An agent running method, an electronic device, a storage medium, and a program product

Abstract

An agent running method, an electronic device, a storage medium and a program product are provided, which are used for realizing flexible use of an agent and helping to improve user experience. For example, an electronic device runs a first application; on a display interface of the first application, a first agent of a second application is run, and the second application is different from the first application.

Description

[0001] This application is a divisional application. The original application has the application number 202510570646.1 and the original application date is April 30, 2025. The entire contents of the original application are incorporated herein by reference. Technical Field

[0002] This application relates to the field of terminal technology, and in particular to an intelligent agent operation method, electronic device, storage medium and program product. Background Technology

[0003] With the development of artificial intelligence (AI), many applications have begun to develop their own intelligent agents. For example, QQ Music. ® It has QQ Music Assistant ® Didi Chuxing ® With Didi Assistant ® Currently, the use of intelligent agents has certain limitations: the intelligent agent of an application can only be used when the application is running. For example, if a user wants to use the intelligent agent of application A, the terminal device must be triggered to run application A (for example, the interface of application A is displayed in the foreground) in order to use the intelligent agent of application A; moreover, while application A is running, only the intelligent agent of application A can be used, and the intelligent agents of other applications cannot be used.

[0004] This shows that using intelligent agents is currently very inconvenient for users, affecting their user experience. Summary of the Invention

[0005] This application provides an intelligent agent operation method, electronic device, storage medium, and program product to improve the user's experience with intelligent agents.

[0006] Firstly, a method for operating an intelligent agent is provided, applied to an electronic device. For example, the electronic device may be a mobile phone. The method for operating an intelligent agent provided in this application includes: running a first application; and running a first intelligent agent of a second application on the display interface of the first application, wherein the second application is different from the first application.

[0007] It should be noted that in current technology, when an electronic device is running a first application in the foreground, it can only use the intelligent agent of the first application and cannot use intelligent agents of other applications. Through the technical solution provided in this application, when an electronic device is running a first application in the foreground, it can run intelligent agents of a second application, not just the intelligent agents of the first application. This improves the flexibility of intelligent agent usage and helps to enhance the user experience of intelligent agents.

[0008] In one possible design, the method further includes: displaying a first interface of the first agent while the first agent of the second application is running; and running a second agent of the third application in response to a first operation by the user on the first interface.

[0009] It should be noted that in current technology, for an electronic device to run an agent of application B (e.g., a third application), application B must be run and its interface must be accessed. The technical solution provided in this application allows users to trigger the electronic device to run agent B of application B within the interface of agent A (the agent of application A), without needing to access the interface of application B. This simplifies the agent usage process, improves the flexibility of agent use, and helps enhance the user experience.

[0010] In one possible design, the method further includes: in response to the first operation, switching the first interface to a second interface of the second agent, the first operation including at least one of the following: selecting a first control on the first interface, the first control being used to instruct the second agent; or receiving an instruction from the user, the instruction corresponding to a function of the second agent.

[0011] It should be noted that in current technology, switching an electronic device from agent A in application A to agent B in application B requires closing the interface of application A, entering the interface of application B, and then running agent B. In other words, switching between agent A and agent B is achieved through switching between application A and application B. In this embodiment, switching between agent A and agent B can be achieved without switching between application A and application B. For example, agent A can be switched to agent B through a first control within the interface of agent A or through a user command. This method improves the convenience of agent switching and enhances the user experience of using the agents.

[0012] In one possible design, the second agent that runs the third application in response to a user's first operation on the first interface includes: obtaining a processing result corresponding to the first operation by invoking the second agent; and displaying the processing result to the user through the first agent.

[0013] Therefore, in this embodiment of the application, an agent of one application can call an agent of another application to process user instructions. In other words, agents across applications can interact, which improves the flexibility of agent use and helps to improve user experience.

[0014] In one possible design, the method further includes: displaying a first control of the second intelligent agent on the first interface; the first operation includes a selection operation on the first control.

[0015] Therefore, in this embodiment, the interface of an application's agent may include a control for instructing another application's agent. This control allows the agent of the other application to process user commands, thereby enabling interaction between agents across applications. This approach enhances the flexibility of agent usage and improves the user experience.

[0016] In one possible design, the first operation is used to instruct a first task, and the method further includes: in response to a first operation by a user on the first interface, running a third agent of a fourth application, the third agent and the second agent being used to collaboratively perform the first task.

[0017] Therefore, in the embodiments of this application, intelligent agents from different applications can work together to process a task, which improves the flexibility of using intelligent agents and helps to improve the user experience.

[0018] In one possible design, before running the first agent, the method further includes: providing a second control on the display interface of the first application; and receiving the user's selection of the first agent through the second control.

[0019] Therefore, in this embodiment of the application, the user can trigger the electronic device to run the intelligent agent of the second application through the controls in the interface of the first application. The intelligent agent of the second application can be run without entering the interface of the second application, which improves the flexibility of the intelligent agent and helps to improve the user experience.

[0020] Optionally, receiving the user's selection of the first intelligent agent through the second control may include: a one-step operation or a multi-step operation.

[0021] As an example, the second control is located in the navigation bar. Receiving the user's selection of the first agent through the second control includes: receiving the operation on the second control located in the navigation bar and launching the first agent. In this way, the second control can be kept away from obstructing the display interface of the first application as much as possible, resulting in a better user experience.

[0022] As another example, receiving the user's selection of the first intelligent agent via the second control may include: receiving an operation on the second control, displaying the display interface of the first application's intelligent agent, the display interface including controls for the first intelligent agent, receiving an operation on the controls for the first intelligent agent, and launching the first intelligent agent. In other words, by using the second control on the first application's display interface, the panel of the first application's intelligent agent is pulled up, and by using the controls for the second application's intelligent agent within that panel, the electronic device is triggered to launch the second application's intelligent agent. This process eliminates the need to run the second application and enter its display interface, simplifying the launch process of the second application's intelligent agent and providing a better user experience.

[0023] In one possible design, before running the first agent, the method further includes: providing an interaction interface between the user and the system assistant on the display interface of the first application; and launching the first agent in response to an instruction input by the user at the interaction interface.

[0024] Therefore, in this embodiment of the application, while the first application is running in the foreground, the user can launch the intelligent agent of the second application through the system assistant. That is, the intelligent agent of the second application can be launched without entering the interface of the second application, which simplifies the launch process of the intelligent agent of the second application, improves the convenience of using the intelligent agent, and helps to improve the user experience.

[0025] In one possible design, before running the first agent, the method further includes: outputting a first prompt message, the first prompt message being used to indicate the existence of an agent to be recommended.

[0026] Therefore, in this way, while the first application is running in the foreground, it can notify the user of the existence of recommended agents through an initial prompt message, and the recommended agents can include agents from the second application. This prompting method provides a better user experience, and the fact that the recommended agents include those from other applications, not just those from the first application, makes the use of agents more flexible and further enhances the user experience. In one possible design, the output of the first prompt message includes: displaying the navigation bar in a first color.

[0027] Therefore, in this embodiment of the application, the user is reminded to use the recommended smart agent by the color of the navigation bar, resulting in a better user experience.

[0028] In one possible design, the first agent satisfies at least one of the following: The first intelligent agent is related to the current display interface of the first application; or, The first intelligent agent is an intelligent agent authorized for use by the first application; or, The first agent is an agent that has been used recently; or, The first intelligent agent is an intelligent agent whose usage frequency is higher than a preset frequency.

[0029] Therefore, in this embodiment, during the foreground operation of the first application, the electronic device can run an agent of another application related to the current display interface of the first application, or run an agent of another application authorized for use by the first application, or run a recently used agent, or run an agent used more frequently than a preset frequency. In short, during the foreground operation of the first application, it is not limited to using only the agent of the first application; agents of other applications can also be used, improving the flexibility of agent usage and helping to enhance the user experience.

[0030] In one possible design, the method further includes: triggering the first application to perform a third operation in response to a second operation by the user on the first agent.

[0031] It should be noted that in current technology, an intelligent agent A of an application can only control that application and cannot control other applications. Through the technical solution provided in this application, an intelligent agent of an application can control other applications, making the application scope of the intelligent agent wider and helping to improve the user experience.

[0032] In one possible design, the third operation is used to update the display interface of the first application.

[0033] Therefore, in this embodiment, an application's intelligent agent can control other applications, such as controlling other applications to update their display interfaces. This broadens the application scope of the intelligent agent and helps improve the user experience.

[0034] In one possible design, the third operation is used to configure the electronic device.

[0035] Therefore, in this embodiment, an intelligent agent of one application can control other applications, such as setting electronic devices through those other applications, for example, setting scene modes. This approach broadens the application scope of the intelligent agent and helps improve the user experience.

[0036] In one possible design, the method further includes: displaying a first interface of the first intelligent agent while the first intelligent agent is running the second application; the first interface and the display interface of the first application are displayed in a split-screen manner.

[0037] Therefore, in this embodiment, the application interface and the smart agent interface can be displayed in a split-screen manner, which makes it convenient for users to compare and use the smart agent interface with the application interface, thus helping to improve the user experience.

[0038] In one possible design, the method further includes: displaying a first interface of the first agent while the first agent is running the second application; and displaying a multitasking interface in response to the user's multitasking interface opening operation on the first interface, wherein the first interface is floating on top of the multitasking interface.

[0039] Therefore, in this embodiment, the interface of the intelligent agent can be displayed floating on top of the multitasking interface, making it convenient for users to use the intelligent agent and helping to improve the user experience.

[0040] Secondly, an electronic device is also provided for performing the method as described in the first aspect above.

[0041] Thirdly, a computer-readable storage medium is also provided for storing a computer program that, when run on a computer, causes the computer to perform the method provided in the first aspect above.

[0042] Fourthly, a computer program product is also provided, comprising a computer program that, when run on a computer, causes the computer to perform the method provided in the first aspect above.

[0043] Fifthly, a chip is also provided for performing the method as described in the first aspect above.

[0044] For the technical effects that can be achieved by the second to fifth aspects mentioned above, please refer to the description of the technical effects that can be achieved by the corresponding design scheme in the first aspect mentioned above. This application will not repeat them here. Attached Figure Description

[0045] Figures 1A to 1B A schematic diagram of an intelligent agent panel provided in an embodiment of this application; Figures 2A to 2B A schematic diagram of an electronic device provided according to an embodiment of this application; Figures 3A to 3C A schematic diagram of an intelligent agent for an application provided in an embodiment of this application; Figure 4 A schematic diagram illustrating the relationship between an application and an intelligent agent according to an embodiment of this application; Figures 5A to 5B An example diagram of a recommended intelligent agent provided in an embodiment of this application; Figures 6A to 6B Another example diagram of the recommended agent provided in an embodiment of this application; Figures 7A to 7B Another example diagram of the recommending agent provided in an embodiment of this application; Figures 8A to 8B Another example diagram of the recommending agent provided in an embodiment of this application; Figure 9 A schematic diagram illustrating the relationship between an intelligent agent and a sub-intelligent agent according to an embodiment of this application; Figures 10A to 10C An example diagram of a recommendation sub-agent provided in an embodiment of this application; Figure 11 Another example diagram of the recommendation sub-agent provided in an embodiment of this application; Figures 12A to 12C An example diagram of an agent switching process provided in an embodiment of this application; Figures 13A to 13B An example diagram of an agent invocation process provided in an embodiment of this application; Figures 14A to 14B An example diagram of an agent collaboration process provided in an embodiment of this application; Figure 14C An example diagram of an agent dialogue list provided in an embodiment of this application; Figures 15A to 15C A schematic diagram illustrating an intelligent agent control application provided in an embodiment of this application; Figures 16A to 16D Another schematic diagram of an intelligent agent control application provided in an embodiment of this application; Figure 17 A schematic diagram of a split-screen mode provided in an embodiment of this application; Figure 18 An example diagram of a multitasking interface provided in an embodiment of this application; Figure 19 Another schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0046] The following provides explanations for some of the terms used in this application. It should be noted that these explanations are for the convenience of those skilled in the art and do not constitute a limitation on the scope of protection claimed in this application.

