Quick input method, device and storage medium

Abstract

The application provides a quick input method, device and storage medium. In the method, a user does not need to input a prompt, and according to a currently displayed user interface and chat content selected by the user in the user interface, text information matched with a current application program, a business scenario and screen content can be quickly generated.

Description

Technical Field

[0001] This application relates to the field of terminal equipment technology, and in particular to a quick input method, device and storage medium. Background Technology

[0002] With the development of computer technology, electronic devices such as mobile phones and tablets are becoming increasingly popular, and these devices support more and more functions. For example, users can use input method applications (hereinafter referred to as input methods) installed on electronic devices to input information, reply to messages, post comments, take notes, edit emails, and search for content, thus bringing great convenience to people's lives, studies, and work.

[0003] Currently, to facilitate users' quick information input, input methods offer predictive text functionality (providing suggested words based on the preceding text). For example, when a user inputs "you," it might suggest words like "we" or "good," thus enabling users to input information quickly.

[0004] However, information quickly entered using predictive text is often only related to the preceding text and not to the application the user is currently using or the content they are viewing. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of this application provide a quick input method, device, and storage medium, aiming to enable the input method to automatically generate appropriate information based on the currently used application and the content displayed on the screen, thereby improving input efficiency and meeting user needs.

[0006] In a first aspect, embodiments of this application provide a quick input method applied to an electronic device. The method includes: displaying a first interface, the first interface including chat content and a text input box; after receiving a first operation, displaying a quick input control; after receiving a second operation on the quick input control, displaying a second interface, the second interface including a first selection box displaying the chat content; after receiving a third operation on the first selection box, displaying a quick content generation control and showing the chat content as selected; after receiving a fourth operation on the quick content generation control, displaying target chat content associated with the chat content; and after receiving a fifth operation on the target chat content, displaying the target chat content in the text input box.

[0007] The first interface can be understood as the user interface currently displayed on the screen of an electronic device. In this application, the first interface is, for example, interface 10f, interface 20f, or interface 30f as described in the following embodiments.

[0008] The text input box is used to display the entered text content. In this application, the text input box is, for example, the text input box 10f-1 described in the following embodiment.

[0009] The first operation can be a user operation performed on a text input box in the first interface, such as clicking the text input box 10f-1.

[0010] The first operation can also be a user operation that activates a voice assistant application. For details on user operations that activate a voice assistant application, please refer to the description section of the following embodiments; these will not be repeated here.

[0011] The shortcut input control can be either the shortcut input control 10f-3 described in the following embodiments, or control 10g-3.

[0012] The second interface can be interface 40f, or interface 40f', or interface 40f'", or interface 30g, as described in the following embodiments. For details regarding the specific implementation of the change of the electronic device's user interface from interface 10f to interface 40f, or interface 40f', or interface 40f'", or interface 30g, please refer to the description section of the following embodiments; these details will not be elaborated upon here.

[0013] The first selection box can be understood as... Figure 9b The message boxes M1', M2', etc., are displayed on the middle layer.

[0014] The third operation can be a user action applied to the select all control displayed on the second interface, such as the select all control 10f-6 or the select all control 10g-5. Understandably, when the third operation is applied to the select all control, all chat content displayed on the second interface can be selected with a single click.

[0015] The third action can also be a user action performed on the first selection box. That is, each time a user clicks on a first selection box on the second interface, it can be considered as triggering a third action.

[0016] The quick content generation control can be the answer generation control 10f-10 or the answer generation control 10g-7 described in the following embodiments.

[0017] The target chat content can include any or more of the following: text, images, and documents.

[0018] Therefore, without requiring users to input prompts, text information that matches the current application, business scenario, and screen content can be quickly generated based on the currently displayed user interface and the chat content selected by the user in that user interface.

[0019] According to the first aspect, after receiving a second operation on the shortcut input control, displaying a second interface includes: after receiving a second operation on the shortcut input control, taking a screenshot of the first interface to obtain a screenshot of the first interface; performing feature extraction on the screenshot of the first interface to extract the chat content and the message box information corresponding to the chat content included in the screenshot of the first interface; overlaying the screenshot of the first interface on the first interface; and adding a mask on the screenshot of the first interface based on the chat content and the message box information corresponding to the chat content to obtain the second interface.

