Information display method and device and electronic equipment

Abstract

The invention discloses an information display method and device and electronic equipment, and belongs to the technical field of artificial intelligence. The information display method comprises the following steps: receiving first information input by a user on a first interface; displaying second information corresponding to the first information on the first interface; wherein the second information is task execution feedback information obtained when the AI assistant executes the first task based on the first information.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, specifically relating to an information display method, device, and electronic device. Background Technology

[0002] With the rapid development of artificial intelligence (AI) technology, users' demand for AI services is growing. For example, users hope to receive AI assistance in scenarios such as chatting, searching, filling out forms, cross-language communication, and scheduling using electronic devices.

[0003] In related technologies, if a user needs to use AI services to answer questions about content on the current screen, they need to copy the page information, exit the current page, open the AI ​​application, and then enter the copied page information into the AI ​​application interface to ask a question before the AI ​​application can respond. This process is quite cumbersome. For example, if a user wants to use AI services to answer a message sent by a friend while chatting on a social application, they need to access an AI application that provides AI services, copy the context of the chat to the AI ​​application interface to ask a question, obtain an answer, and then copy the answer from the AI ​​application interface to the social application to send it to their friend. Summary of the Invention

[0004] The purpose of this application is to provide an information display method, apparatus, and electronic device that can improve the convenience of electronic devices in performing tasks.

[0005] In a first aspect, embodiments of this application provide an information display method, which includes: receiving first information input by a user on a first interface; and displaying second information corresponding to the first information on the first interface; wherein the second information is task execution feedback information obtained by an artificial intelligence AI assistant performing a first task based on the first information.

[0006] In this solution, since the electronic device can automatically control the AI ​​assistant to execute the first task corresponding to the first information based on the first information input by the user, and display the task execution feedback information obtained from executing the first task on the first interface, the electronic device does not need to manually switch between different applications when it needs to execute the first task through different applications. This improves the convenience of the electronic device when executing the first task through different applications.

[0007] In some embodiments of this application, the first interface is any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

[0008] In this way, electronic devices can automatically execute the first task corresponding to the first information by controlling AI in an interface without AI functionality, without the need for users to manually switch between different applications in the electronic device, thus improving the convenience of electronic devices executing the first task through different applications.

[0009] In some embodiments of this application, the second information includes at least one of the following: reply information for responding to the first information; travel planning information corresponding to the first information; service evaluation information corresponding to the first information; prompt information for indicating that the first task has been executed; task information corresponding to the first task; and warning information corresponding to the first information.

[0010] In this way, since the electronic device can automatically control the AI ​​assistant to execute the first task corresponding to the first information based on the first information input by the user, and display the task execution feedback information obtained from executing the first task on the first interface, the user does not need to manually switch between different applications when the electronic device needs to execute the first task through different applications. This improves the convenience of the electronic device when executing the first task through different applications.

[0011] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a first conversation message from a first contact; the first information is information entered by the user on the input method keyboard, and the first information is a question message about at least part of the message content in the first conversation message; wherein, the question message is a complete question description, or the question message is at least part of the question keywords in the complete question description; displaying second information corresponding to the first information includes: displaying reply information, the reply information being used to reply to the question message.

[0012] In this way, users do not need to exit the conversation interface and open an AI question-and-answer program to get answers to questions. They can simply enter "What is a large language model?" in the input box of the conversation interface and wait for the electronic device to automatically perform the above task, reducing the number of user operation steps and the time to obtain reply information.

[0013] In some embodiments of this application, when the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is task instruction information that instructs the generation of travel planning information for the travel destination; displaying the second information corresponding to the first information includes: displaying the travel planning information for the travel destination; wherein, the travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

[0014] In this way, when the travel planning interface is displayed, the electronic device can automatically call the AI ​​assistant to execute the first task corresponding to the first information entered by the user, and display the travel planning information obtained from executing the first task in the travel planning interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing travel planning.

[0015] In some embodiments of this application, when the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; the first information is the information entered by the user in the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; the second information corresponding to the first information is displayed, including: displaying the store evaluation information of the first store.

[0016] In this way, when the service evaluation interface is displayed, the electronic device can automatically call the AI ​​assistant to automatically execute the first task corresponding to the first information entered by the user, and display the store evaluation information obtained from executing the first task in the service evaluation interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing store evaluations.

[0017] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of a to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion; the first information is information entered by the user on the input method keyboard, and the first information indicates task instruction information for setting a first schedule reminder based on the second conversation message; displaying second information corresponding to the first information includes: displaying a first prompt message and a first schedule reminder identifier; wherein, the first schedule reminder identifier is used to indicate a first schedule reminder; the first prompt message is used to indicate that the first schedule reminder corresponding to the description of the to-do item has been set.

[0018] In this way, when the instant messaging interface is displayed, the electronic device can automatically call the AI ​​assistant to execute the first task corresponding to the first information entered by the user, and display the first prompt information and the first schedule reminder icon obtained from executing the first task in the instant messaging interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing schedule reminders.

[0019] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation message includes an instruction message requiring the user to send authentication credential information; the first message is the information entered by the user on the input method keyboard, and the first message includes authentication credential information; displaying second message corresponding to the first message includes: displaying a first warning message, which is used to warn the user to avoid sending authentication credential information.

[0020] In this way, when the instant messaging interface is displayed, the electronic device can automatically call the AI ​​assistant to execute the first task corresponding to the first information entered by the user, and display the first warning information obtained from executing the first task in the instant messaging interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the security of the electronic device when sending SMS verification codes.

[0021] In some embodiments of this application, before displaying the second information corresponding to the first information on the first interface, the method further includes: determining that an AI capability call intention is identified when the first reference information includes a trigger word; the first reference information includes at least one of the following: first information; interface context information of the first interface; and outputting the second information through an AI assistant when the AI ​​capability call intention is identified; wherein the trigger word is used to trigger the AI ​​assistant to obtain the second information.

[0022] In this way, electronic devices can determine whether to call the AI ​​assistant to output the second information based on the trigger words contained in the first information, thus improving the flexibility of electronic devices in calling the AI ​​assistant.

[0023] In some embodiments of this application, the first interface includes an input method keyboard and an AI identifier; the AI ​​identifier is used to trigger an AI assistant to perform a first task based on first information and display second information; before displaying the second information corresponding to the first information on the first interface, the method further includes: receiving a user's selection input for the AI ​​identifier; displaying the second information corresponding to the first information on the first interface includes: in response to the selection input, displaying the second information corresponding to the first information on the first interface.

[0024] In this way, electronic devices can invoke AI assistants by inputting AI identifiers from users, avoiding misidentification of the first information by the electronic devices and improving the accuracy of the second information output by the electronic devices.

[0025] In some embodiments of this application, the above-mentioned output of second information through an AI assistant when it is determined that the intention to call AI capabilities has been identified includes: when it is determined that the intention to call AI capabilities has been identified based on first reference information, the first information and the interface context information of the first interface are input into the task execution model through the AI ​​assistant, and the task execution model performs context recognition processing on the first information based on the interface context information of the first interface, and outputs the second information.

[0026] In this way, the electronic device can output the second information based on the first information input by the user and the interface context information of the first interface, avoiding the semantic inaccuracy caused by semantic recognition based solely on the first information, and improving the accuracy of the second information output by the electronic device.

[0027] In some embodiments of this application, before displaying the second information corresponding to the first information on the first interface, the method further includes: when the first information is missing at least one task element of the first task, obtaining at least one candidate information based on the first information and the interface context information of the first interface through the AI ​​assistant; wherein the at least one candidate information is task element information determined based on the interface context information of the first interface; the at least one candidate information includes all task elements missing from the first information; displaying the at least one candidate information on the input method keyboard; determining target candidate information; wherein the target candidate information is the candidate information selected by the user among the at least one candidate information, or the target candidate information is the candidate information ranked at the beginning position among the at least one candidate information; when it is determined that the intention to call AI capabilities is identified, outputting the second information through the AI ​​assistant, including: when it is determined that the intention to call AI capabilities is identified based on the first reference information, inputting the first information, the interface context information of the first interface, and the target candidate information into the task execution model through the AI ​​assistant, and performing context recognition processing on the first information based on the interface context information of the first interface and the target candidate information through the task execution model, and outputting the second information.

[0028] In this way, the electronic device can output second information based on the first information input by the user, the interface context information of the first interface, and the target candidate information, thus avoiding semantic inaccuracies caused by semantic recognition based solely on the first information and improving the accuracy of the second information output by the electronic device.

[0029] In some embodiments of this application, the above-mentioned determination of target candidate information includes: when receiving input from a user to select a first candidate information among at least one candidate information, determining the first candidate information as target candidate information; and when not receiving input from a user to select candidate information, determining the second candidate information in the starting position among at least one candidate information as target candidate information.

[0030] In this way, electronic devices can determine target candidate information based on user input, or automatically determine target candidate information without user input, thus improving the flexibility of electronic devices in determining target candidate information.

[0031] In some embodiments of this application, the aforementioned interface context information includes at least one of the following: the interface content of the first interface; the application attribute information of the first application corresponding to the first interface; the geographical location information of the electronic device; and second reference information associated with the interface content of the first interface; wherein, the application attribute information includes at least one of the following: application name; application type; application function; the second reference information is information that matches the interface content of the first interface; the second reference information includes at least one of the following: image information; schedule information; and video information.