[0047] An agent is an executable computer program that performs specific functions. Generally, agents are implemented based on artificial intelligence, such as large language models (LLMs). An agent independently performs one or more functions, such as thinking, calling tools, and processing tasks. For example, an agent primarily relies on four core modules: planning, memory, tools, and action. Planning involves the agent breaking down large tasks into sub-tasks and planning the execution order of these sub-tasks. Memory includes short-term memory and long-term memory. Short-term memory can be understood as the context generated during task execution, which can be temporarily stored in the agent and cleared after the task is completed. Long-term memory can be understood as information retained for a long time, such as a knowledge base for retrieval. Tools include, for example, providing the agent with a tool API, allowing the agent to call other modules through the API, such as calculators, search tools, code executors, etc.

[0048] To enable user interaction with the intelligent agent, the intelligent agent can provide an intelligent agent panel (hereinafter referred to as the panel), which is the display interface of the intelligent agent. Optionally, the intelligent agent's panel may include descriptive information about the intelligent agent, which includes at least one of the following: the intelligent agent's name, icon, and opening remarks. For an example, please refer to [link to example]. Figure 1A This is an exemplary schematic diagram of the panel of agent A. Figure 1A The panel for Agent A includes Agent A's name, Agent A's icon, Agent A's opening remarks, and so on.

[0049] The name of the intelligent agent can be pre-configured, for example, by the application to which the agent corresponds. For instance, the name of the intelligent agent in a weather application might be related to the name of the application it corresponds to. For example, the intelligent agent in a weather application might be named "Weather Assistant," and the intelligent agent in a Huawei video application might be named "Video Assistant," and so on.

[0050] The icon of the agent can be pre-configured, for example, by the application corresponding to the agent. For instance, the agent's icon is related to the icon of the application it corresponds to; for example, the agent's icon is identical to the icon of the application it corresponds to.

[0051] The opening statement of the agent can be pre-configured, such as by the application corresponding to the agent. Optionally, the opening statement of agent A can be a question-and-answer style opening statement or a non-question-and-answer style opening statement.

[0052] Taking a non-question-and-answer opening as an example, one possible implementation is that the opening is a welcome speech, such as... Figure 1A The greeting can start with "Hello, I am agent A". Optionally, the greeting can also include a brief introduction to agent A's functions. For example, if agent A is a weather assistant, the greeting could include: "I have weather query functions."

[0053] Taking a question-and-answer style opening as an example, one possible implementation is that when the agent starts, it answers the question (query) and displays the answer in a pop-up panel. Optionally, the question can be a preset question, such as a question pre-configured by the application corresponding to the agent. Taking a weather application as an example, assuming the preset question in the weather application is "24-hour weather changes," then when the weather assistant starts, it answers this question and displays the answer in the pop-up panel. For example, please see... Figure 1B This is an exemplary diagram of the weather assistant's panel. Figure 1B The weather assistant's panel opens with a question-and-answer format, displaying the answer to the question "24-hour weather changes".

[0054] Optional, continue with Figure 1A For example, the agent's dashboard can also include identifiers for historical questions and / or frequently asked questions. Historical questions can be understood as questions that users have historically entered into the agent's dashboard. Frequently asked questions can be understood as questions that most users have asked. Optionally, frequently asked questions can be common questions that are statistically analyzed in real time by the server of the application corresponding to the agent.

[0055] Optional, continue with Figure 1A For example, the agent's panel may also include an input module, which can be a voice input module and / or a text input module. Taking a voice input module as an example, the agent's panel might include a "Press and hold to speak" button, allowing voice input when the button is pressed. Taking a text input button as an example, the agent's panel might include a virtual keyboard for inputting text information.

[0056] Therefore, users can input commands within the agent's dashboard to enable the agent to process those commands. For example, a user can input a voice command through the voice input module within the agent's dashboard, and the agent can convert the voice command into text information and display the text information in a conversational manner within the dashboard. Furthermore, the agent can also output responses, such as displaying the text message "Processing for you" in a conversational manner within the dashboard.

[0057] The embodiments of this application involve at least one, including one or more; where "multiple" means two or more. Furthermore, it should be understood that in the description of this specification, terms such as "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or order. For example, the first identifier and the second identifier do not represent the degree of importance or order of the two, but are merely for descriptive distinction. In the embodiments of this application, "and / or" merely describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0058] The directional terms mentioned in the embodiments of this application, such as "up", "down", "left", "right", "inner", and "outer", are only for reference to the directions in the accompanying drawings. Therefore, the directional terms used are for better and clearer explanation and understanding of the embodiments of this application, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0059] References to "one embodiment," "in some examples," or "some embodiments" as described in this specification mean that one or more embodiments of this specification include a particular feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in some examples," "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. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0060] The interaction method provided in this application can be applied to electronic devices. For example, an electronic device can be a terminal device. Terminal devices may include portable devices such as mobile phones, tablets, laptops, personal computers (PCs), ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs); or they may be wearable devices such as watches and wristbands; or they may be large-screen devices such as smart screens and televisions; or they may be in-vehicle devices; or they may be virtual reality (VR) devices, augmented reality (AR) devices, mixed reality (MR) devices, etc. In short, this application does not limit the specific type of terminal device. The terminal device can use the interaction method provided in this application to achieve flexible use of the intelligent agent and improve the user experience of the intelligent agent, which will be explained in detail later.

[0061] Figure 2A This is a schematic diagram of an electronic device provided according to an embodiment of this application. The electronic device may, for example, be one of the terminal devices listed above. Figure 2A As shown, the electronic device 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, an antenna 1, an 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, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. 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, a bone conduction sensor 180M, etc.

[0062] 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, memory, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). Different processing units may be independent devices or integrated into one or more processors. The controller may serve as the nerve center and command center of the electronic device. The controller can generate operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution. Processor 110 may also include memory for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. This memory can store instructions or data that processor 110 has just used or is recurring. If processor 110 needs to reuse an instruction or data, it can directly retrieve it from the memory. This avoids repeated access, reduces the waiting time of processor 110, and thus improves system efficiency.

[0063] Optionally, the processor 110 can be used to execute the interaction method provided in the embodiments of this application. For example, after detecting an agent invocation event, the processor 110 can recommend agents to the user, such as determining N agents from M agents and displaying the identifiers of the N agents for the user to choose from. Here, the N agents correspond to N different applications. Therefore, in this way, flexible use of agents can be achieved, improving the user's experience with agents.

[0064] In some embodiments, the processor 110 may include one or more interfaces. 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 subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0065] The I2C interface is a bidirectional synchronous serial bus, including a serial data line (SDA) and a serial clock line (SCL). In some embodiments, the processor 110 may include multiple I2C buses. The processor 110 can couple to the touch sensor 180K, charger, flash, camera 193, etc., through different I2C bus interfaces. For example, the processor 110 can couple to the touch sensor 180K through the I2C interface, enabling the processor 110 and the touch sensor 180K to communicate through the I2C bus interface, thereby realizing the touch function of the electronic device 100.

[0066] The I2S interface can be used for audio communication. In some embodiments, the processor 110 may include multiple I2S buses. The processor 110 can be coupled to the audio module 170 via the I2S bus to enable communication between the processor 110 and the audio module 170. In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 via the I2S interface to enable the function of answering phone calls through a Bluetooth headset.

[0067] The PCM interface can also be used for audio communication, sampling, quantizing, and encoding analog signals. In some embodiments, the audio module 170 and the wireless communication module 160 can be coupled via the PCM bus interface. In some embodiments, the audio module 170 can also transmit audio signals to the wireless communication module 160 via the PCM interface, enabling the function of answering phone calls through a Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.

[0068] The UART interface is a universal serial data bus used for asynchronous communication. This bus can be a bidirectional communication bus. It converts the data to be transmitted between serial and parallel communication. In some embodiments, the UART interface is typically used to connect the processor 110 and the wireless communication module 160. For example, the processor 110 communicates with the Bluetooth module in the wireless communication module 160 via the UART interface to implement Bluetooth functionality. In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 via the UART interface to enable music playback through Bluetooth headphones.

[0069] The MIPI interface can be used to connect the processor 110 to peripheral devices such as the display screen 194 and the camera 193. The MIPI interface includes a camera serial interface (CSI) and a display serial interface (DSI). In some embodiments, the processor 110 and the camera 193 communicate via the CSI interface to enable the electronic device 100 to capture images. The processor 110 and the display screen 194 communicate via the DSI interface to enable the electronic device 100 to display images.

[0070] The GPIO interface can be configured via software. It can be configured as a control signal or a data signal. In some embodiments, the GPIO interface can be used to connect the processor 110 to a camera 193, a display screen 194, a wireless communication module 160, an audio module 170, a sensor module 180, etc. The GPIO interface can also be configured as an I2C interface, an I2S interface, a UART interface, a MIPI interface, etc.

[0071] USB port 130 is a USB standard compliant interface, specifically a Mini USB port, Micro USB port, USB Type-C port, etc. USB port 130 can be used to connect a charger to charge electronic device 100, and can also be used for data transfer between electronic device 100 and peripheral devices. It can also be used to connect headphones for audio playback. This interface can also be used to connect other electronic devices, such as AR devices.

[0072] It is understood that the interface connection relationships between the modules illustrated in the embodiments of the present invention are merely illustrative and do not constitute a structural limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0073] The wireless communication function of the electronic device can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor, and baseband processor. Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the electronic device can be used to cover one or more communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in conjunction with a tuning switch.

[0074] The mobile communication module 150 can provide solutions for wireless communication applications including 2G / 3G / 4G / 5G in electronic devices. 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 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.

[0075] The wireless communication module 160 can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) 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.

[0076] In some embodiments, antenna 1 of the electronic device is coupled to mobile communication module 150, and antenna 2 is coupled to wireless communication module 160, enabling the electronic device to communicate with networks and other devices via wireless communication technology.

[0077] The display screen 194 is used to display the application's interface, etc. The display screen 194 includes a display panel. In some embodiments, the electronic device may include one or more display screens 194.

[0078] The electronic device 100 can perform shooting functions through an ISP, a camera 193, a video codec, a GPU, a display 194, and an application processor. The ISP is used to process the data fed back by the camera 193.

[0079] Internal memory 121 can be used to store computer executable program code, which includes instructions. Processor 110 executes various functional applications and data processing of the electronic device by running the instructions stored in internal memory 121. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system and software code for at least one application program. The data storage area may store data generated during the use of the electronic device (e.g., images, videos, etc.). Furthermore, internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, general-purpose flash memory, etc.

[0080] 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. The external memory card communicates with the processor 110 through the external storage interface 120 to perform data storage functions. For example, images, videos, and other files can be saved on the external memory card.

[0081] Electronic devices can implement audio functions such as music playback and recording through audio modules 170, speakers 170A, receivers 170B, microphones 170C, headphone jacks 170D, and application processors.

[0082] The audio module 170 is used to convert digital audio information into analog audio signals for output, and also to convert analog audio input into digital audio signals. The audio module 170 can also be used for encoding and decoding audio signals. In some embodiments, the audio module 170 may be located in the processor 110, or some functional modules of the audio module 170 may be located in the processor 110.

[0083] The speaker 170A, also known as a "loudspeaker," is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music or listen to hands-free calls and other external playback scenarios through one or more speakers 170A.

[0084] The receiver 170B, also known as a "handpiece," can be one or more, and is used to convert audio electrical signals into sound signals. When the electronic device 100 answers a telephone call or voice message, the receiver 170B can be brought close to the ear to listen to the voice.

[0085] The microphone 170C, also known as a "microphone" or "voice transducer," is used to convert sound signals into electrical signals.

[0086] The 170D headphone jack is used to connect wired headphones.

[0087] The pressure sensor 180A is used to sense pressure signals and can convert the pressure signals into electrical signals. In some embodiments, the pressure sensor 180A may be disposed on the display screen 194.

[0088] The gyroscope sensor 180B can be used to determine the motion attitude of an electronic device. In some embodiments, the gyroscope sensor 180B can determine the angular velocity of the electronic device about three axes (i.e., the x, y, and z axes). The gyroscope sensor 180B can be used for image stabilization.

[0089] The barometric pressure sensor 180C is used to measure air pressure. In some embodiments, the electronic device calculates altitude using the air pressure value measured by the barometric pressure sensor 180C to assist in positioning and navigation.

[0090] The magnetic sensor 180D includes a Hall effect sensor. Electronic devices can use the magnetic sensor 180D to detect the opening and closing of a flip cover.