[0020] The first screenshot refers to a full-screen screenshot of the first interface. For example, if the first interface is at 30fps, the first screenshot can be understood as a full-screen screenshot of interface 30fps.

[0021] For example, the message box is Figure 9b The message boxes M1, M2, etc. in the screenshot corresponding to interface 30f.

[0022] The message box information may include the coordinates of the message box, the user's avatar, nickname, etc.

[0023] Adding a mask to the first screenshot can be understood as adding a layer with a certain degree of transparency to the first screenshot.

[0024] For specific implementation details in this regard, please refer to the following embodiments. Figure 9b The description of that part will not be elaborated here.

[0025] Based on the first aspect, or any implementation of the first aspect above, a mask is added to the first interface screenshot according to the chat content and the corresponding message box information, including: adding a layer to the first interface screenshot, the layer having a certain transparency; drawing a first selection box on the layer according to the message box information corresponding to the chat content; and displaying the corresponding chat content in the first selection box.

[0026] The first selection box drawn is, for example, Figure 9b The message boxes M1', M2', etc. are shown in the image.

[0027] For specific implementation details in this regard, please refer to the following embodiments. Figure 9b The description of that part will not be elaborated here.

[0028] According to the first aspect, or any implementation of the first aspect above, the method further includes: after receiving the fourth operation on the quick content generation control, constructing a prompt based on the chat content in the selected state and the page features of the first interface extracted from the screenshot of the first interface; and generating the target chat content based on the prompt.

[0029] The constructed prompts include user prompts and system prompts.

[0030] Among them, page features are used to determine the application information of the application to which the first interface belongs, as well as the corresponding business scenario.

[0031] For specific implementation details in this regard, please refer to the description of steps S110 to S13, or steps S210 to S213, or steps S310 to S313, or steps S408 to S411 in the following embodiments, which will not be repeated here.

[0032] Based on the first aspect, or any implementation of the first aspect above, a prompt is constructed based on the chat content in the selected state and the page features of the first interface extracted from the screenshot of the first interface. This includes: preprocessing the chat content and page features to obtain a preprocessing result; performing intent recognition processing on the preprocessing result to determine the user intent; constructing a first prompt based on the preprocessing result and the user intent, the first prompt being used to identify the topic of the target chat content to be generated; and constructing a second prompt based on the user intent and page features, the second prompt being used to indicate the creation type corresponding to the target chat content to be generated.

[0033] The first prompt can be understood as the user prompt mentioned in the following embodiments, and the second prompt can be understood as the user prompt mentioned in the following embodiments.

[0034] For specific implementation details of this aspect, please refer to the description of step S111, or step S211, or step S311, or step S409 in the following embodiments, which will not be repeated here.

[0035] According to the first aspect, or any implementation of the first aspect above, the target chat content is generated based on the prompt, including: generating target chat content that matches the theme identified by the first prompt and whose creation type is the creation type indicated by the second system prompt word, based on the first prompt and the second prompt.

[0036] Based on the first aspect, or any implementation of the first aspect above, the chat content and page features are preprocessed to obtain preprocessing results, including: deleting sensitive information in the chat content and deleting sensitive information in the page features; or, replacing sensitive information in the chat content and replacing sensitive information in the page features.

[0037] For specific implementation details regarding this aspect, please refer to the description of the desensitization processing of chat content and page features in step S111, or step S211, or step S311, or step S409 in the following embodiments, which will not be elaborated here.

[0038] According to the first aspect, or any implementation of the first aspect above, the first input operation is a user operation that wakes up the voice assistant application.

[0039] For example, user actions to wake up a voice assistant application, such as pressing and holding the power button for 1 second, or using a set voice wake-up word to wake up the voice assistant application.