[0032] In this way, since the electronic device can automatically control the AI ​​assistant to execute the first task corresponding to the first information based on the first information input by the user, and display the task execution feedback information obtained from executing the first task on the first interface, the user does not need to manually switch between different applications when the electronic device needs to execute the first task through different applications. This improves the convenience of the electronic device when executing the first task through different applications.

[0033] Secondly, embodiments of this application provide an information display device, which includes a receiving module and a display module. The receiving module is used to receive first information input by a user on a first interface. The display module is used to display second information corresponding to the first information received by the receiving module on the first interface; wherein, the second information is task execution feedback information obtained by an artificial intelligence AI assistant performing a first task based on the first information.

[0034] In one possible implementation, the aforementioned first interface can be any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

[0035] In one possible implementation, the second information includes at least one of the following: reply information for responding to the first information; travel planning information corresponding to the first information; service evaluation information corresponding to the first information; prompt information for indicating that the first task has been executed; task information corresponding to the first task; and warning information corresponding to the first information.

[0036] In one possible implementation, when the first interface is an instant messaging interface, the instant messaging interface includes a first conversation message from a first contact; the first information is information entered by the user on the input method keyboard, and the first information is a question message about at least part of the message content in the first conversation message; wherein, the question message is a complete question description, or the question message is at least part of the question keywords in the complete question description; and the display module is specifically used to display reply information, which is used to reply to the question message.

[0037] In one possible implementation, when the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that indicates the generation of travel planning information for the travel destination; the display module is specifically used to display the travel planning information for the travel destination; wherein, the travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

[0038] In one possible implementation, when the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; the first information is the information entered by the user in the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; the display module is specifically used to display the store evaluation information of the first store.

[0039] In one possible implementation, if the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of the to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion; the first information is information entered by the user on the input method keyboard, and the first information indicates the task instruction information for setting a first schedule reminder based on the second conversation message; the display module is specifically used to display a first prompt message and a first schedule reminder identifier; wherein, the first schedule reminder identifier is used to indicate the first schedule reminder; the first prompt message is used to indicate that the first schedule reminder corresponding to the description of the to-do item has been set.

[0040] In one possible implementation, if the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation information includes an instruction message requiring the user to send authentication credential information; the first information is information entered by the user on the input method keyboard, and the first information includes authentication credential information; the display module is specifically used to display a first warning message, which is used to warn the user to avoid sending authentication credential information.

[0041] In one possible implementation, the information display device further includes a processing module. The processing module is configured to, before displaying second information corresponding to the first information on the first interface, determine, if the first reference information includes a trigger word, that an AI capability invocation intent has been identified; the first reference information includes at least one of the following: first information; interface context information of the first interface; and, upon determining that an AI capability invocation intent has been identified, output the second information through an AI assistant; wherein the trigger word is used to trigger the AI ​​assistant to obtain the second information.

[0042] In one possible implementation, the first interface includes an input method keyboard and an AI icon. The AI ​​icon triggers the AI ​​assistant to perform a first task based on the first information and display second information. The receiving module is further configured to receive user selection input for the AI ​​icon before displaying the second information corresponding to the first information on the first interface. The display module is specifically configured to, in response to the selection input received by the receiving module, display the second information corresponding to the first information on the first interface.

[0043] In one possible implementation, the aforementioned processing module is specifically used to, when determining that the intention to invoke AI capabilities is recognized based on the first reference information, input the first information and the interface context information of the first interface into the task execution model through the AI ​​assistant, and then, through the task execution model, perform context recognition processing on the first information based on the interface context information of the first interface, and output the second information.

[0044] In one possible implementation, the processing module is further configured to, before displaying the second information corresponding to the first information on the first interface, obtain at least one candidate information based on the first information and the interface context information of the first interface when the first information is missing at least one task element of the first task, through the AI ​​assistant; wherein the at least one candidate information is task element information determined based on the interface context information of the first interface; the at least one candidate information includes all task elements missing from the first information. The display module is further configured to display at least one candidate information on the input method keyboard; determine target candidate information; wherein the target candidate information is the candidate information selected by the user from the at least one candidate information, or the target candidate information is the candidate information ranked at the beginning position among the at least one candidate information. Specifically, the processing module is configured to, when determining based on the first reference information that an intention to invoke AI capabilities has been identified, input the first information, the interface context information of the first interface, and the target candidate information into the task execution model through the AI ​​assistant; and, through the task execution model, perform context recognition processing on the first information based on the interface context information of the first interface and the target candidate information, and output the second information.

[0045] In one possible implementation, the above-mentioned processing module is specifically used to determine the first candidate information as the target candidate information when receiving input from the user to select the first candidate information among at least one candidate information; and to determine the second candidate information in the starting position among at least one candidate information as the target candidate information when not receiving input from the user to select candidate information.

[0046] In one possible implementation, the aforementioned interface context information includes at least one of the following: the interface content of the first interface; the application attribute information of the first application corresponding to the first interface; the geographic location information of the electronic device; and second reference information associated with the interface content of the first interface; wherein the application attribute information includes at least one of the following: application name; application type; application function; the second reference information is information that matches the interface content of the first interface; and the second reference information includes at least one of the following: image information; schedule information; and video information.

[0047] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, wherein the memory stores a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implement the steps of the information display method as described in the first aspect.

[0048] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the information display method as described in the first aspect.

[0049] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the information display method as described in the first aspect.

[0050] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the information display method as described in the first aspect.

[0051] In this embodiment, the system receives first information input by the user on a first interface; on the first interface, it displays second information corresponding to the first information; wherein the second information is task execution feedback information obtained by the AI ​​assistant based on the first information when performing a first task. In this solution, since the electronic device can automatically control the AI ​​assistant to automatically execute the first task corresponding to the first information based on the user's input, and display the task execution feedback information obtained from executing the first task on the first interface, the user does not need to manually switch between different applications when the electronic device needs to perform the first task through different applications. This improves the convenience of the electronic device performing the first task through different applications.

[0052] Understandably, the information display device provided in the second aspect, the electronic device provided in the third aspect, the readable storage medium provided in the fourth aspect, the chip provided in the fifth aspect, and the computer program product provided in the sixth aspect are all used to execute the method provided in this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating an information display method provided in some embodiments of this application;

[0054] Figure 2A These are schematic diagrams of the session interface provided in some embodiments of this application;

[0055] Figure 2B These are schematic diagrams of the session interface provided in some embodiments of this application;

[0056] Figure 3 These are schematic diagrams of the session interface provided in some embodiments of this application;

[0057] Figure 4A These are schematic diagrams of travel planning interfaces provided in some embodiments of this application;

[0058] Figure 4B These are schematic diagrams of travel planning interfaces provided in some embodiments of this application;

[0059] Figure 5 These are schematic diagrams of travel planning interfaces provided in some embodiments of this application;

[0060] Figure 6A This is a schematic diagram of a restaurant rating interface provided in some embodiments of this application;

[0061] Figure 6B This is a schematic diagram of a restaurant rating interface provided in some embodiments of this application;

[0062] Figure 7This is a schematic diagram of a restaurant rating interface provided in some embodiments of this application;

[0063] Figure 8A These are schematic diagrams of the session interface provided in some embodiments of this application;

[0064] Figure 8B These are schematic diagrams of the session interface provided in some embodiments of this application;

[0065] Figure 9 These are schematic diagrams of the session interface provided in some embodiments of this application;

[0066] Figure 10A These are schematic diagrams of SMS interfaces provided in some embodiments of this application;

[0067] Figure 10B These are schematic diagrams of SMS interfaces provided in some embodiments of this application;

[0068] Figure 11 These are schematic diagrams of SMS interfaces provided in some embodiments of this application;

[0069] Figure 12 These are schematic diagrams of the session interface provided in some embodiments of this application;

[0070] Figure 13 These are schematic diagrams of the session interface provided in some embodiments of this application;

[0071] Figure 14 These are schematic diagrams of the structure of an information display device provided in some embodiments of this application;

[0072] Figure 15 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0073] Figure 16 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0074] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0075] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0076] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0077] The terminology used in the implementation section of this application is only for explaining specific embodiments of this application and is not intended to limit this application. The terminology involved in the embodiments of this application is explained below.

[0078] Identifiers: In this application, identifiers are text, symbols, images, etc. used to indicate information. They can be used as carriers for displaying information, including but not limited to text identifiers, image identifiers, symbol identifiers, etc.

[0079] Applications: In this embodiment, the electronic device may have multiple applications (APPs) installed, and icons of these applications may be displayed on the home screen of the electronic device. The applications in this embodiment may be embedded applications (i.e., system applications of the electronic device) or downloadable applications. Embedded applications are applications provided as part of the implementation of the electronic device. Downloadable applications are applications that can provide their own Internet Protocol Multimedia Subsystem (IMS) connectivity. The downloadable application may be an application pre-installed on the electronic device or a third-party application downloaded and installed by the user. As an example, applications may include: social applications, image management applications (e.g., photo albums), map applications (e.g., maps), browser applications, music applications, etc.