[0091] The 180E accelerometer can detect the magnitude of acceleration in various directions (typically three axes) of electronic devices. When the electronic device is stationary, it can detect the magnitude and direction of gravity.

[0092] The 180F distance sensor is used to measure distance. Electronic devices can measure distance using infrared or laser.

[0093] The proximity sensor 180G may include, for example, a light-emitting diode (LED) and a light detector, such as a photodiode. The LED may be an infrared LED. The electronic device emits infrared light outward through the LED. The electronic device uses the photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that an object is near the electronic device. When insufficient reflected light is detected, the electronic device can determine that no object is near the electronic device.

[0094] An ambient light sensor 180L is used to detect ambient light levels. Electronic devices can adaptively adjust the brightness of the display screen 194 based on the detected ambient light levels.

[0095] The fingerprint sensor 180H is used to collect fingerprints.

[0096] The 180J temperature sensor is used to detect temperature.

[0097] Touch sensor 180K, also known as a "touch panel," can be located on display screen 194. The touch sensor 180K and display screen 194 together form a touchscreen, also known as a "touch screen." Touch sensor 180K is used to detect touch operations applied to or near it. The touch sensor can then transmit the detected touch operation to the application processor to determine the type of touch event.

[0098] The bone conduction sensor 180M can acquire vibration signals. In some embodiments, the bone conduction sensor 180M can acquire vibration signals from the vibrating bone segments of the human vocal cords.

[0099] Buttons 190 include a power button, volume buttons, etc. Buttons 190 can be mechanical buttons or touch buttons. The electronic device can receive button inputs and generate key signal inputs related to user settings and function control. Motor 191 can generate vibration alerts. Motor 191 can be used for incoming call vibration alerts or for touch vibration feedback. Indicator 192 can be an indicator light, used to indicate charging status, battery level changes, messages, missed calls, notifications, etc. SIM card interface 195 is used to connect a SIM card. The SIM card can be inserted into or removed from the SIM card interface 195 to achieve contact and separation with the electronic device.

[0100] Understandable, Figure 2A The components shown do not constitute a specific limitation on the electronic device. The electronic device in the embodiments of the present invention may include, but is not limited to, components that are more advanced than those shown. Figure 2A More or fewer parts. Furthermore, Figure 2A The combination / connection relationships between the components can also be adjusted and modified.

[0101] Figure 2B This is another schematic diagram of an electronic device provided according to an embodiment of this application. The electronic device may be, for example, the terminal devices listed above. Figure 2B This can be understood as a software architecture diagram of an electronic device. For example... Figure 2BThe software architecture of an electronic device can be a layered structure. A layered architecture divides the software into several layers, each with a clear role and function. Layers communicate with each other through software interfaces. Such a layered architecture can be, for example, an event-driven architecture, a microkernel architecture, a microservices architecture, or a cloud architecture. This application uses a layered Android® system as an example to illustrate the software architecture of an electronic device. In some embodiments, the Android® system is divided into five layers, from top to bottom: the application layer, the application framework layer, the Android runtime and system libraries, the kernel layer, and the hardware layer.

[0102] like Figure 2B The application layer can include a first application and a first intelligent agent, a second application and a second intelligent agent, etc. The first intelligent agent is an intelligent agent of the first application, and the second intelligent agent is an intelligent agent of the second application. Optionally, the software package of the first intelligent agent can be located within the application package of the first application or outside the application package of the first application. The software package of the second intelligent agent can be located within the application package of the second application or outside the application package of the second application. For example, the first application can be a browser application, a reading application, an instant messaging application, an image capture application, a video playback application, an audio playback application, a shopping application, etc., and the specific type is not limited. The second application and the first application can be the same type of application or different types of applications. Optionally, the first application and / or the second application are third-party applications or system applications. It should be noted that... Figure 2B In this example, taking the first and second intelligent agents as being located inside an electronic device, optionally, the first and / or second intelligent agents can also be located on a server, which can be the server corresponding to the electronic device. For example, if the electronic device is a Huawei terminal device, then the server is a Huawei server. Therefore, the electronic device can access the first and / or second intelligent agents through the server.

[0103] 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. For example... Figure 2BAs shown, the application framework layer may include an interface module for implementing interactions between different intelligent agents, or interactions between an application and an intelligent agent. Taking interactions between different intelligent agents as an example, for instance, a first intelligent agent can interact with a second intelligent agent through the interface module. The interaction process between different intelligent agents is described in Embodiment 3 below. Taking interactions between an application and an intelligent agent as an example, for instance, during the operation of a first application by an electronic device, the first application can call an intelligent agent through the interface module. Exemplarily, the first application can call a first intelligent agent, or it can call an intelligent agent of another application, such as calling a second intelligent agent of a second application. The interaction process between an application and an intelligent agent is described in Embodiment 4 below. It should be noted that... Figure 2B Taking the example of the interface module being located in the application framework layer, it is optional that the interface module can also be located in other layers, such as the system library or kernel layer, without limitation. It is understandable that, although... Figure 2B Although not shown in the diagram, the application framework layer may also include content providers, view systems, call managers, resource managers, notification managers, etc. Content providers store and retrieve data, making this data accessible to the application. This data may include videos, images, audio, made and received calls, browsing history and bookmarks, phone books, etc. View systems include visual controls, such as controls for displaying text and controls for displaying images. View systems can be used to build applications. The display interface can consist of one or more views. For example, a display interface including a text notification icon may include views for displaying text and views for displaying images. The call manager provides communication functions for electronic devices, such as managing call status (including connection, hang-up, etc.). The resource manager provides the application with various resources, such as localized strings, icons, images, layout files, video files, etc. The notification manager allows the application to display notification information in the status bar. It can be used to convey informational messages and can disappear automatically after a short pause without user interaction. For example, the notification manager is used to notify of download completion, message alerts, etc. The notification manager can also display notifications as icons or scrolling text in the system's 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 alert sounds, causing electronic devices to vibrate, and flashing indicator lights.

[0104] The Android Runtime consists of the core libraries and the virtual machine. The Android runtime is responsible for scheduling and managing the Android system. The core libraries consist of two parts: one part contains the functionalities that Java needs to call, and the other part is the core Android library itself. The application layer and application framework layer run in the 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] The system library can include multiple functional modules, such as a surface manager, media libraries, 3D graphics processing libraries (e.g., OpenGL ES), and 2D graphics engines (e.g., SGL). The surface manager manages the display subsystem and provides fusion of 2D and 3D layers for multiple applications. The media libraries support playback and recording of various common audio and video formats, as well as still image files. They support multiple audio and video encoding formats, such as MPEG4, H.264, MP3, AAC, AMR, JPG, and PNG. The 3D graphics processing libraries implement 3D graphics drawing, image rendering, compositing, and layer processing. The 2D graphics engine is the drawing engine for 2D graphics.

[0106] The kernel layer is the layer between hardware and software. The kernel layer can contain hardware drivers, such as display drivers, camera drivers, audio drivers, and so on.

[0107] The hardware layer includes various hardware components such as displays, touch sensors, and cameras.

[0108] Understandable, Figure 2B The software structure shown does not constitute a specific limitation on the software structure of electronic devices. The software structure of the electronic devices in the embodiments of the present invention may include, but is not limited to, the following: Figure 2B More or fewer modules, for example, than Figure 2B More or fewer layers, or, a layer containing more than Figure 2B More or fewer modules, etc. Furthermore, Figure 2B The combination / connection relationships between modules can also be adjusted and modified.

[0109] The following description mainly uses a mobile phone as an example of an electronic device, and describes the technical solution provided by the embodiments of this application in conjunction with the accompanying drawings.

[0110] As described in the background section, many applications are now developing their own intelligent agents. For example, application A has an intelligent agent A, and application B has an intelligent agent B. However, the current use of intelligent agents has the following two drawbacks: First, intelligent agents cannot operate independently; they can only operate when an application is running. For example, agent A can only operate when application A is running. Similarly, agent B can only operate when application B is running.

[0111] Second, agents in different applications are isolated from each other. For example, during the operation of application A, agent A can be used, but agent B cannot be used; similarly, during the operation of application B, agent B can be used, but agent A cannot be used.

[0112] Because of these two mechanisms, if a user wants to use an agent from another application while one application is running, they must switch applications. For example, if a user wants to use agent B from application B while application A is running, the electronic device must be switched from application A to application B to use agent B. However, the application switching process is cumbersome and negatively impacts the user experience.

[0113] For ease of understanding, Figure 3A Provide an example. For instance... Figure 3A (a) Running Xiaohongshu in the foreground on the mobile phone ® Therefore, users can access Xiaohongshu. ® Intelligent agents, such as Xiaohongshu Assistant ® At this point, if the user wants to use the browser application's intelligent agent, they need to open Xiaohongshu. ® Switch to a browser application. For example, as Figure 3A (b) The browser application runs in the foreground on the phone. Therefore, the user can invoke the browser application's intelligent agent, such as a browser assistant. Figure 3A It can be seen that the intelligent agents in different applications are isolated from each other.

[0114] Continue with Figure 3A (b) For example, after the phone receives the operation to enter the multitasking interface, it displays as follows: Figure 3B (a) shows the multitasking interface. The multitasking interface includes a floating window for the currently running application. For example, Figure 3B In (a), the multitasking interface includes a floating window of the browser application, which contains the browser application's agent. Figure 3B In (a), the phone receives a left / right swipe gesture and displays as shown below. Figure 3B (b) The multitasking interface, which includes Xiaohongshu. ® A floating window containing Xiaohongshu (Little Red Book).® Intelligent agents. Through Figure 3B As can be seen, during the process of switching the application window from a full-screen window to a floating window, the application's intelligent agent scales with the window and always remains within the application window, without moving out of the application window's range.

[0115] The above text passed Figure 3A and Figure 3B This example illustrates the shortcomings of current intelligent agents in use. The following section will combine... Figure 3C Explain the reasons for the aforementioned defects. For example... Figure 3C Agent A is part of application A, for example, a function of application A; Agent B is part of application B, for example, a function of application B. Therefore, as part of an application, an agent cannot run independently of the application and can only be used while the application is running. Furthermore, the agent's panel (see the glossary section above for more information on panels) is part of the application's window and will not move out of the application's window area; therefore, [the following occurs]. Figure 3B In this context, the panel for each agent in a multitasking interface is located within the window of its corresponding application. Furthermore, agent A does not belong to application B, and agent B does not belong to application A; therefore, agents from different applications are isolated from each other, and cross-application agent usage will not occur.

[0116] As can be seen from the above, users currently have a poor experience using intelligent agents on terminal devices.

[0117] Therefore, embodiments of this application provide a method for running intelligent agents, which enables the operation of intelligent agents across applications, thereby breaking the limitation of isolation between intelligent agents in different applications in traditional technologies. As an example, while an electronic device is running application A (e.g., in the foreground), it can run intelligent agent B of application B. In other words, while application A is running in the foreground, the user can use intelligent agent B of application B. This approach enables flexible use of intelligent agents and enhances the user experience.

[0118] The technical solutions provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0119] As mentioned above, the use of intelligent agents in the technical solutions provided in this application is relatively flexible and can be invoked across applications.

[0120] In one possible implementation, the intelligent agent in this application embodiment can operate independently of the corresponding application. For example, such as Figure 4Application A corresponds to an agent called Agent A, and application B corresponds to an agent called Agent B. Agent A can run independently of application A, meaning it is not limited to being used only when application A is running; similarly, Agent B can run independently of application B, meaning it is not limited to being used only when application B is running. As a specific implementation, an application can expose its agent to the operating system of an electronic device, allowing the operating system to call the agent, thus enabling the agent to run independently of the application. In other words, in traditional technology, an application's agent is only called by the application itself, and the operating system of the electronic device cannot call it, thus preventing the agent from running independently; however, in this embodiment, after the application exposes its agent to the operating system, the operating system can call the agent, enabling the agent to run independently. One possible way for an application to expose its agent to the operating system is that the application can perform actions related to authorizing the operating system to call it (e.g., processing the agent's software package according to the operating system's interface protocol), so that after the application is installed on the electronic device, the operating system of the electronic device can call its agent. For example, the operating system of an electronic device provides an interface through which the application's intelligent agent can be invoked. Exemplarily, this interface could be an Application Programming Interface (API). Optionally, the invocation interfaces of intelligent agents in different applications can be the same or different, without limitation.