[0040] According to the first aspect, or any implementation of the first aspect above, after receiving the first operation, displaying a shortcut input control includes: after receiving the first operation, displaying an operation window corresponding to the voice assistant application on a first interface, the operation window including the shortcut input control.

[0041] The first interface displays the operation window corresponding to the voice assistant application, such as window 10g-2 as described in the following embodiment.

[0042] Regarding the form of the operation window and the shortcut input control in this regard, please refer to the window 10g-2 and control 10g-3 shown in the following embodiments.

[0043] According to the first aspect, or any of the above implementations of the first aspect, the second interface also includes a select all control, and the third operation on the first selection box is an operation performed on the select all control.

[0044] For example, the second interface in this aspect is, for example, interface 40f, or interface 40f', or interface 40f", or interface 30g as described in the following embodiments.

[0045] Accordingly, the select all control is, for example, select all control 10f-6 or select all control 10g-5.

[0046] For specific implementation details in this regard, please refer to the following embodiments. Figure 8a Middle (4), or Figure 10 Middle (2), or Figure 12 Middle (2), or Figure 14 The description of (3) will not be repeated here.

[0047] According to the first aspect, or any implementation of the first aspect above, the first operation is a user operation applied to the text input box; after receiving the first operation, displaying a shortcut input control includes: after receiving the first operation, displaying the keyboard corresponding to the input method application on the first interface, and displaying the shortcut input control in the area corresponding to the keyboard.

[0048] For specific implementation details in this regard, please refer to Figure 8a Middle (1) to Figure 8aThe description of (3) will not be repeated here.

[0049] According to the first aspect, or any of the above implementations of the first aspect, the second interface also includes a quick input window, which includes a select all control, and the third operation on the first selection box is an operation performed on the select all control.

[0050] For example, the second interface in this aspect is, for example, interface 40f, or interface 40f', or interface 40f as described in the following embodiments.

[0051] Accordingly, the quick input window is, for example, W1 as described in the following embodiments.

[0052] Correspondingly, the select all control is, for example, the select all control 10f-6.

[0053] For specific implementation details in this regard, please refer to Figure 8a The description of (4) will not be repeated here.

[0054] Based on the first aspect, or any of the implementation methods of the first aspect above, the quick input window is a floating window.

[0055] According to the first aspect, or any implementation of the first aspect above, the quick input window also includes a prompt input box, which is used for the user to input a prompt; wherein, after the prompt entered by the user is displayed in the prompt input box, a quick content generation control is displayed.

[0056] The prompt input box is, for example, the prompt input box 10f-14 described in the following embodiments.

[0057] The prompt input box that displays the prompt input by the user is, for example, the prompt input box 10f-14' described in the following embodiments. Correspondingly, the quick content generation control that is displayed is, for example, the answer generation control 10f-10 displayed in interface 50f'.

[0058] For specific implementation details in this regard, please refer to Figure 10 Zhong (2) and Figure 10 The description of (3) will not be repeated here.

[0059] According to the first aspect, or any of the implementations of the first aspect above, the quick input window also includes a text style selection control, which is used to allow users to select the expression style of the target chat content.

[0060] The text style selection control is, for example, the text style selection control 10f-15 or text style selection control 10f-15' described in the following embodiments.

[0061] For specific implementation details in this regard, please refer to Figure 12 The description of that part will not be repeated here.

[0062] Secondly, embodiments of this application provide an electronic device. The electronic device includes: a memory and a processor, the memory and the processor being coupled; the memory stores program instructions, which, when executed by the processor, cause the electronic device to perform the methods of the first aspect or any possible implementation thereof.

[0063] Thirdly, embodiments of this application provide a computer-readable medium for storing a computer program, the computer program including instructions for performing the method in the first aspect or any possible implementation of the first aspect.

[0064] Fourthly, embodiments of this application provide a computer program including instructions for performing the method in the first aspect or any possible implementation thereof.