[0080] Model: A model is a simulation or abstraction of certain characteristics and inherent relationships of objective reality. A model is a role. The concept of a model can be defined as follows: a thing is called a "model" because of its role or purpose in a specific situation—in that situation, it directly or indirectly carries certain attributes of another thing, and based on these attributes, it acts as a substitute or representation of that thing; thus, by using the attributes obtained from the model, the correlation between operations and the corresponding attributes of that thing can be achieved.

[0081] Icons: Icons are computer graphics with clear referential meanings. Icons can also be graphic symbols with referential significance; they are not only graphics but also symbols, possessing the characteristics of highly condensed and quick information delivery, and easy memorability.

[0082] Interface: This refers to the visual interface through which users interact with electronic devices, such as mobile phones. It serves as the medium for information presentation and input / output within a hardware or software system. Electronic devices can display an interface on a screen, allowing users to interact with the device through touch, clicks, or gestures. The interface can include elements such as icons, buttons, menus, text, and labels.

[0083] Controls: A control (also called a part, component, widget, or control) is a graphical user interface element. It is a basic building block of the user interface, such as a window or text box, displayed in the program interface of any application. Controls can be buttons, text boxes, labels, etc., used to control all the data processed by each application and the interactive operations related to that data. Controls, elements in a graphical user interface, can receive user input to perform corresponding processing or display related data. Controls can include, but are not limited to, virtual buttons, sliders, progress bars, and checkboxes.

[0084] Artificial Intelligence (AI) is a key driving force behind the new round of technological revolution and industrial transformation. It is a new technological science that studies and develops theories, methods, technologies, and application systems to simulate, extend, and expand human intelligence. AI is an important component of the discipline of intelligence; it attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI is a very broad science, encompassing robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, and more.

[0085] Large Language Models (LLMs) are AI models trained on massive amounts of text data using deep learning techniques. They are capable of understanding and generating natural language and demonstrate powerful capabilities in natural language processing tasks.

[0086] Optical Character Recognition (OCR): OCR refers to the process by which electronic devices examine the characters displayed on the screen, determine their shape by detecting dark and light patterns, and then translate the shape into computer text using character recognition methods. In other words, for printed characters, it uses optical methods to convert the text displayed on the screen into a black and white dot matrix image file, and then uses recognition software to convert the text in the image into text format for further editing and processing by word processing software.

[0087] Window or pop-up: In electronic devices, a window or pop-up is a basic unit set up in the graphical user interface by an application to use data, where the application and data are integrated. Users can operate the application and manage, generate, and edit data within a window or pop-up. A window or pop-up typically includes elements such as a title bar, menu bar, toolbar, control menu buttons, maximize, minimize, and close buttons, scroll bars, window or pop-up borders, and a work area.

[0088] The information display method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0089] The information display method provided in this application can be applied to scenarios where users use electronic devices to obtain AI service functions.

[0090] For example, in scenario 1, user A is chatting with a friend on their phone and uses an AI application on the phone to answer the friend's questions. Another example is scenario 2, where user B uses an AI application on their phone to write a review for a restaurant.

[0091] The information display method provided in this application can be executed by an information display device. Exemplarily, the information display device can be an electronic device, or a functional component or entity within that electronic device. The following will use an electronic device as an example to illustrate the information display method provided in this application.

[0092] Figure 1 This is a flowchart illustrating the information display method provided in an embodiment of this application, as shown below. Figure 1 As shown, the information display method provided in this application embodiment may include the following steps 201 and 202.

[0093] Step 201: The electronic device receives the first information entered by the user on the first interface.

[0094] In some embodiments of this application, the first interface described above can be any interface in an electronic device that does not have AI functionality.

[0095] For example, the first interface mentioned above can be any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

[0096] In this way, electronic devices can automatically execute the first task corresponding to the first information by controlling AI in an interface without AI functionality, without the need for users to manually switch between different applications in the electronic device, thus improving the convenience of electronic devices executing the first task through different applications.

[0097] In some embodiments of this application, the aforementioned first information may be text or voice input by the user on the first interface. The specific details can be determined according to actual usage requirements, and this application does not impose any limitations.

[0098] For example, in conjunction with scenario 1 above, as follows: Figure 2A As shown, the first piece of information mentioned above can be "What is a large language model?" which is entered by the user in the instant messaging interface.

[0099] For example, in conjunction with scenario 2 above, as follows: Figure 4A As shown, the first piece of information mentioned above can be the "Is Restaurant A good?" that the user enters in the service evaluation interface.

[0100] In some embodiments of this application, the first interface may include an input method keyboard, on which a user can input information so that the electronic device can obtain first information.

[0101] Step 202: The electronic device displays the second information corresponding to the first information on the first interface.

[0102] In some embodiments of this application, the aforementioned second information is task execution feedback information obtained by the AI ​​assistant based on the first information when performing the first task.

[0103] In some embodiments of this application, the first task described above may be a task determined based on first information.

[0104] For example, if the first information is "What is a large language model", the first task could be to search for the meaning of "large language model" through a browser.

[0105] In some embodiments of this application, the electronic device may display the second information in a pop-up window on the first interface; or, the electronic device may display the second information in a blank area of ​​the first interface.

[0106] It should be noted that the blank areas mentioned above are areas in the first interface that do not contain text or controls.

[0107] For example, as follows Figure 2A As shown, the blank area mentioned above can be understood as Figure 2A The area between the session message 101 and the input method keyboard 11.

[0108] In some embodiments of this application, the second information includes at least one of the following: reply information for responding to the first information; travel planning information corresponding to the first information; service evaluation information corresponding to the first information; prompt information for indicating that the first task has been executed; task information corresponding to the first task; and warning information corresponding to the first information.

[0109] In the information display method provided in this application embodiment, the electronic device can receive first information input by the user on a first interface; then, on the first interface, it displays second information corresponding to the first information; wherein, the second information is task execution feedback information obtained by an AI assistant based on the first information to perform a first task. In this solution, since the electronic device can automatically control the AI ​​assistant to automatically execute the first task corresponding to the first information according to the first information input by the user, and display the task execution feedback information obtained from executing the first task on the first interface, the user does not need to switch between different applications when the electronic device needs to perform the first task through different applications. Thus, the convenience of the electronic device performing the first task through different applications is improved.

[0110] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a first conversation message from a first contact; the first information is information entered by the user on the input method keyboard, and the first information is a question about at least part of the message content in the first conversation message; wherein, the question information is a complete question description, or the question information is at least part of the question keywords in the complete question description.

[0111] In some embodiments of this application, the aforementioned first session message may be one or more.

[0112] For example, the first conversation message mentioned above can be sent by a contact corresponding to the instant messaging interface.

[0113] In some embodiments of this application, the instant messaging interface can be a group chat interface or a private chat interface. The specific interface can be determined based on actual usage needs, and this application does not impose any limitations.

[0114] For example, when the first information is a complete problem description, the first information can be "What is a large language model".

[0115] It is understandable that the complete problem description information above can be a statement containing a subject, verb, and object for a specific problem.

[0116] For example, when the first information is at least a portion of the problem keywords in the complete problem description information, the first information can be "what".

[0117] It is understandable that at least some of the keywords in the above questions can be predicates.

[0118] For example, step 202 above can be implemented by step 202a below.

[0119] Step 202a: The electronic device displays the reply information on the first interface.

[0120] In some embodiments of this application, the above response information is used to respond to questions.

[0121] In some embodiments of this application, the electronic device may display the reply information in a pop-up window on the first interface; or, the electronic device may display the reply information in a blank area of ​​the first interface.

[0122] For example, such as Figure 2A As shown, taking a mobile phone as an example, the phone can display a conversation interface 10 with Xiaohong. This conversation interface 10 includes the conversation message 101 sent by Xiaohong: "Do you know what a big model means?". Then, the user can trigger the phone to display an input method keyboard 11 in the conversation interface 10 and enter the first information "What is a big model?" in the input method keyboard 11. Figure 2B As shown, at this point, the phone can call the AI ​​assistant in the phone to query "What is a large model", and the reply information will be displayed in pop-up window 12: "The large language model is an AI model based on deep learning technology and trained through massive text data. It can understand and generate natural language and shows powerful capabilities in natural language processing tasks."

[0123] For example, such as Figure 3 As shown, the phone can display a conversation interface 10 with Xiaohong, which includes the conversation message 101 sent by Xiaohong: "Do you know what a large language model means?". Then, the user can trigger the phone to display an input method keyboard 11 in the conversation interface 10 and input the first message "what" into the input method keyboard 11. At this time, as... Figure 2BAs shown, the mobile phone can call the AI ​​assistant in the phone to query "What is a large language model", and display the reply information "A large language model is an AI model based on deep learning technology and trained through massive text data. It can understand and generate natural language and shows powerful capabilities in natural language processing tasks" in pop-up window 12. The pop-up window 12 also displays a sending control 102, which is used to send the reply information to Xiaohong or other contacts.

[0124] In this embodiment, the user does not need to exit the conversation interface to open a program with AI question-and-answer function in order to answer the question. That is, the user can simply enter "What is a large language model" in the input box of the conversation interface and wait for the electronic device to automatically perform the above task, which reduces the user's operation steps and the time to obtain the reply information.

[0125] In some embodiments of this application, when the first interface is a travel planning interface, the aforementioned first information is information entered by the user on the input method keyboard, and the first information is task instruction information that instructs the generation of travel planning information for the travel destination.