[0121] Assume an electronic device includes M applications, where M is a positive integer, and each of the M applications corresponds to one of the M intelligent agents. Each of the M intelligent agents can run independently of its corresponding application. The relationship between the M applications and the M intelligent agents can be one-to-one, meaning one application corresponds to one intelligent agent. Alternatively, the relationship can be non-one-to-one, without limitation. Optionally, the M applications may include third-party applications, i.e., applications not included in the operating system. In this case, the electronic device can invoke any one or more of the M intelligent agents. As an example, the electronic device can recommend intelligent agents to the user. For instance, after detecting an intelligent agent invocation event, the electronic device recommends N intelligent agents from the M intelligent agents for the user to choose from. This recommendation method allows for wider use of the intelligent agents in each application.

[0122] Example 1

[0123] This first embodiment illustrates the process of an electronic device recommending agents. For example, after detecting an agent activation event, the electronic device recommends N agents to the user based on the event. These N agents correspond to N different applications, where N is a positive integer and is less than or equal to M.

[0124] Optionally, the agent activation event can include several types: First, the agent activation event is the launch event of a first application; second, the agent activation event is the interface switching event of the first application; wherein, the first application is any application in the electronic device, which can be a system application or a third-party application, without limitation; third, the agent activation event is the event in which the user inputs an agent activation operation; fourth, the agent activation event is the wake-up event of a system assistant (e.g., Xiaoyi). For ease of understanding, the above four types of agent activation events are shown in Table 1 below.

[0125] Table 1: Agent Evocation Events

[0126] It should be noted that Table 1 above is a brief description of the four agent call-up events. The following text will provide a detailed description of each agent call-up event.

[0127] The first type is where the agent call-up event is the startup event of the first application.

[0128] For example, if an electronic device detects the launch event of a first application, it recommends N smart agents to the user, with each of the N smart agents corresponding to a different application. As one possible implementation, the N smart agents are N smart agents that are associated with the first application.

[0129] As an example, the first agent of the first application is included among the N agents. In other words, if the electronic device detects the launch event of the first application, it recommends the agent of the first application. For example, such as... Figure 5A (a) Electronic devices launch Didi Chuxing ® Applications in Didi Chuxing ® Didi Chuxing is displayed in the application's interface (e.g., the homepage). ® Application agents (e.g., Didi Assistant) ® The electronic device receives an identifier for Didi Assistant. ® The operation of the identifier, as shown in the image. Figure 5A (b) Didi Assistant ® The panel includes Didi Assistant. ® Description information, such as name, icon, opening remarks, etc.

[0130] As another example, among the N agents, there is an agent that allows (or authorizes) other applications to be invoked by the first application. For example, a second agent for a second application, which is different from the first application. In other words, the electronic device detects the launch event of the first application and can recommend the second agent of the second application to the user. For example, see [link to example]. Figure 5A (c) Electronic devices launch Didi Chuxing® Applications in Didi Chuxing ® Didi Chuxing is displayed in the application's interface (e.g., the homepage). ® Application agents (e.g., Didi Assistant) ® The electronic device receives an action targeting the weather assistant's identifier and displays an identifier such as... Figure 5A (d) shows the weather assistant panel.

[0131] As mentioned above, the N intelligent agents include intelligent agents of other applications that are allowed to be invoked by the first application. As one possible implementation, the electronic device can determine the intelligent agents of other applications that are allowed to be invoked by the first application based on the application package name of the first application and a first correspondence relationship. The first correspondence relationship describes the intelligent agents that are allowed to be invoked by each application. For example, please refer to Table 2 below, which is an example of a first correspondence relationship.

[0132] Table 2: First Correspondence

[0133] Therefore, the electronic device can determine the intelligent agents of other applications that the first application is allowed to call, based on the application package name of the first application and the first correspondence (e.g., Table 2 above). It should be noted that the electronic device needs to obtain the first correspondence beforehand. One possible implementation is that after the electronic device downloads application B, the application package of application B contains a whitelist, which includes the application package name. The application corresponding to the application package name in the whitelist is the application that is allowed to call the intelligent agent B of application B. For example, if the whitelist includes the package name of application A, then application A is allowed to call the intelligent agent B of application B. In other words, for application A, the intelligent agents it is allowed to call include the intelligent agent B of application B, i.e., the first row in Table 1 above. Therefore, the electronic device can generate the aforementioned first correspondence through the whitelists of each application.

[0134] The above embodiments illustrate the process by which an electronic device recommends N intelligent agents to a user after detecting the launch event of a first application. Recommending N intelligent agents to the user means displaying relevant information about N intelligent agents. Optionally, recommending N intelligent agents to the user may include method A and / or method B.

[0135] Method A: Displaying identifiers for N intelligent agents. Optionally, the identifiers for the intelligent agents may include the agent's name and / or icon. This application embodiment does not limit the display style of the intelligent agent identifiers. As an example, the intelligent agent identifiers may be in the form of bubbles (chips). Exemplarily, the identifiers of the N intelligent agents may be displayed on the homepage of the first application, or on other interfaces accessed from the homepage. Optionally, the identifiers of the N intelligent agents may be superimposed on top of the window of the first application. To avoid obscuring the display content of the first application, the identifiers of the N intelligent agents may be located near the edge. For example, Figure 5A In the diagram, the identifiers for the N agents are located near the bottom edge, such as in the navigation bar area. It should be noted that... Figure 5A In (a) or (c), taking the N smart agent identifiers located on the homepage of the first application as an example, optionally, the N smart agent identifiers can also be located on other interfaces of the first application besides the homepage. As an example, during the process of switching interfaces of the first application, the N smart agent identifiers are always displayed, for example, always displayed on the top layer of the first application window. Considering that the smart agent identifiers may disturb the user, the electronic device can hide the N smart agent identifiers. One hiding method is automatic hiding, for example, if the electronic device determines that the display duration of the N smart agent identifiers has reached a preset duration, then it automatically hides the N smart agent identifiers. Another hiding method is manual hiding, for example, if the electronic device receives a hide operation to hide the N smart agent identifiers, then it hides the N smart agent identifiers. Optionally, after the N smart agent identifiers are hidden, the electronic device can also recall the N smart agent identifiers, for example, if the electronic device receives a recall operation to recall the N smart agent identifiers, then it displays the N smart agent identifiers.

[0136] Method B involves pulling up the panel of the first agent of the first application, displaying the identifiers of the other agents among N agents besides the first agent of the first application. For example, the identifiers of the other agents can be located at the bottom of the panel of the first agent. In other words, after receiving the launch event of the first application, the electronic device pulls up the panel of the application's agents and recommends agents to the user within that panel.

[0137] In the above embodiments, if the electronic device detects the launch event of the first application, it recommends N agents to the user. In other embodiments, after detecting the launch event of the first application, the electronic device may display a prompt message to inform the user that there are agents to be recommended, and after receiving a user operation, display the agents to be recommended. For example, please refer to 5B(a), after the electronic device receives the launch event of the first application, it displays a prompt message on the homepage of the first application, such as the navigation bar being displayed in a first color, to inform the user that there are agents to be recommended. When the electronic device receives a user operation, such as an operation on the navigation bar, it displays... Figure 5B (b) The identifier of the intelligent agent. It should be noted that... Figure 5B (a) uses a black navigation bar as an example. In practical applications, the navigation bar can be other colors, such as multicolor.

[0138] The second type is where the agent call-up event is the interface switching event of the first application.

[0139] For example, an electronic device detects an interface switching event of a first application and recommends N smart agents to the user, with each of the N smart agents corresponding to a different application. As one possible implementation, the N smart agents are N smart agents that have an association with the interface of the first application after the switch.

[0140] As an example, the N agents include the first agent of the first application. In other words, if the electronic device detects an interface switching event of the first application, it recommends the agent of the first application to the user.

[0141] As another example, the N agents include those that are associated with the context of the interface after the first application is switched. In other words, when the electronic device detects an interface switching event of the first application, it determines the agents that are associated with the context of the switched interface and recommends those agents. For example, please see... Figure 6A (a) Electronic device displays wasp nest ® An application interface detects an interface switching event and switches to, for example... Figure 6A The interface shown in (b) is an example. The electronic device can determine the context of the switched interface; for example, if the context is tourism, it can identify intelligent agents related to tourism, such as a weather assistant and a flight assistant. ® These two intelligent agents display the icons for the weather assistant and the flight assistant. ® The logo, such as Figure 6A (b). For example, a weather assistant is an intelligent agent for a weather application, and a flight assistant... ® It's Flight Manager ® The intelligent agent of the application.

[0142] In this approach, after the electronic device determines the context of the interface after the first application switch, it needs to determine the intelligent agent associated with the context. As one possible implementation, the electronic device can determine the intelligent agent associated with the context based on the context and a second correspondence. The second correspondence describes the intelligent agents corresponding to various contexts. For example, please refer to Table 3 below, which provides an example of a second correspondence.

[0143] Table 3: Second Correspondence

[0144] Therefore, the electronic device can determine the agent associated with the context based on the context and the second correspondence (e.g., Table 3 above). It should be noted that the electronic device needs to obtain the second correspondence beforehand. One possible implementation is that after the electronic device downloads application B, the configuration file in the application package of application B declares the context in which agent B of application B applies. For example, agent B of application B applies to travel, as shown in the first row of Table 3 above. Therefore, the electronic device can generate the aforementioned second correspondence through the configuration files of each application.

[0145] It is understandable that the first application may experience more than one interface switching event. In one possible implementation, the electronic device recommends an agent based on the context of the switched interface each time it detects an interface switching event. In another possible implementation, an agent is recommended only when the first application switches to a specific interface, based on the context of that specific interface; otherwise, no agent recommendation is required. The specific interface may be a pre-configured interface of the first application.

[0146] The above embodiments illustrate the process by which an electronic device recommends N intelligent agents to the user after detecting an interface switching event of a first application. Optionally, recommending N intelligent agents to the user may include method A and / or method B. Method A involves displaying the identifiers of the N intelligent agents. Method B involves pulling up the panel of the first intelligent agent of the first application, and displaying the identifiers of the other intelligent agents among the N intelligent agents besides the first intelligent agent of the first application in this panel. For details on methods A and B, please refer to the preceding description, which will not be repeated here.

[0147] In the above embodiments, if the electronic device detects an interface switching event of the first application, it recommends N intelligent agents to the user. In other embodiments, after detecting an interface switching event of the first application, the electronic device may display a prompt message to inform the user that there are intelligent agents to be recommended, and after receiving a user operation, display the intelligent agents to be recommended. For example, please refer to 6B(a), after the electronic device receives an interface switching event of the first application, it switches to the interface of the first application as shown in the figure. Figure 6B (b) The interface displays prompts, such as the navigation bar being displayed in the first color, indicating to the user that there are intelligent agents to be recommended. When the electronic device receives a user action, such as an action on the navigation bar, it displays... Figure 6B (c) The identifier of the intelligent agent. It should be noted that... Figure 6B (b) uses a black navigation bar as an example. In practical applications, the navigation bar can be other colors, such as multicolor.

[0148] The third type is the agent invocation event, which is an event where the user inputs an action to invoke the agent.

[0149] Optionally, the agent invocation operation can be an operation targeting a first preset component, a first preset gesture operation, etc. Examples are given below.

[0150] I. Taking the agent activation operation as an example, which is an operation targeting a first preset component. Optionally, the first preset component can be a virtual button and / or a physical button. If the first preset component is a physical button, it could be a power button, volume "+", volume "-", etc. In this case, the agent activation operation can be a double-click, triple-click, or long-press operation targeting the physical button. If the first preset component is a virtual button, it can be a newly added virtual button or a reused existing virtual button. For example, if the first preset component reuses an existing virtual button, such as a navigation bar, the agent activation operation can be a double-click or triple-click operation targeting the navigation bar. If a new virtual button is added, this new virtual button is used to activate the agent; therefore, the agent activation operation can be an operation targeting this new virtual button.

[0151] Taking a virtual button as the first preset component as an example. Optionally, the first preset component can be displayed on any interface of the electronic device, such as the desktop, the negative one screen, the application interface, etc.