[0065] Fifthly, embodiments of this application provide a chip including a processing circuit and transceiver pins. The transceiver pins and the processing circuit communicate with each other via an internal connection path. The processing circuit executes the method in the first aspect or any possible implementation of the first aspect to control the receiving pin to receive signals and to control the transmitting pin to transmit signals. Attached Figure Description

[0066] Figure 1 This is a schematic diagram illustrating a scenario of quick input;

[0067] Figure 2a and Figure 2b This is an illustrative diagram illustrating yet another example of a quick input method.

[0068] Figure 3 This is an illustrative diagram illustrating yet another example of a quick input method.

[0069] Figure 4 This is an illustrative diagram illustrating yet another example of a quick input method.

[0070] Figure 5 This is an illustrative diagram illustrating yet another example of a quick input method.

[0071] Figure 6 This is a schematic diagram of the hardware structure of an electronic device as an example.

[0072] Figure 7 A schematic diagram illustrating the software structure of an electronic device as an example;

[0073] Figure 8a and Figure 8b This is an illustrative diagram illustrating yet another example of a quick input method.

[0074] Figure 9a One implementation is shown as an example. Figure 8a and Figure 8b A timing diagram of the shortcut input method in the scenario shown;

[0075] Figure 9b This is an example of setting a mask on an interface;

[0076] Figure 10 This is an illustrative diagram illustrating yet another example of a quick input method.

[0077] Figure 11 One implementation is shown as an example. Figure 10 A timing diagram of the shortcut input method in the scenario shown;

[0078] Figure 12 This is an illustrative diagram illustrating yet another example of a quick input method.

[0079] Figure 13 One implementation is shown as an example. Figure 12 A timing diagram of the shortcut input method in the scenario shown;

[0080] Figure 14 This is an illustrative diagram illustrating yet another example of a quick input method.

[0081] Figure 15 One implementation is shown as an example. Figure 14 A timing diagram illustrating the shortcut input method for the scenario shown. Detailed Implementation

[0082] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0083] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0084] The terms "first" and "second," etc., used in the specification and claims of this application are used to distinguish different objects, not to describe a specific order of objects. For example, "first target object" and "second target object," etc., are used to distinguish different target objects, not to describe a specific order of target objects.

[0085] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0086] In the description of the embodiments in this application, unless otherwise stated, "multiple" means two or more. For example, multiple processing units means two or more processing units; multiple systems means two or more systems.

[0087] With the development of computer technology, electronic devices such as mobile phones and tablets are becoming increasingly popular, and these devices support more and more functions. For example, they can support the use of instant messaging applications, video applications, live streaming applications, short video applications, shopping applications, and games, thus bringing great convenience to people's lives, studies, and work.

[0088] Currently, users frequently use input methods every day, such as replying to messages and posting on social media in instant messaging applications (hereinafter referred to as "applications"), posting bullet comments and comments in video applications, live streaming applications, and short video applications, and searching for product names in shopping applications.

[0089] To facilitate quick information input using the input method, some embodiments of this application provide a predictive text function (providing suggested context based on the preceding text). To better understand the predictive text function, the following will be combined with... Figure 1 The scenario shown will be explained.

[0090] See Figure 1 In (1), (2), and (3), the chat interface between a user account (e.g., Li Si) and his friend Zhang San is shown. Understandably, interfaces 10a, 20a, and 30a are all chat interfaces between the user and Zhang San, except that interfaces 10a, 20a, and 30a correspond to the chat interfaces when the user inputs different content using the input method.

[0091] See Figure 1In (1), for example, in a scenario where a user receives a message sent by Zhang San, such as "You can get off work soon. Have a nice weekend", and is about to use the input method to reply to Zhang San with "You too". When the user operates on the character blocks in the keyboard area and enters "You" in the text input box 10a-1, the associated area 10a-2 of the input method will display the following texts associated with "You", such as "men", "hao", "de", "shi", "shuo", "zai", "jiu", "jia". If the user wants to reply to Zhang San with "You too", they need to continue to operate on the character blocks in the keyboard input area, such as successively clicking on the "WXYZ" character block and the "DEF" character block in the keyboard input area of interface 10a.