[0126] For example, the first piece of information mentioned above can be "generate a travel guide" or "generate a travel guide for city A".

[0127] For example, step 202 above can be implemented by step 202b below.

[0128] Step 202b: The electronic device displays travel planning information for the destination on the first interface.

[0129] In some embodiments of this application, the aforementioned travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

[0130] In some embodiments of this application, the route planning information for the travel destination may include at least one of the following: route navigation information for the travel destination, real-time route congestion information for the travel destination, parking information for the travel destination, and train schedule information for the travel destination.

[0131] For example, the train information for the aforementioned travel destination may include at least one of the following: airfare information, high-speed rail information, and regular train information.

[0132] In some embodiments of this application, the accommodation planning information for the aforementioned travel destination may include at least one of the following: accommodation location information, accommodation price information, transportation information related to accommodation, and restaurant information related to accommodation.

[0133] In some embodiments of this application, the travel planning information for the aforementioned travel destination may include at least one of the following: scenic spot ticket information, scenic spot internal route planning information, scenic spot opening hours information, route planning information between multiple scenic spots, and travel time planning information.

[0134] In some embodiments of this application, the electronic device can display travel planning information in a pop-up window on the first interface; or, the electronic device can display travel planning information in a blank area of ​​the first interface.

[0135] For example, such as Figure 4A As shown, the mobile phone can display a travel planning interface 13, which includes a brief introduction of City A 14: "City A boasts beautiful scenery, amazing natural landscapes, and a rich cultural heritage." Then, the user can trigger the display of the input method keyboard 11 on the travel planning interface 13 and input the first message "Generate a travel guide for City A" into the input method keyboard 11. At this time, as... Figure 4B As shown, the mobile phone can call the AI ​​assistant in the phone to query "Generate a travel guide for city A", and display the travel guide planning information for the destination in pop-up window 15: "Hotel planning: Set up to stay at hotel B. Hotel B is closest to attraction C, which is a 5-minute walk away. Hotel B costs D yuan per night, which is affordable. Scenic spot planning: You can enter the scenic spot through gate E and tour the scenic spot from top to bottom. There is a restaurant in area F of the scenic spot where you can eat. The price is slightly expensive, so you can bring your own food. Route planning: Take the highway from point B to toll station C, exit the highway, and walk straight for 100 meters to reach hotel B in city A." Pop-up window 15 also displays a sending control 103, which is used to send the travel guide planning information for the destination to other people.

[0136] For example, such as Figure 5 As shown, the mobile phone can display a travel planning interface 13, which includes a brief introduction of City A 14: "City A boasts beautiful scenery, amazing natural landscapes, and a rich cultural heritage." Then, the user can trigger the display of the input method keyboard 11 on the travel planning interface 13 and input the first message "Generate travel guide" into the input method keyboard 11. At this time, combined with... Figure 4B As shown, the mobile phone can call the AI ​​assistant in the phone to query "Generate a travel guide for city A", and display the travel guide planning information for the destination in pop-up window 15: "Hotel planning: Set up to stay at hotel B. Hotel B is closest to attraction C, which is a 5-minute walk away, and hotel B costs D yuan per night, which is affordable. Scenic spot planning: You can enter the scenic spot through gate E and tour the scenic spot from top to bottom. There is a restaurant in area F of the scenic spot where you can eat, but the price is slightly expensive. You can bring your own food. Route planning: Take the highway from point B to toll station C, exit the highway, and walk straight for 100 meters to reach hotel B in city A."

[0137] In this embodiment of the application, when the travel planning interface is displayed, the electronic device can automatically call the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the travel planning information obtained from executing the first task in the travel planning interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing travel planning.

[0138] In some embodiments of this application, when the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; the first information is the information entered by the user in the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store.

[0139] In some embodiments of this application, the first shop mentioned above can be a restaurant, clothing store, or amusement park, etc. The specific type can be determined according to actual usage needs, and this application does not impose any limitations.

[0140] For example, the above-mentioned store logo can be any of the following: text logo, image logo, or number logo, etc., which can be determined according to actual usage needs, and this application embodiment does not impose any restrictions.

[0141] For example, the first piece of information mentioned above could be "How is the evaluation of store A?" or "How is the evaluation of this store?"

[0142] For example, step 202 above can be implemented by step 202c below.

[0143] Step 202c: The electronic device displays the store review information of the first store on the first interface.

[0144] In some embodiments of this application, the electronic device may display store review information in a pop-up window on the first interface; or, the electronic device may display store review information in a blank area of ​​the first interface.

[0145] For example, such as Figure 6A As shown, the mobile phone can display a restaurant review interface 16, which includes a brief introduction of restaurant A 17: "Restaurant A has reasonable prices, large portions, and delicious food." Then, the user can trigger the phone to display an input method keyboard 11 on the restaurant review interface 16 and input the first message, "How is restaurant A rated?", into the input method keyboard 11. At this time, as... Figure 6BAs shown, the mobile phone can call the AI ​​assistant in the phone to query "How is the review of Restaurant A", and display the restaurant review information of Restaurant A in pop-up window 18: "Restaurant A costs 100 RMB per person, the portions are large, but the taste is average. It is recommended for family gatherings." Pop-up window 18 also displays a sending control 104, which is used to send the restaurant review information of Restaurant A to other users.

[0146] For example, such as Figure 7 As shown, the mobile phone can display a restaurant review interface 16, which includes a restaurant description 17: "Restaurant A has reasonable prices, large portions, and delicious food." Then, the user can trigger the phone to display an input method keyboard 11 on the restaurant review interface 16 and input the first message, "How is this restaurant rated?". At this time, combined with... Figure 6B As shown, the mobile phone can call the AI ​​assistant in the phone to query "What is the review of Restaurant A", and display the restaurant review information of Restaurant A in pop-up window 18: "Restaurant A costs 100 RMB per person, the portions are large, but the taste is average. It is recommended for family gatherings."

[0147] In this embodiment of the application, when the service evaluation interface is displayed, the electronic device can automatically call the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the store evaluation information obtained from executing the first task in the service evaluation interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing store evaluations.

[0148] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of a to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion of the item; the first information is information entered by the user on the input method keyboard, and the first information indicates task instruction information for setting a first schedule reminder based on the second conversation message.

[0149] For example, the tasks mentioned above can be any of the following: setting an alarm, scheduling an event, or booking a train or bus. The specific task can be determined based on actual usage needs, and this application embodiment does not impose any limitations.

[0150] It is understandable that the deadline for completing the above matters is determined through the second session message.

[0151] For example, the first information mentioned above could be "set an alarm for 7 a.m. tomorrow" or "set an alarm".

[0152] For example, step 202 above can be implemented by step 202d below.

[0153] Step 202d: The electronic device displays the first prompt message and the first schedule reminder icon on the first interface.

[0154] In some embodiments of this application, the aforementioned first schedule reminder identifier is used to indicate a first schedule reminder.

[0155] In some embodiments of this application, the aforementioned first prompt information is used to indicate that a first schedule reminder corresponding to the description information of the to-do item has been set.

[0156] In some embodiments of this application, the aforementioned first schedule reminder identifier may include at least one of the following: text identifier, symbol identifier, and image identifier, etc. The specific identifier can be determined according to actual usage requirements, and this application does not impose any limitations.

[0157] In some embodiments of this application, the electronic device may display a first prompt message and a first schedule reminder icon in a pop-up window on the first interface; or, the electronic device may display the first prompt message and the first schedule reminder icon in a blank area of ​​the first interface.

[0158] For example, such as Figure 8A As shown, the phone can display a conversation interface 19 with Xiao Wang, which includes Xiao Wang's conversation message 20, "Get up at seven tomorrow morning to take the child to school." Then, the user can trigger the phone to display the input method keyboard 11 in the conversation interface 19 and input the first message, "Set an alarm for seven tomorrow morning," into the input method keyboard 11. At this time, as... Figure 8B As shown, the mobile phone can call the AI ​​assistant in the phone, and through the AI ​​assistant call the alarm clock application in the phone, set the alarm for 7:00 am in the alarm clock application, and display the first prompt message 22 "Okay, the alarm will ring at 7:00 am tomorrow" and the alarm clock logo 23 in the pop-up window 21, and display the confirmation control 105 in the pop-up window 21, which is used to instruct the user to set the alarm.

[0159] For example, such as Figure 9 As shown, the phone can display a conversation interface 19 with Xiao Wang. This conversation interface 18 includes Xiao Wang's conversation message 20, "Get up at seven tomorrow to take the child to school." Then, the user can trigger the phone to display the input method keyboard 11 in the conversation interface 18 and enter the first message "set alarm" on the input method keyboard 11. At this time, as... Figure 8B As shown, the phone can call the AI ​​assistant in the phone, and through the AI ​​assistant call the alarm clock application in the phone, set the alarm for 7:00 am in the alarm clock application, and display the first prompt message 22 "Okay, the alarm will ring at 7:00 am tomorrow" and the alarm clock icon 23 in the pop-up window 21.

[0160] In this embodiment of the application, when the instant messaging interface is displayed, the electronic device can automatically call the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the first prompt information and the first schedule reminder icon obtained from executing the first task in the instant messaging interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the convenience of the electronic device when executing schedule reminders.