[0152] (1) Taking the first preset component located within the application interface as an example. For instance, the electronic device displays the first interface of the first application, which includes the first preset component. When the electronic device receives an operation on the first preset component, it recommends N intelligent agents to the user. As one possible implementation, the electronic device can determine N intelligent agents based on the first application and / or the first interface. For the process of determining intelligent agents based on the first application, please refer to the first method mentioned above, such as determining intelligent agents based on the application package name of the first application and the first correspondence. For the process of determining intelligent agents based on the first interface, please refer to the second method mentioned above, such as determining intelligent agents based on the context of the first interface and the second correspondence.

[0153] As an example, the first agent for the first application is included among the N agents. For example, see [link to example]. Figure 7A (a) An electronic device displays a weather application interface, which includes a first preset component. The electronic device receives an operation on the first preset component and displays, as shown in the image. Figure 7A (b) shows the weather assistant logo.

[0154] As another example, the N agents include agents of other applications that allow the first application to invoke them, such as a second agent of a second application, which is different from the first application. See, for example, [link to example]. Figure 7A (a) An electronic device displays a weather application interface, which includes a first preset component. The electronic device receives an operation on the first preset component and displays, as shown in the image. Figure 7A (b) shows the Xiaohongshu assistant ® The logo.

[0155] The above embodiments illustrate the process by which an electronic device recommends N intelligent agents to a user after detecting an operation on a first preset component within a first interface. Optionally, recommending N intelligent agents to the user may include method A and / or method B.

[0156] Method A displays the identifiers of N agents. For example, Figure 5B As shown in (b).

[0157] Method B involves pulling up the panel for the first agent of the first application, which displays the identifiers of the other N agents besides the first agent of the first application. For example, please see... Figure 7A (c) The electronic device displays the interface of a weather application, which includes a first preset component. The electronic device receives an operation on the first preset component and pulls up, such as... Figure 7A (d) shows the weather assistant panel, which includes Xiaohongshu. ® The application's identifier.

[0158] (2) Taking the first preset component located on the desktop as an example. For instance, when an electronic device receives an operation on the first preset component on the desktop, it recommends N intelligent agents to the user. In this case, the N intelligent agents include at least one of the following: intelligent agents with a usage frequency higher than a preset frequency, recently used intelligent agents, default intelligent agents, and user-specified intelligent agents. Optionally, the display position of the first preset component on the desktop is not limited. For example, please refer to... Figure 7B (a) An electronic device displays a desktop, which includes a first preset component. The electronic device receives an operation on the first preset component and displays, as shown in the image. Figure 7B (b) shows N intelligent agents (e.g., weather assistant, Xiaohongshu assistant). ®The N agents are identified by their frequency of use by the user. For example, please refer to [link to relevant documentation]. Figure 7B (c) The electronic device displays a desktop, which includes a first preset component. The electronic device receives an operation on the first preset component and displays, as shown below. Figure 7B (d) shows the weather assistant panel or system assistant panel, which displays the identifiers of N agents. Among them, the weather assistant is the agent most frequently used by the user. The N agents displayed in the weather assistant panel may include at least one of the following: frequently used agents, recently used agents, default agents, and user-specified agents.

[0159] II. Taking the intelligent agent activation operation as an example of a first preset gesture operation. For example, the first preset gesture operation can be a touch operation or a non-touch operation. For touch operations, examples include drawing circles on the screen, tapping with a knuckle, or touching the screen with the palm. For non-touch operations, examples include air gestures, such as drawing circles in the air with a finger. Taking the first preset gesture operation as a touch operation as an example, after the electronic device detects the first preset gesture operation, it recommends N intelligent agents to the user. Optionally, the intelligent agents invoked through the first preset gesture operation differ depending on the interface displayed by the electronic device. Taking the electronic device displaying the desktop as an example, the intelligent agents invoked through the first preset gesture operation can include at least one of the following: intelligent agents with a usage frequency higher than a preset frequency, recently used intelligent agents, default intelligent agents, and user-specified intelligent agents. Taking the electronic device displaying the first interface of a first application as an example, the intelligent agents invoked through the first preset gesture operation can include intelligent agents associated with the first application and / or the first interface. This part has been described in detail above and will not be repeated.

[0160] The fourth type is the intelligent agent wake-up event, which is the wake-up event of the system assistant.

[0161] The system assistant can be a voice interaction portal provided by an electronic device, such as Xiaoyi on a Huawei phone. In this embodiment, after the electronic device receives a wake-up event from the system assistant (e.g., the user issues a voice command "Xiaoyi Xiaoyi"), it wakes up the system assistant, for example, by displaying the system assistant's panel and recommending N intelligent agents to the user within the panel.

[0162] In one possible implementation, the N intelligent agents include those associated with the currently running application and / or the currently displayed interface of the electronic device. For example, if the electronic device displays a first interface of a first application, and during the display of the first interface, a wake-up event from the system assistant is received, then the system assistant's panel will recommend intelligent agents associated with the first application and / or the first interface. The process of determining intelligent agents based on the first application is described in the first method above, for example, determining intelligent agents based on the application package name and a first correspondence. The process of determining intelligent agents based on the first interface is described in the second method above, for example, determining intelligent agents based on the context and a second correspondence of the first interface. As an example, the N intelligent agents include a first intelligent agent of the first application. As another example, the N intelligent agents include intelligent agents that allow (or authorize) the first application to call other applications, for example, a second intelligent agent of a second application, which is different from the first application.

[0163] In another possible implementation, the N agents include at least one of the following: agents used more frequently than a preset frequency, recently used agents, default agents, and user-specified agents.

[0164] In this approach, the electronic device recommends N intelligent agents within the system assistant's panel. Considering the small display area of ​​the system assistant's panel, recommending N intelligent agents can include displaying the identifiers of the N intelligent agents within the panel. For example, please see... Figure 8A (a) The electronic device displays the first interface of the first application. The electronic device receives the wake-up command from "Xiaoyi Xiaoyi" and wakes up the system assistant, for example, displaying... Figure 8A (b) shows the system assistant panel, which includes identifiers for N intelligent agents, such as Didi Assistant and Weather Assistant. The previous example used a user waking up the system assistant via voice command (e.g., "Xiaoyi Xiaoyi"). Optionally, the system assistant can also be woken up in other ways. For example, Figure 8A In (a), when the electronic device receives a long press operation on the navigation bar, it wakes up the system assistant. Therefore, the implementation of this application does not limit the method of waking up the system assistant.

[0165] Understandably, after waking up the system assistant, the user can input commands within the assistant's panel, such as via voice input. In this case, the electronic device detects the user's input command within the system assistant's panel and recommends intelligent agents to the user based on that command. For example, please see... Figure 8B (a) The system assistant has been activated. The electronic device detects that the user has entered the command "Is today suitable for skiing?" in the system input panel. The system assistant can respond, for example, by displaying... Figure 8B (b) shows information such as "Today's weather is suitable for skiing." Electronic devices can recommend intelligent agents based on user input, such as weather assistants and Gaode Maps assistant. For example, as shown... Figure 8B (b) The system assistant panel includes the logos for the weather assistant and the Gaode assistant.

[0166] Example 2

[0167] The preceding Example 1 illustrates the process of an electronic device recommending intelligent agents. This Example 2 illustrates the process of an electronic device recommending sub-intelligent agents. In other words, the difference between Example 2 and Example 1 is that the recommendation granularity in Example 1 is intelligent agents, while the recommendation granularity in Example 2 is sub-intelligent agents. The intelligent agents and sub-intelligent agents will be described below.

[0168] An intelligent agent can include one or more sub-agents. For example, a weather assistant includes a weather forecast sub-agent and a clothing suggestion sub-agent. Similarly, a gallery app's gallery assistant can include a pedestrian removal sub-agent and a photo enhancement sub-agent.

[0169] In the embodiments of this application, the sub-agent can operate independently of the main agent. For example, please refer to... Figure 9 Agent A includes sub-agents A1 and A2. Sub-agents A1 and A2 can operate independently of Agent A. Agent B includes sub-agents B1 and B2. Sub-agents B1 and B2 can operate independently of Agent B. As one possible implementation, the application can expose the various sub-agents included in the application's agent to the operating system of the electronic device, so that the operating system can call the various sub-agents, thereby enabling the various sub-agents to operate independently. The principle of this part is the same as the principle of the application exposing its agent to the electronic device in Embodiment 1 above, and will not be repeated.

[0170] Suppose an electronic device includes M applications, each application corresponds to one of M agents, and each agent includes one or more sub-agents, for a total of P sub-agents. The electronic device can invoke one or more of the P sub-agents. For example, after detecting a sub-agent invoke event, the electronic device can recommend Q sub-agents out of the P to the user.

[0171] As mentioned earlier, after detecting a sub-agent activation event, the electronic device can recommend Q sub-agents to the user. Optionally, the sub-agent activation event can include several types: First, the sub-agent activation event is the launch event of the first application; second, the sub-agent activation event is the interface switching event of the first application; third, the sub-agent activation event is the event in which the user inputs a sub-agent activation operation; fourth, the sub-agent activation event is the wake-up event of a system assistant (e.g., Xiaoyi). For ease of understanding, Table 4 below illustrates the aforementioned four types of sub-agent activation events.

[0172] Table 4: Sub-agent Evocation Events

[0173] It should be noted that Table 4 above is a brief description of the four types of sub-agent call-up events. The following text will provide a detailed description of each type of sub-agent call-up event.

[0174] The first type is where the sub-agent call-up event is the startup event of the first application.

[0175] For example, an electronic device detects the launch event of a first application and recommends Q sub-agents to the user. These Q sub-agents can correspond to different applications. As one possible implementation, the Q sub-agents are those that are associated with the first application.

[0176] As an example, the Q sub-agents include one or more sub-agents contained in the first agent of the first application. These could be frequently used, recently used, default, or user-specified sub-agents.

[0177] As another example, the Q sub-agents include sub-agents of other applications that the first application is allowed to invoke, such as one or more sub-agents contained in the second agent of the second application. As one possible implementation, the electronic device can determine the sub-agents of other applications that the first application is allowed to invoke based on the application package name of the first application and a third correspondence. The third correspondence describes the sub-agents that are allowed to be invoked by each application. For example, please refer to Table 5 below, which provides an example of a third correspondence.

[0178] Table 5: Third Correspondence

[0179] Therefore, the electronic device can determine the sub-agents of other applications that the first application is allowed to call, based on the application package name of the first application and the third correspondence (such as Table 5 above). It should be noted that the electronic device needs to obtain the third correspondence beforehand. The principle for obtaining the third correspondence is the same as that for obtaining the first correspondence, and will not be repeated here.

[0180] The above embodiments illustrate the process by which an electronic device recommends Q sub-agents to a user after detecting the launch event of a first application. Recommending Q sub-agents to the user means displaying relevant information about the Q sub-agents. Optionally, recommending Q sub-agents to the user may include method A and / or method B.

[0181] Method A: Displaying the identifiers of Q sub-agents. The identifiers of the sub-agents may include the agent's name and / or icon. This application embodiment does not limit the display style of the agent identifiers. Regarding the display location of the sub-agent identifiers (e.g., the area where the navigation bar is located), the hiding method, and the method of recalling after hiding, please refer to the description of the first method in Embodiment 1 above, which will not be repeated here. Optionally, after the electronic device detects the launch event of the first application and displays the identifiers of the Q sub-agents, the identifiers of the Q sub-agents are always displayed regardless of which interface the first application switches to. In other words, the recommended sub-agents are the same for all interfaces of the first application. For example, please refer to... Figure 10A (a) Taking a photo gallery application as an example, after the first application starts, the homepage displays the identifiers of two sub-agents: one for generating memory videos and the other for finding travel photos. These two sub-agents are, for example, two sub-agents contained within the main agent of the first application. Figure 10A (b) After the first application switches interfaces, the identifiers of the two sub-agents are still displayed on that interface. In other words, the identifiers of the two sub-agents are displayed regardless of which interface the first application switches to.

[0182] Method B involves bringing up the panel of the first agent in the first application, displaying the identifiers of Q sub-agents within this panel. In other words, after receiving the launch event of the first application, the electronic device brings up the panel of the application's agents and recommends sub-agents to the user within this panel.

[0183] The second type is where the sub-agent call-up event is the interface switching event of the first application.