[0092] Correspondingly, in response to this user operation, the text displayed in the associated area 10a-2 will be updated to the text displayed in the associated area 10a-2' in interface 20a, such as "ye", "yie shi", "ye", "ye", "ye", "ye", "ye".

[0093] See Figure 1 In (2), for example, when the user clicks on "yie shi" displayed in the associated area 10a-2', in response to this user operation, the selected text "yie shi" will appear in the text input box. That is, the text displayed in the text input box 10a-1 shown in interfaces 10a and 20a will be updated to the text displayed in the text input box 10a-1' in interface 30a.

[0094] In addition, when the text displayed in the text input box 10a-1 is updated to the text displayed in the text input box 10a-1', taking "shi" as the previous text, the following texts related to "shi" will be displayed in the associated area. For example Figure 1 As shown in (3), when the chat interface is updated from interface 20a to interface 30a, the associated area will be updated from the associated area 10a-2' shown in interface 20a to the associated area 10a-2" shown in interface 30a, and the displayed text (content) is, for example, ",", "ge", "o", "a", "ma", "ya", "de", "wo".

[0095] For example, if a user only wants to reply with "You too," after the chat interface updates to interface 30a, the user can click the "Send" button displayed in interface 30a to send the message "You too" to Zhang San. Zhang San's chat interface will then display the sent message. While this method speeds up information input, eliminating the need for word-by-word typing, information input via predictive text is often only related to the preceding text and not to the application or content the user is currently viewing. Therefore, it fails to meet the diverse needs of information development and user usage.

[0096] It should be understood that, Figure 1 The scenario shown for quickly inputting information uses the example of providing related following text content based on the preceding input. In practical applications, the related following text could also be images, documents, etc.

[0097] To meet the diverse needs of information and enable input methods to better satisfy user demands, in some embodiments of this application, the input method provides an intelligent assistant. For example, when content needs to be entered, the user can select a suitable creation type and / or enter a prompt describing the content summary, thereby using the input method's built-in Artificial Intelligence (AI) model to quickly generate the content to be edited.

[0098] See Figure 2a and Figure 2b This example illustrates a scenario where an input method-based intelligent assistant (local intelligent assistant) allows for quick information input.

[0099] It should be noted that, Figure 2a and Figure 2b Interfaces 10b to 100b shown can be understood as a series of SMS editing interfaces (or SMS chat interfaces) involved in the process of a user sending an SMS message to Zhang San using an SMS application.

[0100] See Figure 2a In example (1), when the user does not operate the character block of the keyboard input area in interface 10b to edit text, the text input box 10b-1 in interface 10b does not display text content, but only the jumping input cursor.

[0101] See also Figure 2a In example (1), when a user clicks the smart assistant control 10b-2 provided by the input method in interface 10b, the mobile phone responds to the user's operation, and the mobile phone's user interface will be updated from interface 10b to interface 10b. Figure 2aThe interface 20b shown in (2) is as follows. For example, the area displaying the smart assistant control 10b-2 may contain one or more of the following: creation type selection control 10b-3, close smart assistant control 10b-4, prompt display area 10b-5, smart text generation control 10b-6, etc.

[0102] See also Figure 2a In example (2), the area where the creation type selection control 10b-3 is located displays "AI Assisted Writing" and the currently selected creation type, such as "Greeting".

[0103] It should be noted that in some embodiments of this application, the smart assistant function is enabled by default. For example, after the user clicks the smart assistant control 10b-2, the selected creation type displayed in the area where the creation type selection control 10b-3 is located is "Greeting Type". That is, the default creation type is "Greeting Type".

[0104] See also Figure 2a In example (2), when a user clicks to close the smart assistant control 10b-4, the phone responds to the user's action by closing the smart assistant function. Accordingly, the phone's user interface will revert from interface 20b to interface 10b.

[0105] See also Figure 2a In example (2), when a user clicks the creation type selection control 10b-3, the phone responds to the user's action by popping up the creation type selection window 10b-7 on the current screen. That is, the phone's user interface will be updated from screen 20b to... Figure 2a Interface 30b is shown in (3).

