assistant is included among the multiple smart assistants; The first operation includes: selecting the second smart assistant recommended by the first smart assistant.

9. The method according to claim 8, characterized in that, The recommendations are determined based on the history of the main session and / or the history of the individual sessions.

10. The method according to claim 1 or 2, characterized in that, The first intelligent assistant provides multiple scenario suggestions in the interface of the main session, and the multiple scenario suggestions include questions about the first scenario; The first operation includes: the user selecting a question about the first scenario.

11. The method according to claim 10, characterized in that, The scenario recommendations are determined based on the history of the main session and / or the history of the independent sessions.

12. The method according to any one of claims 1 to 11, characterized in that, The method further includes: In the first application, a suggestion card is displayed on the interface. The first smart assistant recommends multiple smart assistants on the suggestion card interface, and the second smart assistant is included among the multiple smart assistants. In response to the user selecting the second smart assistant, the interface of the first independent session is displayed.

13. The method according to any one of claims 1 to 11, characterized in that, The method further includes: The first application displays an interface for suggestion cards, and the first smart assistant provides multiple scenario suggestions on the interface for suggestion cards, the multiple scenario suggestions including questions about the first scenario; In response to the user selecting a question about the first scenario, the interface of the first independent session is displayed.

14. The method according to any one of claims 1 to 13, characterized in that, The first intelligent assistant's answers in the main session are related to the history of the first independent session.

15. The method according to any one of claims 1 to 14, characterized in that, The second intelligent assistant's answers in the first independent session are related to the history of the main session.

16. The method according to any one of claims 1 to 15, characterized in that, The at least one independent session also includes a second independent session, which is a session between the user and a third intelligent assistant. The third intelligent assistant is an intelligent dialogue service invoked by the first application for the second scenario. The answers of the second intelligent assistant in the first independent session are related to the history of the second independent session.

17. The method according to any one of claims 1 to 16, characterized in that, The at least one independent session also includes a second independent session, which is a session between the user and a third intelligent assistant. The third intelligent assistant is an intelligent dialogue service invoked by the first application for the second scenario. The first independent session and the second independent session are displayed simultaneously in the first application.

18. The method according to any one of claims 1 to 17, characterized in that, The at least one independent session also includes a second independent session, which is a session between the user and a third intelligent assistant. The third intelligent assistant is an intelligent dialogue service invoked by the first application for the second scenario. The first independent session and the second independent session are switched and displayed in the first application through the user's third operation.

19. The method according to any one of claims 1 to 18, characterized in that, The history of the first independent session can be viewed in the interface of the first independent session.

20. The method according to any one of claims 1 to 19, characterized in that, The interface of the first independent session includes at least one of the following: Welcome message, icon or name of the second smart assistant, icon or name of the service provider of the second smart assistant, introduction of the functions of the first independent session, and exit control of the first independent session.

21. An electronic device, characterized in that, The method includes a processor and a memory, the memory being used to store program instructions, and the processor being used to execute the program instructions stored in the memory to implement the method as described in any one of claims 1 to 20.

22. A chip system, characterized in that, Includes a processor for reading instructions stored in memory, wherein when the processor executes the instructions, the method as described in any one of claims 1 to 20 is implemented.

23. A computer program product, characterized in that, The computer program product stores program instructions that, when executed on a computer, cause the method as described in any one of claims 1 to 20 to be performed.

24. A readable storage medium, characterized in that, The readable storage medium stores program instructions that, when executed on a computer, cause the method as described in any one of claims 1 to 20 to be performed.

Images