[0184] For example, an electronic device detects an interface switching event of a first application and recommends Q sub-agents to the user, with each of the Q sub-agents corresponding to a different application. As one possible implementation, the Q sub-agents are those that are associated with the interface of the first application after the switch.

[0185] As an example, the Q sub-agents include one or more sub-agents contained in the first agent of the first application. For example, sub-agents in the first agent that are associated with the switched interface.

[0186] As another example, the Q sub-agents include sub-agents of other applications that are associated with the context of the interface after the first application is switched. In this approach, after the electronic device determines the context of the interface after the first application is switched, it needs to determine the sub-agents of other applications that are associated with the context. As one possible implementation, the electronic device can determine the sub-agents of other applications that are associated with the context based on the context and a fourth correspondence. The fourth correspondence describes the sub-agents corresponding to various contexts. For example, please refer to Table 6 below, which provides an example of a fourth correspondence.

[0187] Table 6: Fourth Correspondence

[0188] Therefore, the electronic device can determine the sub-agents of other applications that are associated with the context based on the context and the fourth correspondence (e.g., Table 6 above). It should be noted that the electronic device needs to obtain the fourth correspondence beforehand. The principle for obtaining the fourth correspondence is the same as that for obtaining the second correspondence in Embodiment 1 above, and will not be repeated here.

[0189] It is understandable that the first application may experience more than one interface switching event. In one possible implementation, each time the electronic device detects an interface switching event, it determines the sub-agent based on the context of the switched interface. For example, see [link to relevant documentation]. Figure 10B (a) Taking the first application as a photo gallery application as an example, the first application displays a first interface, within which the identifiers of two sub-agents are displayed: the identifier of the sub-agent for generating memory videos and the identifier of the sub-agent for finding travel photos. For example... Figure 10B (b) The first application switches to the second interface, which displays the identifiers of two other sub-agents: the pedestrian removal sub-agent and the image enhancement sub-agent.

[0190] In another possible implementation, the sub-agent is recommended only when the first application switches to a specific interface, based on the context of that specific interface; otherwise, no sub-agent is recommended. The specific interface can be a pre-configured interface of the first application. For example, see [link to relevant documentation]. Figure 10C (a) Taking the first application as an example, the first application displays the first interface, and no sub-agents are recommended at this time. For example... Figure 10C(b) When the first application switches to a specific interface (e.g., Highlights), it recommends sub-agents based on the context of the specific interface, such as displaying identifiers for sub-agents that generate travel memories or sub-agents that generate annual memories. In other embodiments, after the first application enters a specific interface, it does not need to recommend sub-agents based on the context of the specific interface. The sub-agents corresponding to the specific interface have been pre-configured. For example, after an electronic device downloads an application, the application package of that application has already configured the specific interface of the application and the sub-agents corresponding to the specific interface.

[0191] The above embodiments illustrate the process by which an electronic device recommends a sub-agent to the user after detecting an interface switching event of a first application. Optionally, recommending a sub-agent to the user may include method A and / or method B. Method A involves displaying the identifier of the sub-agent. Method B involves pulling up the panel of the first agent in the first application and displaying the identifier of the sub-agent within that panel. For details on methods A and B, please refer to the preceding description; they will not be repeated here.

[0192] In the above embodiments, if the electronic device detects an interface switching event of the first application, it recommends a sub-agent to the user. In other embodiments, after detecting an interface switching event of the first application, the electronic device may display a prompt message to inform the user that there is a sub-agent to be recommended, and after receiving a user operation, display the sub-agent to be recommended. For example, the prompt message may be that the navigation bar is displayed in a first color, such as a color.

[0193] The third type is the sub-agent call-out event, which is an event where the user inputs an action to call out the agent.

[0194] Optionally, the sub-agent invocation operation can be an operation targeting a second preset component, a second preset gesture operation, etc. The second preset component can be the same component or a different component from the first preset component in Embodiment 1 above. The second preset gesture operation can be the same type of gesture operation (e.g., both are circle drawing operations) or a different type of gesture operation from the first preset gesture operation in Embodiment 1 above.

[0195] I. Taking the invocation of a sub-agent as an example of an operation targeting the second preset component. Assume the second preset component is a virtual button, which is optional. The second preset component can be displayed on any interface of the electronic device, such as the desktop, the negative one screen, the application interface, etc.

[0196] (1) Taking the second preset component as an example, where the component is located within the application interface. For example, the electronic device displays the first interface of the first application, which includes the second preset component. The electronic device receives an operation on the second preset component and recommends Q sub-agents to the user.

[0197] As an example, the Q sub-agents include one or more sub-agents contained in the first agent of the first application.

[0198] As another example, the Q sub-agents include sub-agents of other applications that allow the first application to call, such as one or more sub-agents contained in the second agent of the second application.

[0199] (2) Taking the second preset component as an example, where the component is located on the desktop. For instance, when an electronic device receives an operation on the second preset component on the desktop, it recommends Q sub-agents to the user. In this case, the Q sub-agents include at least one of the following: sub-agents with a usage frequency higher than a preset frequency, recently used sub-agents, default sub-agents, and user-specified sub-agents. Optionally, the display position of the second preset component on the desktop is not limited.

[0200] II. Taking the agent invocation operation as a second preset gesture operation as an example. After detecting the second preset gesture operation, the electronic device recommends Q sub-agents to the user. Optionally, the sub-agents invoked through the second preset gesture operation are different when the electronic device displays different interfaces. Taking the electronic device displaying the desktop as an example, the sub-agents invoked through the second preset gesture operation may include at least one of the following: sub-agents with a usage frequency higher than a preset frequency, recently used sub-agents, default sub-agents, and user-specified sub-agents. Taking the electronic device displaying the first interface of the first application as an example, the sub-agents invoked through the second preset gesture operation may include: sub-agents that are associated with the first application and / or the first interface. This part has been described in detail above and will not be repeated.

[0201] The above embodiments illustrate the process by which an electronic device, upon receiving an operation or a second preset gesture operation on a second preset component, recommends a sub-agent to the user. Optionally, recommending a sub-agent to the user may include method A and / or method B. Method A involves displaying the identifier of the sub-agent. Method B involves pulling up the panel of the first agent in the first application and displaying the identifier of the sub-agent within that panel. For details regarding methods A and B, please refer to the preceding description; they will not be repeated here.

[0202] The fourth type is the sub-agent wake-up event, which is the wake-up event of the system assistant.

[0203] After receiving a wake-up event from the system assistant (e.g., when the user issues the voice command "Xiaoyi Xiaoyi"), the electronic device wakes up the system assistant, for example, by displaying the system assistant's panel and recommending Q sub-intelligent agents to the user within the panel.

[0204] In one possible implementation, the Q sub-agents include agents associated with the currently running application and / or the currently displayed interface of the electronic device. For example, when the electronic device displays the first interface of the first application and receives a wake-up event from the system assistant, it recommends sub-agents associated with the first application and / or the first interface within the system assistant's panel. As an example, the Q sub-agents include one or more sub-agents contained in the first agent of the first application. As another example, the Q sub-agents include sub-agents that allow (or authorize) the first application to call other applications, such as one or more sub-agents contained in the second agent of a second application, which is different from the first application.

[0205] In another possible implementation, the Q sub-agents may include at least one of the following: sub-agents with a usage frequency higher than a preset frequency, recently used sub-agents, default sub-agents, and user-specified sub-agents.

[0206] In this approach, the electronic device can recommend Q sub-agents within the system assistant's panel, for example, by displaying the identifiers of the Q sub-agents within the system assistant's panel. See, for example, [link to relevant documentation]. Figure 11 In (a), the electronic device displays the first interface of the first application. The electronic device receives the wake-up command from "Xiaoyi Xiaoyi" and wakes up the system assistant, for example, displaying... Figure 11 The system assistant panel shown in (b) includes identifiers for multiple sub-agents, such as identifiers for clothing suggestion sub-agents, travel suggestion sub-agents, and exercise suggestion sub-agents. The travel suggestion can be a sub-agent included in the Didi Assistant of the Didi app, and the exercise suggestion can be a sub-agent included in the exercise assistant of the sports and health app.

[0207] Understandably, after waking up the system assistant, the user can input commands within the system assistant's panel, such as through voice input. In this case, the electronic device detects the user's input command within the system assistant's panel and recommends sub-agents to the user based on that command. For example, if the user inputs the command "What clothes should I wear today?" within the system assistant's panel, then based on the user's command, the device will recommend the identifier of the sub-agent for clothing suggestions.

[0208] As explained above, the differences between Embodiment 1 and Embodiment 2 are as follows. Optionally, the technical solutions of Embodiment 1 and Embodiment 2 can be used individually or in combination. Taking combined use as an example, if an electronic device detects an agent activation event, it can use the technical solution of Embodiment 1 to recommend agents, or it can use the technical solution of Embodiment 2 to recommend sub-agents. For example, the electronic device recommends N agents and Q sub-agents to the user.

[0209] Example 3

[0210] The preceding Examples 1 and 2 illustrate the process of an electronic device recommending intelligent agents / sub-intelligent agents. This Example 3 illustrates the interaction process between different intelligent agents, where each intelligent agent corresponds to a different application.

[0211] In the embodiments of this application, the interaction between different intelligent agents may include at least one of the following: switching, invocation, and collaboration between different intelligent agents. These will be described in detail below.

[0212] I. Switching between different intelligent agents

[0213] For example, if an electronic device detects a first trigger event, which is an agent switching event, then it triggers an agent switch. Exemplarily, the agent switching event indicates a switch from a first agent to a second agent; therefore, the switch proceeds. Optionally, the switch from the first agent to the second agent may include: the panel of the first agent being replaced by the panel of the second agent.

[0214] In this embodiment of the application, the switching of intelligent agents can be manual or automatic.

[0215] Taking manual switching as an example, in one possible implementation, the electronic device provides an agent switching button. Upon receiving an operation on the agent switching button, the agent is switched. Optionally, the agent switching button can be located within any interface of the electronic device. As an example, the agent switching button is located in the agent's panel; exemplaryly, each agent's panel can include an agent switching button. For example, please refer to... Figure 12A (a) The electronic device displays a weather assistant panel, which includes a button 1200. After receiving an operation on the button 1200, the electronic device displays the following: Figure 12A (b) shows the options for multiple smart agents. After receiving an operation on the Didi Assistant option, the electronic device switches to, as shown in the example. Figure 12A (c) shows the Didi Assistant panel.

[0216] Taking automatic switching as an example, in one possible implementation, when the electronic device displays the panel of the first intelligent agent, if it detects that a user has entered a user command within the panel of the first intelligent agent, and determines that the user command is directed to the second intelligent agent, then the first intelligent agent switches to the second intelligent agent. In other words, if the user enters a user command directed to the second intelligent agent within the panel of the first intelligent agent, it triggers the first intelligent agent to switch to the second intelligent agent. As an example, if the user enters (e.g., voice input) commands such as "Help me open intelligent agent B" or "Help me ask intelligent agent B" within the panel of intelligent agent A, indicating that the command is directed to intelligent agent B, then intelligent agent A switches to intelligent agent B.

[0217] For example, such as Figure 12B (a) The electronic device displays Xiaoyi's panel. At this time, the user issues a user command, "Ask the weather assistant if today is a good day for skiing." After detecting the user command, Xiaoyi determines that the user command is directed to the weather assistant, so Xiaoyi switches to the weather assistant. Optional, such as... Figure 12B (a) Before switching to the weather assistant, Xiaoyi can output the response "Okay, switching to the weather assistant." After switching to the weather assistant, the electronic device can display as follows: Figure 12B (b) shows the weather assistant panel, which includes user commands and the weather assistant's response to the command, "Today's weather is suitable for skiing."

[0218] As mentioned above, when an electronic device detects a user command entered into the first agent's panel and determines that the command is directed to the second agent, the first agent switches to the second agent. In practical applications, a situation may arise where the electronic device detects a user command entered into the first agent's panel, but this command could be directed to either the second or a third agent. For example, the user command might be "Please help me navigate," which could be handled by either Baidu Assistant or Gaode Assistant. In this case, the electronic device can randomly select an agent, or choose one that the user frequently uses, has recently used, or has specified; alternatively, it can select based on the currently running application.