[0106] See Figure 2a In (3), for example, the creation type selection window 10b-7 may include one or more creation type options, such as greeting options, friend activity options, daily post options, script options, plant recommendation options, evaluation options, free writing options, speech options, meeting minutes options, email options, self-introduction options, praise options, polishing and rewriting options, writing outline options, group notification options, brainstorming options, naming options, advertising slogan options, etc.

[0107] See also Figure 2a In example (3), after a user clicks the praise option, the phone responds to the user's action by switching the praise option to the selected state and the greeting option to the unselected state, such as... Figure 2aAs shown in interface 40b in (4). That is, the creation type selection window 10b-7 shown in interface 30b of the current interface is updated to the creation type selection window 10b-7' shown in interface 40b. Among them, for creation type selection window 10b-7', the border of the praise option is, for example, bolded and / or highlighted, while other options are not bolded and / or highlighted.

[0108] See Figure 2a In example (4), when a user clicks the "Cancel" control provided in the creation type selection window 10b-7', the phone responds to the user's operation by closing the creation type selection window 10b-7' and deselecting the praise option. The current creation type remains the default creation type, such as "Greeting type". Alternatively, the previously selected creation type is retained. For example, if the selected creation type displayed in the area where the creation type selection control 10b-3 is located is "Friends' Moments", when the user clicks the praise option in the creation type selection window and then clicks the "Cancel" control, the phone responds to the user's operation by closing the creation type selection window. The selected creation type displayed in the area where the creation type selection control 10b-3 is located remains "Friends' Moments".

[0109] See also Figure 2a In example (4), when a user clicks the "OK" control provided in the creation type selection window 10b-7', the phone responds to the user's operation by updating the creation type to the type corresponding to the option selected by the user in the creation type selection window 10b-7', such as "Praise Type," and then closes the creation type selection window 10b-7'. That is, in this case, after closing the creation type selection window 10b-7', the selected creation type displayed in the area where the creation type selection control 10b-3 is located will be updated from "Greeting" to... Figure 2a In the interface 50b shown in (5), the area containing the creation type selection control 10b-3' displays "Praise".

[0110] Accordingly, the content displayed in the prompt area will also change depending on the selected creation type. For example, when the creation type is "Greeting type", the content displayed in prompt area 10b-5 will be "Greetings to a long-lost friend". When the creation type is updated to "Praise type", the content displayed in prompt area 10b-5' will be "Praise to an old friend".

[0111] It should be noted that the content displayed by default in the prompt display area is not the prompt entered by the user, but rather a prompt message given to the user before the user enters a prompt. In other words, it is information that instructs the user to enter a prompt.

[0112] For example, in the character block of the keyboard area in the user interface 50b, after entering a prompt such as "confident" or "brave" in the prompt display area 10b-5', the prompt display area 10b-5' will display the prompt entered by the user, such as... Figure 2b The prompt display area 10b-5” in the interface 60b shown in (1) is shown.

[0113] See Figure 2b In example (1), when the prompts “confident” and “brave” are displayed in the prompt display area 10b-5, if the user clicks the smart text generation control 10b-6, the mobile phone responds to the user’s operation and automatically generates text content based on the creation type selected by the user and the prompt entered.

[0114] For example, in some embodiments of this application, in order to display automatically generated text content, after receiving a user operation on the intelligent text generation control 10b-6, the content displayed in the area below the text input box 10b-1 in the interface 60b will change Figure 2b The content displayed in the area below the text input box 10b-1 in the interface 70b shown in (2).

[0115] See Figure 2b In example (2), the content displayed in the area below the text input box 10b-1 in interface 70b may include one or more of the following: back control 10b-8, close smart assistant control 10b-4, smart assistant operation area 10b-9. Among them, the smart assistant operation area 10b-9 may include one or more of the following: smart text input box 10b-91, smart text editing control 10b-92, smart text style selection control 10b-93, smart text switching control 10b-94, smart text switching control 10b-95, smart text refresh control 10b-96, smart text insertion control 10b-97.