[0161] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation message includes an instruction message requiring the user to send authentication credential information; the first information is information entered by the user on the input method keyboard, and the first information includes authentication credential information.

[0162] For example, the instant messaging interface described above can be a text messaging interface.

[0163] For example, step 202 above can be implemented by step 202e below.

[0164] Step 202e: The electronic device displays the first warning information on the first interface.

[0165] In some embodiments of this application, the aforementioned first warning information is used to alert users to avoid sending authentication credential information.

[0166] In some embodiments of this application, the electronic device may display the first warning information in a pop-up window on the first interface; or, the electronic device may display the first warning information in a blank area of ​​the first interface.

[0167] For example, such as Figure 10A As shown, the mobile phone can display an SMS interface 24 with Bank A. This SMS interface 24 includes a conversation message 25 from Bank A: "Your bank card has been frozen due to out-of-town spending. You need to provide an SMS verification code immediately to unfreeze it, otherwise your funds will be cleared." Then, the user can trigger the phone to display the input method keyboard 11 on the SMS interface 24 and enter the SMS verification code "1234" on the input method keyboard 11. At this time, as... Figure 10B As shown, the mobile phone can call the AI ​​assistant in the phone to automatically generate anti-fraud text, and display anti-fraud text 27 "You may have encountered a scam! Please stop all operations immediately and do not provide any verification code for transfer", in pop-up window 26, and delete the SMS verification code "1234" entered by the user in the input method keyboard 11, and display a confirmation control 106 in pop-up window 26, which is used to indicate to the user that they are aware that the SMS is a scam SMS.

[0168] For example, such as Figure 10AAs shown, the mobile phone can display an SMS interface 24 with Bank A. This SMS interface 24 includes a conversation message 25 from Bank A: "Your bank card has been frozen due to out-of-town spending. You need to provide an SMS verification code immediately to unfreeze it, otherwise your funds will be cleared." Then, the user can trigger the phone to display the input method keyboard 11 on the SMS interface 24 and enter the SMS verification code "1234" on the input method keyboard 11. At this time, as... Figure 11 As shown, the mobile phone can call the AI ​​assistant in the phone to automatically generate anti-fraud text, and display the anti-fraud text 27 in the pop-up window 26: "You may have encountered a fraud! Please stop all operations immediately and do not provide any verification codes or transfers. Tip: Clicking the 'Confirm Control' 28 can help you quickly delete the verification code and add the SMS number corresponding to this SMS interface 24 to the blacklist." After clicking the 'Confirm Control' 28, the user can delete the SMS verification code "1234" entered by the user in the input method keyboard 11 and add the SMS number to the blacklist.

[0169] In this embodiment of the application, when the instant messaging interface is displayed, the electronic device can automatically call the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the first warning information obtained from executing the first task in the instant messaging interface. Thus, the electronic device does not require the user to switch between different applications when executing the first task, thereby improving the security of the electronic device when sending SMS verification codes.

[0170] In some embodiments of this application, prior to step 202 described above, the information display method provided in this application further includes steps 301 and 302 as described below.

[0171] Step 301: If the first reference information includes a trigger word, the electronic device determines that it recognizes the intention to invoke AI capabilities.

[0172] In some embodiments of this application, the first reference information mentioned above includes at least one of the following: first information; interface context information of the first interface.

[0173] In some embodiments of this application, the aforementioned trigger words are used to trigger the AI ​​assistant to obtain second information.

[0174] In some embodiments of this application, the electronic device can perform text recognition on the aforementioned first information and interface context information to determine whether the first information and interface context information contain trigger words that trigger the AI ​​assistant.

[0175] For example, the trigger words mentioned above may include at least one of the following:

[0176] Verbs: help me, trouble, please, take a look, what, check, find, search, retrieve, locate, recommend, compare, contrast, generate, write, draft, rewrite, polish, translate, summarize, organize, summarize, extract, extract, analyze, plan, arrange, book, make an appointment, remind, set, set, add, delete, update, modify, change, cancel, synchronize, share, copy, paste, open, navigate, dial, send, push, query, statistics, calculate, convert, transform, format, proofread, correct errors, optimize, compress.

[0177] Time: Today, Tomorrow, The Day After Tomorrow, This Week, Next Week, Monday to Sunday, Morning, Afternoon, Evening, Morning, Afternoon, Midnight, This Weekend, Next Month, End of Month, Beginning of Year, 12 o'clock.

[0178] Schedule: Meetings, appointments, meetings, interviews, reminders, alarms, itineraries, calendars, check-ins.

[0179] Location: nearby, close to, nearest, to, go, how to get there, route, navigation, map, location, distance, how far, address, store, shop, restaurant, hotel, airport, train station, subway station, parking lot, company, school, hospital.

[0180] Shopping: Buy, purchase, place an order, reserve, group buying, discounts, coupons, prices, reviews, rankings, best, recommendations, word-of-mouth, food delivery, delivery, home service, repair, express delivery, pickup.

[0181] Communication: send, forward, share, @, contact, dial, SMS, email, business card.

[0182] Document processing: PDF, Word, Excel, PPT, tables, formatting, templates, contracts, quotations, resumes, meeting minutes, export, import, merge, split, convert to image, convert to text, OCR.

[0183] Data and Calculation: Statistics, summarization, reconciliation, verification, alignment, average, maximum, minimum, variance, percentage, month-on-month comparison, year-on-year comparison, conversion, calculation, sorting, and filtering.

[0184] Multilingual: English, Chinese, Japanese, Korean, German, French, Spanish, Russian, Arabic.

[0185] High-risk keywords: money laundering, deduction of fees, bank card, verification code, rebate, virtual currency, freeze.

[0186] In some embodiments of this application, the aforementioned interface context information includes at least one of the following: the interface content of the first interface; the application attribute information of the first application corresponding to the first interface; the geographical location information of the electronic device; and the second reference information associated with the interface content of the first interface.

[0187] For example, the interface content of the first interface can be all the interface content included in the first interface. For example, if the first interface is a conversation interface with Xiaohong, the interface content can include: the contact name "Xiaohong" and the conversation message "Do you know what a large language model is?".

[0188] In some embodiments of this application, the electronic device can obtain the interface content of the first interface described above through OCR.

[0189] For example, the application attribute information includes at least one of the following: application name; application type; application function.

[0190] For example, if the first interface is an instant messaging interface, the name of the application could be "A Conversation Application"; the application type could be a communication type; and the application function could be chat.

[0191] For example, the second reference information mentioned above is information that matches the interface content of the first interface; the second reference information includes at least one of the following: image information; schedule information; video information.

[0192] For example, when the first interface includes an image and the image includes a portrait of person A, the second reference information could be that an image in a gallery application also contains a portrait of person A.

[0193] For example, when the first interface includes setting an alarm for tomorrow morning, the second reference information could be the "taking the child to school tomorrow morning" schedule added by the user in the calendar.

[0194] For example, if the first interface includes a video and the video contains a portrait of person B, the second reference information may also include a video in a gallery application that contains a portrait of person B.

[0195] Step 302: Once the intent to invoke AI capabilities is identified, the electronic device outputs second information through the AI ​​assistant.

[0196] In some embodiments of this application, the electronic device can combine the first information and the interface context content into prompts and send them to the local edge-side large language model, which then determines whether AI capabilities need to be invoked. For performance considerations, a query is only performed after the user has entered a complete sentence, i.e., if the pause time in the input method exceeds 1 second.

[0197] For example, an electronic device can combine initial information and interface context information into prompts through an AI assistant, and then input the prompts into a local edge-side large language model, which will determine and recognize the intent to call AI capabilities.

[0198] Example of prompts:

[0199] <system>

[0200] You are an intent recognition assistant that determines whether a user needs to utilize the phone's AI capabilities based on their input and context.

[0201] <input>

[0202] What

[0203] <context>

[0204] Current application: Chat application A

[0205] Interviewee: Xiaohong

[0206] Recent conversation: Do you know what a large language model is?

[0207] If the model determines that AI capabilities need to be invoked, it returns "Yes"; otherwise, it returns "No".

[0208] It should be noted that the specific implementation process of step 302 above can be found in the following embodiments, and will not be repeated here to avoid repetition.

[0209] In this embodiment, the electronic device can determine whether to call the AI ​​assistant to output the second information based on the trigger word contained in the first information, thereby improving the flexibility of the electronic device in calling the AI ​​assistant.

[0210] In some embodiments of this application, the first interface described above includes an input method keyboard and an AI icon.

[0211] In some embodiments of this application, the aforementioned AI identifier is used to trigger an AI assistant to perform a first task based on first information and display second information.

[0212] In some embodiments of this application, the AI ​​identifier can be any of the following: a numerical identifier, a text identifier, or an image identifier, etc. The specific identifier can be determined according to actual usage requirements, and this application does not impose any limitations.

[0213] In some embodiments of this application, the aforementioned AI identifier may be displayed in the input method keyboard or in the first interface. The specific display can be determined according to actual usage requirements, and this application does not impose any limitations.

[0214] In some embodiments of this application, the AI ​​identifier can be carried on a screen component, that is, the AI ​​identifier can be displayed through a floating control.

[0215] For example, a screen component can be displayed floating at any position on the screen, and when the user drags the floating control, the floating control can move on the screen as the user drags it.