[0219] For example, see Figure 12C(a) The electronic device displays the system assistant's panel. The system assistant receives a user command to "navigate to the train station". The system assistant determines that the user command can be handled by either Baidu Assistant or Gaode Assistant. The system assistant can then determine which application is currently running (e.g., the foreground application). If it is Baidu Maps, it uses Baidu Assistant; if it is Gaode Maps, it uses Gaode Assistant. Assuming the currently running application is Gaode Maps, the system assistant can switch to Gaode Assistant. Optionally, before switching, the system assistant can display the response "Switching you to Gaode Assistant". After switching, the electronic device displays as follows: Figure 12C (b) shows the Gaode Assistant panel, which includes user commands issued by the user and the response to the user commands: "Plan routes for you, including routes 1 and 2".

[0220] As mentioned above, when an electronic device detects a user command for a second intelligent agent within the panel of a first intelligent agent, the first intelligent agent switches to the second intelligent agent. In one specific implementation, the first intelligent agent can send the user command to the second intelligent agent, causing the second intelligent agent to process the user command and display the processing result on its panel.

[0221] II. Calling between different intelligent agents

[0222] For example, if an electronic device detects a first trigger event, which is an agent invocation event, and the agent invocation event is used to instruct a first agent to invoke a second agent to process instructions, then the first agent will invoke the second agent to process instructions.

[0223] As an example, an agent invoking an event could include: inputting a user command within the interface of a first agent that needs to be processed by a second agent. For instance, a user inputs (e.g., voice input) "Help me XXX" in the panel of agent A. This user command is directed to agent A, but the event "XXX" in this command needs to be processed by agent B. Agent A can then invoke agent B to process the "XXX" event. After agent A invokes agent B to process the "XXX" event, the processing result of agent B for the "XXX" event can be displayed in the panel of agent A.

[0224] For example, see Figure 13A (a) The electronic device displays the Air China Assistant panel. The user enters the command "What will the weather be like in Chengdu tomorrow?" into the Air China Assistant panel. The Air China Assistant determines that the user command needs to be processed by the Weather Assistant, then invokes the Weather Assistant to query the weather and displays the query results in the Air China Assistant panel, such as... Figure 13A(b) Optionally, the Air China Assistant panel may also display a Weather Assistant icon to indicate that the weather query results were obtained by calling the Weather Assistant. If an electronic device receives an action targeting the Weather Assistant icon, it can switch from Air China Assistant to the Weather Assistant.

[0225] For example, such as Figure 13B (a) The electronic device displays the system assistant's panel. The system assistant receives the user's command, "Is today suitable for skiing?". The system assistant determines that this user command requires the weather assistant to execute, so it invokes the weather assistant for processing and displays the processing result in the system assistant's panel, such as... Figure 13B (b) The system assistant panel displays "Today's weather is suitable for skiing." Optionally, the system assistant panel may also display a weather assistant icon to indicate that the processing result was obtained by calling the weather assistant. If the electronic device receives an operation targeting the weather assistant icon, the system assistant switches to the weather assistant, for example, displaying... Figure 13B (c) shows the weather assistant panel.

[0226] As mentioned above, when a user command is input into the interface of the first intelligent agent, but this command needs to be processed by the second intelligent agent, the first intelligent agent invokes the second intelligent agent to process the user command. As a specific implementation, the first intelligent agent can send the user command to the second intelligent agent, causing the second intelligent agent to process the command and return the processing result to the first intelligent agent. Therefore, the first intelligent agent can display the processing result within its own panel.

[0227] III. Collaboration among different intelligent agents

[0228] For example, if an electronic device detects a first trigger event, which is an agent collaboration event, and the agent collaboration event is used to instruct a first agent and a second agent to collaborate on instruction processing, then the first agent and the second agent will collaborate on instruction processing.

[0229] As an example, an agent collaboration event can include: an event where a user command is input within the interface of a first agent that requires collaborative processing by both the first and second agents. For instance, a user inputs (e.g., voice input) the command "Help me XXX" into the panel of agent A. Part of this command needs to be processed by agent A, and another part by agent B. In this case, agent A and agent B collaboratively process the command. After the collaborative processing by agents A and B is complete, the result can be displayed in the panel of agent A.

[0230] For example, see Figure 14A(a) The electronic device displays the weather assistant's panel. The weather assistant detects the user's instruction, "Check the weather in Shanghai tomorrow and arrange a business trip to Shanghai tomorrow." The weather assistant parses the instruction and determines that it consists of two parts: the first part, "Check the weather in Shanghai tomorrow," and the second part, "Arrange a business trip to Shanghai tomorrow." The first part is handled by the weather assistant, and the second part by the Air China assistant. Therefore, this user instruction requires collaborative processing by two intelligent agents (e.g., the weather assistant and the Air China assistant). Thus, the weather assistant can process the first part independently and call the Air China assistant to process the second part, displaying the collaborative processing result on the weather assistant's panel—that is, the weather assistant's processing result for the first part and the Air China assistant's processing result for the second part, as shown below. Figure 14A (b). Optionally, the Air China Assistant logo can also be displayed in the Weather Assistant panel.

[0231] In the above embodiment, the electronic device detects that a user inputs a user command within the interface of the first intelligent agent that requires collaborative processing by the first and second intelligent agents. Then, the first and second intelligent agents collaboratively process the command. As a specific implementation, the first intelligent agent can send the part that needs to be processed by the second intelligent agent to the second intelligent agent and receive the processing result of the second intelligent agent on that part, so that the first intelligent agent displays the collaborative processing result on its own panel.

[0232] As another example, agent collaboration events can include events where a user command is input into the system assistant's panel, requiring collaborative processing by a first agent and a second agent. For instance, if a user inputs (e.g., voice input) the command "Help me XXX" into the system assistant's panel, and part of this command requires processing by agent A and another part by agent B, the system assistant can invoke agents A and B to collaboratively process the command. After the collaborative processing is complete, the result is displayed in the system assistant's panel.

[0233] For example, see Figure 14B(a) The electronic device displays the system assistant's panel. The system assistant detects a user's instruction: "Check the weather in Shanghai tomorrow and arrange a business trip to Shanghai tomorrow." The system assistant parses the instruction and determines that it consists of two parts: the first part, "Check the weather in Shanghai tomorrow," and the second part, "Arrange a business trip to Shanghai tomorrow." The first part is handled by the weather assistant, and the second part by the Air China assistant. Therefore, this user instruction requires collaborative processing by two agents (e.g., the weather assistant and the Air China assistant). Thus, the system assistant can invoke the weather assistant to process the first part and the Air China assistant to process the second part, displaying the collaborative processing results on the system assistant's panel—that is, the weather assistant's processing result for the first part and the Air China assistant's processing result for the second part, as shown below. Figure 14B (b). Optionally, the system assistant panel may also display the weather assistant logo and / or the Air China assistant logo.

[0234] In the above embodiment, the electronic device detects that the user has entered a user command within the system assistant's interface that requires collaborative processing by a first intelligent agent and a second intelligent agent. The system assistant then invokes both agents to collaboratively process the command. As a specific implementation, the system assistant can send the portion requiring processing by the first intelligent agent and receive the processing result from the first intelligent agent for that portion. Furthermore, it can also send the portion requiring processing by the second intelligent agent and receive the processing result from the second intelligent agent for that portion, allowing the system assistant to display the collaborative processing result on the panel.

[0235] Optionally, in this embodiment of the application, the user can also view the interaction content between the user and each intelligent agent. For example, please refer to... Figure 14C (a) The electronic device displays the interface of a weather application and also displays a weather assistant panel, which includes the user's command "Is the weather suitable for skiing today?" and the weather assistant's response. Upon receiving an operation to display the panel in full-screen mode, the electronic device displays as follows: Figure 14C The interface shown in (b) displays the weather assistant panel in full screen, and also shows buttons 1400 and 1401. When the electronic device receives an operation on button 1400, it closes the weather assistant panel and returns to the weather application interface, as shown in [example interface]. Figure 14C (c) When the electronic device receives an operation on button 1401, it displays as follows: Figure 14C (d) shows a dialogue list that includes interactions between various agents and the user. For example, if an electronic device receives an action to select a weather assistant, it displays something like... Figure 14C The interface shown in (b) is thus accessible to the user. Figure 14C (d) shows the dialog list, which quickly opens the panel for each agent.

[0236] The above embodiment three is used to illustrate the interaction between different intelligent agents. Optionally, different sub-intelligent agents can also interact, and the interaction principle is the same as that between different intelligent agents, so it will not be repeated.

[0237] Example 4

[0238] The preceding embodiment three illustrates the interaction process between different intelligent agents. This embodiment four illustrates the interaction process between an intelligent agent and an application. Taking intelligent agent A of application A as an example, the interaction between intelligent agent A and the application can include: intelligent agent A interacting with application A, and / or, intelligent agent A interacting with application B, where application B is different from application A. As one possible implementation, the interaction between intelligent agent A and the application can include: an electronic device providing an interface through which intelligent agent A interacts with the application, where the application can be application A of intelligent agent A, or other applications, such as application B.

[0239] In one possible implementation, the interaction between the agent and the application may include: the agent controlling the application, such as performing at least one of the following processes: page turning, context summarizing, copying, and translating.

[0240] As mentioned above, agent A can interact with both application A and application B. As one possible implementation, if agent A is configured to interact only with application A and not with other applications, then agent A cannot interact with application B. As another possible implementation, if agent A is configured to interact with both application A and application B, then agent A can interact with application B. For example, the electronic device determines which applications agent A can interact with based on agent A and the first correspondence mentioned above. For details on the first correspondence, please refer to Embodiment 1, which will not be repeated here.

[0241] For example, see Figure 15A The electronic device displays a browser application interface containing an article and a browser assistant panel. The user enters a command to "summarize this article" in this panel. After detecting this command, the browser assistant summarizes the context of the current foreground application interface and displays the summary result in its panel. It should be noted that... Figure 15A In this context, the foreground application of the electronic device is a browser application, and the intelligent agent is an intelligent agent within the browser application. In other words, the application is controlled through its own intelligent agent.

[0242] For example, please see Figure 15BThe electronic device displays the interface of an instant messaging application, which includes chat content and a browser assistant panel. The user enters a "summary" command in this panel. After detecting the command, the browser assistant summarizes the context of the chat content and displays the summary in its panel. Therefore, Figure 15B In this context, the foreground application of an electronic device is an instant messaging application, and the intelligent agent is the intelligent agent of the browser application. In other words, one application controls another application through its intelligent agent assistant.

[0243] For ease of understanding, the following text will continue to use... Figure 15A or Figure 15B Using this as an example, we can illustrate the control principle of an intelligent agent over an application.

[0244] For example, see Figure 15C This is a flowchart illustrating an interaction method provided in Embodiment 4. This method can be applied to the interaction between an intelligent agent and a first application, wherein the intelligent agent can be an intelligent agent of the first application or an intelligent agent of the second application, without limitation. Figure 15C The process may include: Step 1500: The agent receives user instructions.

[0245] For example, Figure 15A or Figure 15B In the process, the browser assistant receives user commands.

[0246] Step 1501: The agent determines whether the user command is context-dependent. If so, proceed to step 1502; otherwise, it can perform intent recognition on the user command and proceed to step 1505. For example, if the user command is to query the weather, the weather assistant will be invoked to provide the user with the query results.

[0247] Step 1502: The agent determines whether the first application is running in the foreground. If so, proceed to step 1503; otherwise, proceed to the result flow.

[0248] It should be noted that step 1502 may or may not be executed; there is no limitation on this, so step 1502 is represented by a dashed line in the diagram. Taking the execution of step 1502 as an example, one possible scenario is that the agent is configured to interact only with the application corresponding to that agent; in other words, Figure 15C The agent in the code is the agent of the first application. In this case, after detecting a user command related to the context, the agent determines whether the application corresponding to it (i.e., the first application) is running in the foreground. If so, it obtains the context of the first application; otherwise, the process ends. Taking step 1503 not being executed as an example, one possible scenario is... Figure 15CThe agent in the second application is configured to interact with other applications. Therefore, when the agent receives a user instruction related to the context, it does not need to determine which application is the foreground application, that is, it does not need to execute step 1502, and can directly execute step 1503.

[0249] Step 1503: The agent obtains the context of the first application through the interface.

[0250] Optionally, the agent can send a context query request to the foreground application (i.e., the first application) through the interface. After receiving the query request, the first application returns the context to the agent through the interface.