[0216] It should be noted that when users want to interact with the floating control later, they can control its movement through specific inputs.

[0217] In some embodiments of this application, the above-mentioned floating control can also be overlaid on the first interface or the input method keyboard with a preset transparency.

[0218] For example, suppose the preset transparency is denoted as T, and the value of T can be 0%. <T1<100%。

[0219] In some embodiments of this application, the aforementioned floating control may also be displayed with high or low brightness to remind the user of the specific display location of the floating control.

[0220] In some embodiments of this application, the electronic device may display an AI identifier when it detects that the first information contains a trigger word.

[0221] It is understandable that the aforementioned AI identifier is used to trigger electronic devices to invoke the AI ​​assistant.

[0222] For example, prior to step 202 above, the information display method provided in this application embodiment further includes step 401 below, and step 202 above can be specifically implemented through step 402 below.

[0223] Step 401: The electronic device receives the user's selection input for the AI ​​identifier.

[0224] In some embodiments of this application, the aforementioned input selection can be user click input, swipe input, or preset trajectory input to the AI ​​icon, etc. The specific method can be determined according to actual usage needs, and this application does not impose any limitations.

[0225] Step 402: In response to the selected input, the electronic device displays the second information corresponding to the first information on the first interface.

[0226] For example, combined Figure 2A ,like Figure 12 As shown, when a user inputs "What is a large language model" into the input method keyboard 11 displayed in the conversation interface 10, the phone detects the trigger word "what" and displays the AI ​​identifier 29 in the input method keyboard 11. The user can then click on the AI ​​identifier 29 to input, such as... Figure 2B As shown, this allows the phone to call the AI ​​assistant on the phone to query "What is a large language model", and displays the reply information in pop-up window 12: "The large language model is an AI model based on deep learning technology and trained through massive text data. It can understand and generate natural language and shows powerful capabilities in natural language processing tasks."

[0227] In this embodiment, the electronic device can invoke the AI ​​assistant by inputting the AI ​​identifier by the user, thereby avoiding misidentification of the first information by the electronic device and improving the accuracy of the second information output by the electronic device.

[0228] In some embodiments of this application, step 302 described above can be implemented by step 302a as described below.

[0229] Step 302a: When the intention to call AI capabilities is identified based on the first reference information, the electronic device inputs the first information and the interface context information of the first interface into the task execution model through the AI ​​assistant. The task execution model performs context recognition processing on the first information based on the interface context information of the first interface and outputs the second information.

[0230] In some embodiments of this application, the task execution model described above can be an AI model, which can be a large language model.

[0231] In some embodiments of this application, the electronic device can generate a prompt word based on the first information and the interface context information of the first interface, and input the prompt word into the task execution model so that the task execution model can perform context recognition processing and output the second information.

[0232] For example, an electronic device can use an AI assistant to concatenate the first information and the interface context information of the first interface into strings to generate prompts. Then, the prompts are input into the AI ​​model corresponding to the AI ​​assistant so that the AI ​​model can perform context recognition processing on the prompts and output the second information.

[0233] Example of prompts:

[0234] <system>

[0235] You are an AI assistant that can answer users' various questions in a friendly manner.

[0236] <input>

[0237] What

[0238] <context>

[0239] Current application: Chat application A

[0240] Interviewee: Xiaohong

[0241] Recent conversation: Do you know what a large language model is?

[0242] In some embodiments of this application, the electronic device can use an AI model to extract features from the aforementioned interface context information execution and the first information to obtain first feature information containing the interface context information execution and the first information. Then, it can perform semantic extraction on the first feature information to obtain semantic information of the interface context information execution and the first information. Finally, it can perform context recognition processing on the aforementioned semantic information to output the aforementioned second information.

[0243] In some embodiments of this application, before step 202 above, the information display method provided in the embodiments of this application further includes steps 501 to 503 as described below, and step 302 above can be specifically implemented by step 302b as described below.

[0244] Step 501: If at least one task element of the first task is missing in the first information, the electronic device obtains at least one candidate information based on the first information and the interface context information of the first interface through the AI ​​assistant.

[0245] In some embodiments of this application, the aforementioned at least one candidate information is task element information determined based on the interface context information of the first interface, and the at least one candidate information includes all task element information missing from the first information.

[0246] In some embodiments of this application, after obtaining the first information, the electronic device can perform semantic recognition on the first information and the interface context to determine at least one task element of the first task that is missing in the first information.

[0247] For example, when the first information is "what" and the interface context information is "Do you know what a large language model is?", the electronic device can determine the missing task element information in the first information "what" and the interface context information "Do you know what a large language model is?" as "is a large language model".

[0248] In some embodiments of this application, the electronic device can perform text generation processing based on the first information and the interface context information of the first interface to obtain at least one candidate information.

[0249] For example, an electronic device can perform semantic recognition on interface context information to determine at least one missing task element information in the first information, and recommend the at least one task element information as at least one candidate information to the user.

[0250] Step 502: The electronic device displays at least one candidate message on the input method keyboard.

[0251] In some embodiments of this application, the electronic device may display at least one candidate information in a pop-up window on the first interface; or, the electronic device may display at least one candidate information in a blank area of ​​the first interface.

[0252] Step 503: The electronic device determines the target candidate information.

[0253] In some embodiments of this application, the target candidate information is the candidate information selected by the user from at least one candidate information, or the target candidate information is the candidate information ordered at the starting position among at least one candidate information.

[0254] For example, combined Figure 3 ,like Figure 13 As shown, the mobile phone can display three candidate messages on the input method keyboard via pop-up window 30 in the conversation interface 10. These three candidate messages can be "What does it mean?", "Large language model", and "What is the large language model?". The user can then click to input the candidate message "What does it mean?", so that the electronic device can identify "What does it mean?" as the target candidate message and input the first message "What", the conversation message 101, and the target candidate message "What does it mean?" into the AI ​​model to display the second message in the conversation interface 10.

[0255] For example, such as Figure 13 As shown, the mobile phone can display three candidate messages on the input method keyboard 11 in the conversation interface 10. These three candidate messages can be "What does it mean?", "Large language model", and "Query". If the user does not select any candidate message, the electronic device can determine the first candidate message "What does it mean?" as the target candidate message and input the first message "What", the conversation message 101, and the target candidate message "What does it mean?" into the AI ​​model to display the second message in the conversation interface.

[0256] In some embodiments of this application, step 503 can be implemented by step 503a or step 503b as described below.

[0257] Step 503a: Upon receiving the user's input of selecting the first candidate information from at least one candidate information, the first candidate information is determined as the target candidate information.

[0258] In some embodiments of this application, the aforementioned selection input can be user click input, swipe input, preset trajectory input, or voice input, etc. The specific method can be determined according to actual usage needs, and this application does not impose any limitations.

[0259] Step 503b: If no user input is received to select candidate information, the second candidate information ranked at the beginning of at least one candidate information is determined as the target candidate information.

[0260] In some embodiments of this application, when no user input of candidate information is received and the user clicks the AI ​​icon, the electronic device automatically determines the second candidate information that ranks first among at least one candidate information as the target candidate information.

[0261] In this embodiment, the electronic device can determine the target candidate information based on user input, or it can automatically determine the target candidate information without user input, thereby improving the flexibility of the electronic device in determining the target candidate information.

[0262] Step 302b: When the intention to call AI capabilities is identified based on the first reference information, the electronic device inputs the first information, the interface context information of the first interface, and the target candidate information into the task execution model through the AI ​​assistant. The task execution model performs context recognition processing on the first information based on the interface context information of the first interface and the target candidate information, and outputs the second information.

[0263] In some embodiments of this application, the electronic device can generate prompt words based on the first information, the interface context information of the first interface, and the target candidate information, and input the prompt words into the task execution model so as to perform context recognition processing through the task execution model and display the second information on the first interface.

[0264] In this embodiment, the electronic device can output second information based on the first information input by the user, the interface context information of the first interface, and the target candidate information. This avoids semantic inaccuracies caused by semantic recognition based solely on the first information and improves the accuracy of the second information output by the electronic device.

[0265] It should be noted that each of the above method embodiments, or various possible implementations of each method embodiment, can be executed individually or in combination of any two or more. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0266] The information display method provided in this application can be executed by an information display device. This application uses an information display device executing the information display method as an example to illustrate the information display device provided in this application.

[0267] Figure 14 This is a schematic diagram of the structure of the information display device 70 provided in the embodiment of this application. The information display device 70 includes a receiving module 71 and a display module 72.

[0268] The receiving module 71 is used to receive first information input by the user on the first interface. The display module 72 is used to display second information corresponding to the first information received by the receiving module on the first interface; wherein, the second information is task execution feedback information obtained by the artificial intelligence AI assistant based on the first information to perform the first task.

[0269] In one possible implementation, the aforementioned first interface can be any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

[0270] In one possible implementation, the second information mentioned above includes at least one of the following:

[0271] Reply information used to respond to the first message;

[0272] The first piece of information corresponds to travel planning information;

[0273] The service evaluation information corresponding to the first piece of information;

[0274] A notification message indicating that the first task has been completed;

[0275] Task information corresponding to the first task;

[0276] The first piece of information corresponds to the warning information.