[0251] Step 1504: The agent processes the context.

[0252] For example, an agent can summarize the context and generate a summary result.

[0253] Step 1505: The agent outputs a response.

[0254] In another possible implementation, the interaction between the agent and the application may include: the agent controlling the application, such as controlling at least one of the following: switching, playing, pausing, fast forwarding, and rewinding the application's multimedia.

[0255] For example, see Figure 16A (a) The electronic device displays the interface of the Huawei Video application, which includes the currently playing multimedia 1 and also displays the video assistant panel. The video assistant detects that the user has entered the command "Play XX program" in the panel, and then switches the currently playing multimedia 1 in the Huawei Video application to the program "XX". For another example, please see... Figure 16A (b) If the video assistant detects that the user has entered the command "play at 30 minutes" in the panel, it will fast forward the currently playing program "XX" in the Huawei Video application to 30 minutes. Figure 16A (c). It should be noted that, Figure 16A In the example of controlling the Huawei Video application with a video assistant, the video assistant may or may not be an intelligent agent of the Huawei Video application, without limitation.

[0256] For ease of understanding, the following text will continue to use... Figure 16A Using this as an example, we can illustrate the control principle of an intelligent agent over an application.

[0257] For example, see Figure 16B This is a flowchart illustrating an interaction method provided in Embodiment 4. This method can be applied to the interaction between an intelligent agent and a first application, wherein the intelligent agent can be an intelligent agent of the first application or an intelligent agent of the second application, without limitation. Figure 16B The process may include: Step 1600: The agent receives user instructions.

[0258] For example, Figure 16A In the middle, the video assistant receives the user's command.

[0259] Step 1601: The agent determines whether the user command is related to multimedia control. If so, step 1602 is executed. Otherwise, the agent can perform intent recognition on the user command and execute step 1605.

[0260] Step 1602: The agent determines whether the first application is running in the foreground. If so, proceed to step 1603; otherwise, proceed to the result flow.

[0261] It should be noted that step 1602 can be performed or not; there is no restriction. Figure 16B This step is indicated by a dashed line. Taking step 1602 as an example, one possible scenario is that the agent is configured to interact only with the application corresponding to that agent; in other words, Figure 16B The agent in this context is the agent of the first application. In this case, after detecting a user command related to multimedia control, the agent determines whether the application corresponding to it (i.e., the first application) is running in the foreground. If so, it executes subsequent steps; otherwise, the process ends. Taking step 1603 not being executed as an example, one possible scenario is... Figure 16B The agent in the second application is configured to interact with other applications. Therefore, after receiving user instructions related to multimedia control, the agent does not need to determine which application is the foreground application, i.e., it does not need to execute step 1602, and can directly execute step 1603.

[0262] Step 1603: The intelligent agent obtains the current page position of the first application through the interface.

[0263] Optionally, the current page position may include the currently playing multimedia in the first application, the playback progress of the currently playing multimedia, etc.

[0264] Step 1604: The intelligent agent controls the multimedia.

[0265] For example, suppose the current page position of the first application includes: currently playing multimedia 1, and playing up to the 60th minute of multimedia 1. If the agent detects a user instruction to play at the 30th minute, then the agent, based on the current page position, controls the first application to fast-forward to the 30th minute.

[0266] Step 1605: The agent outputs a response.

[0267] The above embodiments illustrate the process of an intelligent agent controlling an application. In other embodiments, the intelligent agent can also control electronic devices, such as querying the functions of the electronic device, setting the scene mode of the electronic device, etc.

[0268] For example, to query the functions of an electronic device through an intelligent agent, please see [link to relevant documentation]. Figure 16C (a) The electronic device displays the interface of the settings application, which includes a first preset component (see the description in Embodiment 1 above). Upon receiving an operation on the first preset component, the electronic device displays the panel of the settings assistant (or an intelligent agent of another application), such as... Figure 16C (b). For example Figure 16C (b) After the settings assistant detects the user command "Find the air screenshot function", it displays as follows: Figure 16C The interface shown in (c) is the interface corresponding to the air screenshot function.

[0269] For example, to set the scene mode of an electronic device through an intelligent agent, please refer to [link to relevant documentation]. Figure 16D (a) The electronic device displays a scene mode settings interface, which includes one or more scene modes. Upon receiving an operation on a first preset component, the electronic device displays a panel of a settings assistant (or an intelligent agent of another application), such as... Figure 16D (b). For example Figure 16D (b) The settings assistant detects the user command "Automatically turn on silent mode after 8 pm every night, and automatically reply to messages, and return to normal at 7 am". Therefore, the settings assistant can set a scenario mode based on this user command, which is a mode in which the electronic device automatically turns on silent mode after 8 pm every night, automatically replies to messages, and returns to normal at 7 am.

[0270] In the above embodiment, taking the floating panel display of the intelligent agent as an example, other display methods are also possible. For example, please refer to... Figure 17 In (a), the tablet displays the Xiaohongshu interface, which is playing a travel guide video. After activating the agent (which can be the Xiaohongshu agent or an agent from other applications, without limitation), the following is displayed: Figure 17 The split-screen mode shown in (b) displays the Xiaohongshu interface and the smart agent's panel in a split-screen format. Optionally, when the smart agent detects a user's command to "view text version of the guide" in the panel, it can display the text version of the guide corresponding to the currently playing video, such as the itinerary for day one, day two, etc. Optionally, the panel can include touch-sensitive words, such as "Beijing Store A". After receiving the operation of this word, the electronic device can search for content related to this word in Xiaohongshu. For example, the electronic device displays something like... Figure 17 The interface shown in (c) is shown in the image.

[0271] In this embodiment, the smart agent's panel can be displayed independently of the corresponding application window. For example, please refer to... Figure 18 In (a), the electronic device displays the browser application interface and a browser assistant panel. Upon receiving an operation to access the multitasking interface, the electronic device displays, as shown below. Figure 18 In the interface shown in (b), the browser assistant panel floats above the multitasking interface. Assuming... Figure 18 In (b) of the above, if the electronic device receives an operation to open the interface of another application from the multitasking interface, the interface of the other application is displayed in the foreground, and the browser assistant interface is still displayed floating on the top layer of the application's interface.

[0272] Figure 19 This is a schematic diagram of the structure of the electronic device 1900 provided in an embodiment of this application. The electronic device 1900 can be one of the electronic devices described above, such as a mobile phone. Figure 19 As shown, electronic device 1900 may include: one or more processors 1901; one or more memories 1902; a communication interface 1903; and one or more computer programs 1904. These devices can be connected via one or more communication buses 1905. The one or more computer programs 1904 are stored in the memory 1902 and configured to be executed by the one or more processors 1901. The one or more computer programs 1904 include instructions. For example, when electronic device 1900 is the electronic device described above, these instructions can be used to perform relevant steps of the electronic device as described in the corresponding embodiments above. The communication interface 1903 is used to enable communication between electronic device 1900 and other devices; for example, the communication interface may be a transceiver.

[0273] Based on the above, this application also provides a computer-readable storage medium storing instructions that, when executed, cause the method provided in any of the above-described method embodiments to be implemented. The computer-readable storage medium may include various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory, random access memory, magnetic disk, or optical disk.

[0274] Based on the above, this application also provides a computer program product, which includes: a computer program (also referred to as code or instructions), which, when run on a computer, causes the computer to perform the method provided in any of the above method embodiments. Optionally, the computer can be a terminal device, such as a tablet computer.

[0275] The methods provided in the embodiments of this application above are described from the perspective of an electronic device (e.g., a mobile phone or tablet computer) as the executing entity. To implement the functions of the methods provided in the embodiments of this application above, the electronic device may include hardware structures and / or software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0276] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)). Where there is no conflict, the solutions in the above embodiments can be used in combination.

[0277] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0278] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0279] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0280] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0281] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope and intent of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and variations.

Claims

1. An agent running method, characterized by, Applied to electronic devices, the method includes: Run the first application; During the display of the first application's display interface, the first interface of the first intelligent agent of the second application is displayed, and the second application is different from the first application; In response to a user command input on the first interface, the second intelligent agent is executed; When the user instruction is a user instruction directed at the second intelligent agent, the first interface is switched to the second interface of the second intelligent agent; and If the user instruction is not a user instruction directed at the second agent and the first agent determines that the user instruction is to be processed by the second agent, the first interface is not switched to the second interface of the second agent, and the processing result of the second agent is displayed on the first interface.

2. A method for operating an intelligent agent, characterized in that, Applied to electronic devices, the method includes: Run the first application; During the display of the first application's display interface, the first interface of the first intelligent agent of the second application is displayed, and the second application is different from the first application; In response to a user command input on the first interface, the second intelligent agent is executed; If the user instruction is directed to the second intelligent agent, or if the user instruction is not directed to the second intelligent agent, and the first intelligent agent determines that the user instruction is processed by the second intelligent agent, and the second intelligent agent is the intelligent agent of the first application, the first interface is switched to the second interface of the second intelligent agent; or If the user instruction is not a user instruction directed at the second agent and the first agent determines that the user instruction is to be processed by the second agent, the first interface is not switched to the second interface of the second agent, and the processing result of the second agent is displayed on the first interface.

3. The method according to claim 1 or 2, characterized in that, After the first interface is not switched to the second interface of the second agent, and the processing result of the second agent is displayed on the first interface, the method further includes: In response to the first operation, the first interface is switched to the second interface of the second agent, and the second interface includes the context information of the first interface. The first operation is a selection operation on the first control on the first interface, and the first control is used to instruct the second agent.

4. The method according to any one of claims 2-3, characterized in that, If the user instruction is not directed to the second agent and the first agent determines that the user instruction is to be processed collaboratively by the second agent and the third agent, the first interface will not be switched to the second interface of the second agent, and the collaborative processing result of the second agent and the third agent will be displayed on the first interface. The third agent and the second agent correspond to different applications.

5. The method according to any one of claims 1-4, characterized in that, The step of displaying the first interface of the first intelligent agent of the second application during the display process of the first application's display interface includes: A second control is provided in the display interface of the first application; The system receives operations on the second control and displays the first interface of the first agent of the second application during the display process of the first application's display interface.

6. The method according to any one of claims 1-4, characterized in that, The step of displaying the first interface of the first intelligent agent of the second application during the display process of the first application's display interface includes: The first application's display interface provides an entry point for user interaction with the system assistant; In response to the instruction input by the user at the interaction entry point, during the display process of the first application's display interface, the first interface of the first intelligent agent of the second application is displayed.

7. The method according to any one of claims 1-6, characterized in that, Before displaying the first interface of the first agent of the second application, the method further includes: Output a first prompt message, which is used to indicate that there is an agent to be recommended.

8. The method according to claim 7, characterized in that, The output of the first prompt information includes: Set the navigation bar color to the first color.

9. The method according to any one of claims 1-8, characterized in that, The first intelligent agent satisfies at least one of the following: The first intelligent agent is related to the current display interface of the first application; or, The first intelligent agent is an intelligent agent authorized for use by the first application; or, The first agent is an agent that has been used recently; or, The first intelligent agent is an intelligent agent whose usage frequency is higher than a preset frequency.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: When the first interface is switched to the second interface of the second intelligent agent, in response to the user's second operation on the second interface, the first application is triggered to perform a third operation; and Without switching the first interface to the second interface of the second agent, and while displaying the processing result of the second agent on the first interface, the first application is triggered to perform a third operation in response to the user's second operation on the first interface.

11. The method according to claim 10, characterized in that, The third operation is used to update the display interface of the first application.

12. The method according to claim 10, characterized in that, The third operation is used to configure the electronic device.

13. The method according to any one of claims 1-12, characterized in that, The first interface and the display interface of the first application are displayed in a split-screen format.

14. The method according to any one of claims 1-13, characterized in that, The method further includes: During the display of the first interface of the first intelligent agent, in response to the multitasking interface opening operation, the size of the first interface is not scaled, and the first interface floats on the upper layer of the multitasking interface. During the display of the second interface of the second agent, in response to the multitasking interface opening operation, the size of the second interface is not scaled, and the second interface floats on top of the multitasking interface.

15. An electronic device, characterized in that, Used to perform the method as described in any one of claims 1-14.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 14.

17. A computer program product, characterized in that, Includes a computer program that, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 14.

Images