[0277] In one possible implementation, when the first interface is an instant messaging interface, the instant messaging interface includes a first conversation message from a first contact; the first information is information entered by the user on the input method keyboard, and the first information is a question message about at least part of the message content in the first conversation message; wherein, the question message is a complete question description, or the question message is at least part of the question keywords in the complete question description; the display module 72 is specifically used to display reply information, and the reply information is used to reply to the question information.

[0278] In one possible implementation, when the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that indicates the generation of travel planning information for the travel destination; the display module 72 is specifically used to display the travel planning information for the travel destination; wherein, the travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

[0279] In one possible implementation, when the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; the first information is the information entered by the user in the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; the display module 72 is specifically used to display the store evaluation information of the first store.

[0280] In one possible implementation, if the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of the to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion; the first information is information entered by the user on the input method keyboard, and the first information indicates the task instruction information for setting a first schedule reminder based on the second conversation message; the display module 72 is specifically used to display a first prompt message and a first schedule reminder identifier; wherein, the first schedule reminder identifier is used to indicate a first schedule reminder; the first prompt message is used to indicate that the first schedule reminder corresponding to the description of the to-do item has been set.

[0281] In one possible implementation, if the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation message includes an instruction message requiring the user to send authentication credential information; the first message is the information entered by the user on the input method keyboard, and the first message includes authentication credential information; the display module 72 is specifically used to display a first warning message, which is used to warn the user to avoid sending authentication credential information.

[0282] In one possible implementation, the information display device 70 further includes a processing module. The processing module is configured to, before displaying second information corresponding to the first information on the first interface, determine, if the first reference information includes a trigger word, that an AI capability invocation intent has been identified; the first reference information includes at least one of the following: first information; interface context information of the first interface; and, upon determining that an AI capability invocation intent has been identified, output the second information through an AI assistant; wherein the trigger word is used to trigger the AI ​​assistant to obtain the second information.

[0283] In one possible implementation, the first interface includes an input method keyboard and an AI icon; the AI ​​icon is used to trigger the AI ​​assistant to perform a first task based on the first information and display the second information; the receiving module 71 is also used to receive the user's selection input for the AI ​​icon before displaying the second information corresponding to the first information on the first interface; the display module is specifically used to display the second information corresponding to the first information on the first interface in response to the selection input.

[0284] In one possible implementation, the aforementioned processing module is specifically used to, when determining that the intention to invoke AI capabilities is recognized based on the first reference information, input the first information and the interface context information of the first interface into the task execution model through the AI ​​assistant, and then, through the task execution model, perform context recognition processing on the first information based on the interface context information of the first interface, and output the second information.

[0285] In one possible implementation, the processing module is further configured to, before displaying the second information corresponding to the first information on the first interface, obtain at least one candidate information based on the first information and the interface context information of the first interface, in the case where the first information lacks at least one task element of the first task; wherein the at least one candidate information is task element information determined based on the interface context information of the first interface; and the at least one candidate information includes all task element information missing from the first information. The display module 72 is further configured to display the at least one candidate information on the input method keyboard. The processing module is further configured to determine target candidate information; wherein the target candidate information is the candidate information selected by the user from the at least one candidate information, or the target candidate information is the candidate information ranked at the beginning position among the at least one candidate information. Specifically, the processing module is configured to, when determining based on the first reference information that the intention to invoke AI capabilities has been identified, input the first information, the interface context information of the first interface, and the target candidate information into the task execution model via the AI ​​assistant; and, through the task execution model, perform context recognition processing on the first information based on the interface context information of the first interface and the target candidate information, output the second information.

[0286] In one possible implementation, the above-mentioned processing module is specifically used to determine the first candidate information as the target candidate information when receiving input from the user to select the first candidate information among at least one candidate information; and to determine the second candidate information in the starting position among at least one candidate information as the target candidate information when not receiving input from the user to select candidate information.

[0287] In one possible implementation, the aforementioned interface context information includes at least one of the following: the interface content of the first interface; the application attribute information of the first application corresponding to the first interface; the geographical location information of the electronic device; and second reference information associated with the interface content of the first interface.

[0288] The application attribute information includes at least one of the following: application name; application type; application function; the second reference information is information that matches the interface content of the first interface; the second reference information includes at least one of the following: image information; schedule information; video information.

[0289] In the information display device provided in this application embodiment, since the information display device can automatically control the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the task execution feedback information obtained from executing the first task in the first interface, the information display device does not need to be manually switched between different applications when it needs to execute the first task through different applications. Thus, the convenience of the information display device when executing the first task through different applications is improved.

[0290] The information display device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device, augmented reality / virtual reality device, robot, wearable device, super mobile personal computer, netbook, or personal digital assistant, etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the specific device.

[0291] The information display device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system used.

[0292] The information display device provided in this application can implement the various processes implemented in the various embodiments of the above-described information display method. To avoid repetition, it will not be described again here.

[0293] Optionally, such as Figure 15 As shown, this application embodiment also provides an electronic device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. When the program or instructions are executed by the processor 601, they implement the various steps of the above-described information display method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0294] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0295] Figure 16 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0296] The electronic device 700 includes, but is not limited to, components such as: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0297] Those skilled in the art will understand that the electronic device 700 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 16 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0298] The user input unit 707 is used to receive first information input by the user on the first interface. The display unit 706 is used to display second information corresponding to the first information on the first interface; wherein the second information is task execution feedback information obtained by the artificial intelligence AI assistant based on the first information to perform the first task.

[0299] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a first conversation message from a first contact; the first information is information entered by the user on the input method keyboard, and the first information is a question message about at least part of the message content in the first conversation message; wherein, the question message is a complete question description, or the question message is at least part of the question keywords in the complete question description; the above-mentioned display unit 706 is specifically used to display reply information, and the reply information is used to reply to the question information.

[0300] In some embodiments of this application, when the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that indicates the generation of travel planning information for the travel destination; the above-mentioned display unit 706 is specifically used to display the travel planning information for the travel destination; wherein, the travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

[0301] In some embodiments of this application, when the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; the first information is the information entered by the user in the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; the above-mentioned display unit 706 is specifically used to display the store evaluation information of the first store.

[0302] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of a to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion; the first information is information entered by the user on the input method keyboard, and the first information indicates task instruction information for setting a first schedule reminder based on the second conversation message; the display unit 706 is specifically used to display a first prompt message and a first schedule reminder identifier; wherein, the first schedule reminder identifier is used to indicate a first schedule reminder; the first prompt message is used to indicate that the first schedule reminder corresponding to the description of the to-do item has been set.

[0303] In some embodiments of this application, when the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation information includes an instruction message requiring the user to send authentication credential information; the first information is information entered by the user on the input method keyboard, and the first information includes authentication credential information; the aforementioned display unit 706 is specifically used to display a first warning message, which is used to warn the user to avoid sending authentication credential information.

[0304] In some embodiments of this application, the processor 710 is configured to determine, before displaying second information corresponding to the first information on the first interface, if the first reference information includes a trigger word, that an AI capability call intention is identified; the first reference information includes at least one of the following: first information; interface context information of the first interface; and if the AI ​​capability call intention is identified, output the second information through an AI assistant; wherein the trigger word is used to trigger the AI ​​assistant to obtain the second information.

[0305] In some embodiments of this application, the first interface includes an input method keyboard and an AI icon; the AI ​​icon is used to trigger an AI assistant to perform a first task based on the first information and display the second information; the user input unit 707 is further used to receive the user's selection input for the AI ​​icon before displaying the second information corresponding to the first information on the first interface. The display unit 706 is specifically used to display the second information corresponding to the first information on the first interface in response to the selection input.

[0306] In some embodiments of this application, the processor 710 is specifically used to, when determining that the intention to call AI capabilities is recognized based on the first reference information, input the first information and the interface context information of the first interface into the task execution model through the AI ​​assistant, and perform context recognition processing on the first information based on the interface context information of the first interface through the task execution model, and output the second information.

[0307] In some embodiments of this application, the processor 710 is further configured to, before displaying second information corresponding to the first information on the first interface, obtain at least one candidate information based on the first information and the interface context information of the first interface when the first information lacks at least one task element of the first task, through an AI assistant; wherein the at least one candidate information is task element information determined based on the interface context information of the first interface; the at least one candidate information includes all task element information missing in the first information. The display unit 706 is further configured to display at least one candidate information on the input method keyboard. The processor 710 is further configured to determine target candidate information; wherein the target candidate information is candidate information selected by the user from at least one candidate information, or the target candidate information is candidate information ordered at the beginning position among at least one candidate information. Specifically, the processor 710 is configured to, when determining based on the first reference information that an intention to call AI capabilities has been identified, input the first information, the interface context information of the first interface, and the target candidate information into a task execution model through an AI assistant, and through the task execution model, perform context recognition processing on the first information based on the interface context information of the first interface and the target candidate information, and output the second information.

[0308] In some embodiments of this application, the processor 710 is specifically configured to, upon receiving input from a user selecting a first candidate information among at least one candidate information, determine the first candidate information as the target candidate information; and, if no input from a user selecting candidate information is received, determine the second candidate information in the starting position among at least one candidate information as the target candidate information.

[0309] In the electronic device provided in this application embodiment, since the electronic device can automatically control the AI ​​assistant to automatically execute the first task corresponding to the first information based on the first information input by the user, and display the task execution feedback information obtained from executing the first task on the first interface, the electronic device does not need to manually switch between different applications when it needs to execute the first task through different applications. Thus, the convenience of the electronic device when executing the first task through different applications is improved.

[0310] It should be understood that, in this embodiment, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042. The GPU 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick, which will not be described in detail here.

[0311] The memory 709 can be used to store software programs and various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0312] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0313] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described information display method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0314] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0315] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described information display method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0316] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0317] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the information display method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0318] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0319] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0320] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.< / context> < / system> < / context> < / system>

Claims

1. An information display method, characterized in that, include: Receive the first information entered by the user on the first interface; On the first interface, the second information corresponding to the first information is displayed; The second information is the task execution feedback information obtained by the AI ​​assistant based on the first information when performing the first task.

2. The method according to claim 1, characterized in that, The first interface can be any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

3. The method according to claim 1, characterized in that, The second information includes at least one of the following: Reply information used to respond to the first information; The travel itinerary planning information corresponding to the first piece of information; The service evaluation information corresponding to the first information; A notification message indicating that the first task has been executed; Task information corresponding to the first task; The warning information corresponding to the first piece of information.

4. The method according to any one of claims 1-3, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes the first conversation message of the first contact. The first information is information entered by the user on the input method keyboard, and the first information is a question about at least part of the message content in the first conversation message; wherein, the question information is a complete question description, or the question information is at least part of the question keywords in the complete question description; The display of the second information corresponding to the first information includes: The response information is displayed and is used to reply to the question.

5. The method according to any one of claims 1-3, characterized in that, When the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that indicates the generation of travel planning information for the travel destination. The display of the second information corresponding to the first information includes: Displays travel itinerary planning information for the stated travel destination; The travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

6. The method according to any one of claims 1-3, characterized in that, When the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; The first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; The display of the second information corresponding to the first information includes: Displays the store reviews for the first store.

7. The method according to any one of claims 1-3, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of the to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion of the item; The first information is the information entered by the user on the input method keyboard, and the first information indicates the task instruction information for setting the first schedule reminder based on the second session message; The display of the second information corresponding to the first information includes: Display the first prompt message and the first schedule reminder icon; The first schedule reminder identifier is used to indicate the first schedule reminder; the first prompt information is used to indicate that the first schedule reminder corresponding to the description information of the to-do item has been set.

8. The method according to any one of claims 1-3, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation message includes an instruction message requiring the user to send authentication credential information. The first information is the information entered by the user on the input method keyboard, and the first information includes authentication credential information; The display of the second information corresponding to the first information includes: The system displays a first warning message, which serves to alert the user to avoid sending the authentication credential information.

9. The method according to claim 1, characterized in that, Before displaying the second information corresponding to the first information on the first interface, the method further includes: If the first reference information includes a trigger word, it is determined that the AI ​​capability invocation intent is identified; the first reference information includes at least one of the following: first information; interface context information of the first interface; Once the intent to invoke AI capabilities is identified, the AI ​​assistant outputs second information. The trigger word is used to trigger the AI ​​assistant to obtain the second information.

10. The method according to claim 1 or 9, characterized in that, The first interface includes an input method keyboard and an AI icon; the AI ​​icon is used to trigger the AI ​​assistant to perform a first task and display second information based on the first information. Before displaying the second information corresponding to the first information on the first interface, the method further includes: Receive user input regarding their selection of the AI ​​identifier; The step of displaying second information corresponding to the first information on the first interface includes: In response to the selection input, second information corresponding to the first information is displayed on the first interface.

11. The method according to claim 9, characterized in that, Upon determining that the intent to invoke AI capabilities has been identified, the AI ​​assistant outputs second information, including: If the intention to invoke AI capabilities is identified based on the first reference information, the AI ​​assistant inputs the first information and the interface context information of the first interface into the task execution model. The task execution model performs context recognition processing on the first information based on the interface context information of the first interface and outputs the second information.

12. The method according to claim 9, characterized in that, Before displaying the second information corresponding to the first information on the first interface, the method further includes: If at least one task element of the first task is missing in the first information, the AI ​​assistant obtains at least one candidate information based on the first information and the interface context information of the first interface; wherein, the at least one candidate information is task element information determined based on the interface context information of the first interface; the at least one candidate information includes all task elements missing in the first information; Display the at least one candidate piece of information on the input method keyboard; Determine target candidate information; wherein, the target candidate information is the candidate information selected by the user from the at least one candidate information, or the target candidate information is the candidate information ranked at the starting position among the at least one candidate information; Upon determining that the intent to invoke AI capabilities has been identified, the AI ​​assistant outputs second information, including: If the intention to invoke AI capabilities is identified based on the first reference information, the AI ​​assistant inputs the first information, the interface context information of the first interface, and the target candidate information into the task execution model. The task execution model performs context recognition processing on the first information based on the interface context information of the first interface and the target candidate information, and outputs the second information.

13. The method according to claim 12, characterized in that, The determination of target candidate information includes: Upon receiving a user's selection input for a first candidate among the at least one candidate information, the first candidate information is determined as the target candidate information; If no user input is received to select candidate information, the second candidate information ranked at the beginning of the at least one candidate information is determined as the target candidate information.

14. The method according to claim 9, characterized in that, The interface context information includes at least one of the following: the interface content of the first interface; the application attribute information of the first application corresponding to the first interface; the geographical location information of the electronic device; and second reference information associated with the interface content of the first interface. The application attribute information includes at least one of the following: application name; application type; application function; the second reference information is information that matches the interface content of the first interface; the second reference information includes at least one of the following: image information; schedule information; video information.

15. An information display device, characterized in that, include: The receiving module is used to receive the first information entered by the user on the first interface. The display module is used to display second information corresponding to the first information received by the receiving module on the first interface; The second information is the task execution feedback information obtained by the AI ​​assistant based on the first information when performing the first task.

16. The apparatus according to claim 15, characterized in that, The first interface can be any of the following: an instant messaging interface; a travel planning interface; or a service evaluation interface.

17. The apparatus according to claim 15, characterized in that, The second information includes at least one of the following: Reply information used to respond to the first information; The travel itinerary planning information corresponding to the first piece of information; The service evaluation information corresponding to the first information; A notification message indicating that the first task has been executed; Task information corresponding to the first task; The warning information corresponding to the first piece of information.

18. The apparatus according to any one of claims 15-17, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes the first conversation message of the first contact. The first information is information entered by the user on the input method keyboard, and the first information is a question about at least part of the message content in the first conversation message; wherein, the question information is a complete question description, or the question information is at least part of the question keywords in the complete question description; The display module is specifically used to display reply information, which is used to reply to the question.

19. The apparatus according to any one of claims 15-17, characterized in that, When the first interface is a travel planning interface, the first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that indicates the generation of travel planning information for the travel destination. The display module is specifically used to display travel itinerary planning information for the travel destination; The travel planning information includes at least one of the following: route planning information for the travel destination; accommodation planning information for the travel destination; and sightseeing planning information for the travel destination.

20. The apparatus according to any one of claims 15-17, characterized in that, When the first interface is a service evaluation interface, the service evaluation interface includes the store identifier of the first store; The first information is the information entered by the user on the input method keyboard, and the first information is the task instruction information that instructs the generation of store evaluation information for the first store; The display module is specifically used to display the store review information of the first store.

21. The apparatus according to any one of claims 15-17, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes a second conversation message from a second contact; the second conversation message includes a description of the to-do item; the description of the to-do item includes: the content of the to-do item and the deadline for completion of the item; The first information is the information entered by the user on the input method keyboard, and the first information indicates the task instruction information for setting the first schedule reminder based on the second session message; The display module is specifically used to display the first prompt information and the first schedule reminder icon; Wherein, the first schedule reminder identifier is used to indicate the first schedule reminder; the first prompt information is used to indicate that the first schedule reminder corresponding to the description information of the to-do item has been set.

22. The apparatus according to any one of claims 15-17, characterized in that, When the first interface is an instant messaging interface, the instant messaging interface includes a third conversation message from a third contact; the third conversation message includes an instruction message requiring the user to send authentication credential information. The first information is the information entered by the user on the input method keyboard, and the first information includes authentication credential information; The display module is specifically used to display a first warning message, which is used to warn the user to avoid sending the authentication credential information.

23. The apparatus according to claim 15, characterized in that, The information display device also includes a processing module; The processing module is used to determine, in the case that the first reference information includes a trigger word, the intention to call AI capabilities before displaying the second information corresponding to the first information on the first interface. The first reference information includes at least one of the following: first information; interface context information of the first interface; and, upon determining that an intention to invoke AI capabilities has been identified, outputting second information through the AI ​​assistant. The trigger word is used to trigger the AI ​​assistant to obtain the second information.

24. The apparatus according to claim 15 or 23, characterized in that, The first interface includes an input method keyboard and an AI icon, wherein the AI ​​icon is used to trigger the AI ​​assistant to perform a first task and display second information based on the first information; The receiving module is further configured to receive the user's selection input for the AI ​​identifier before displaying the second information corresponding to the first information on the first interface; The aforementioned display module is specifically used to respond to the selection input received by the receiving module and display second information corresponding to the first information on the first interface.

25. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the information display method as described in any one of claims 1 to 14.

Images