[0116] See also Figure 2b In example (2), when the user interface of the mobile phone is interface 70b, when the user clicks to close the smart assistant control 10b-4, the mobile phone responds to the user's operation, closes the smart assistant function, and the user interface will also be restored from interface 70b to interface 10b.

[0117] See also Figure 2b In example (2), when a user clicks the back control 10b-8, the mobile phone responds to the user's operation by displaying interface 60.

[0118] See also Figure 2bIn example (2), the smart text input box 10b-91 displays the text content generated based on the selected style displayed in the area where the smart text style selection control 10b-93 is located.

[0119] See also Figure 2b In example (2), when there are multiple automatically generated text contents based on the user's selected creation type and input prompt, the user clicks the smart text refresh control 10b-96, and the mobile phone responds to the user's operation by refreshing the text content displayed in the smart text input box 10b-91. For example, the content displayed in the smart text input box 10b-91 in interface 70b, "You are always full of confidence and courage, and never back down when facing difficulties. This is really amazing.", can be refreshed to... Figure 2b The content displayed in the intelligent text input box 10b-91' of the interface 80b shown in (3) is: "Courage is a sturdy boat that allows you to raise the sails of confidence, cross the turbulent river, and sail to the other side of success."

[0120] In addition, it should be noted that when there are multiple automatically generated text contents based on the user's selected creation type and input prompt, and the text content currently displayed in the smart text input box is the first one, the smart text toggle control 10b-94 can be set to gray, which is an unavailable state, while the smart text toggle control 10b-95 is set to an available state, as shown in interface 70b.

[0121] See also Figure 2b In example (2), when a user clicks the smart text switching control 10b-95, the mobile phone responds to the user's operation and can refresh the text content displayed in the smart text input box 10b-91, such as refreshing the content displayed in the smart text input box 10b-91 in the interface 70b to the content displayed in the smart text input box 10b-91'.

[0122] For example, if the content displayed in the smart text input box 10b-91' matches the last text content of the current creation type and prompt, then the smart text toggle control 10b-95 is grayed out and set to an unavailable state, as shown in interface 80b as smart text toggle control 10b-95'. Correspondingly, the smart text toggle control 10b-94 is set to an available state, as shown in interface 80 as smart text toggle control 10b-94'.

[0123] Furthermore, it should be noted that when the user clicks the smart text generation control 10b-6 and the smart assistant operation area 10b-9 appears on the current interface, the text content displayed in the smart text input box 10b-91 (or smart text input box 10b-91') is not editable by default. In this case, when the user clicks the smart text editing control 10b-92, the phone responds to the user's operation, and the text content displayed in the smart text input box 10b-91 (or smart text input box 10b-91') will switch to an editable state. For example, at the location clicked by the user, the cursor will appear at that location, and the keyboard corresponding to the input method will be brought up.

[0124] For example, in some embodiments of this application, the text content displayed in the smart text input box 10b-91 (or smart text input box 10b-91') will be switched to an editable state. After the keyboard corresponding to the input method is pulled up, the smart assistant operation area 10b-9 displayed in the current interface, as well as the content above the smart assistant operation area 10b-9, can be pushed up by the keyboard.

[0125] For example, in some other embodiments of this application, the text content displayed in the smart text input box 10b-91 (or smart text input box 10b-91') will be switched to an editable state. After pulling up the keyboard corresponding to the input method, the smart assistant operation area 10b-9 can float on the interface 60b in the form of a floating window.

[0126] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0127] See Figure 2b In example (3), taking the user clicking the smart text insertion control 10b-97 in interface 80b as an example, after the user clicks the smart text insertion control 10b-97, the mobile phone responds to the user's operation by copying and pasting the text content displayed in the smart text input box 10b-91' into the text input box 10b-1, and turning off the smart assistant function. That is, interface 80b can be updated to Figure 2b Interface 90b is shown in (4).

[0128] For example, if the text input box 10b-1' in interface 90b displays text content generated by the smart assistant, such as "Courage is a sturdy boat that lets you raise the sails of confidence, cross the turbulent river, and sail to the shore of success.", and the user clicks the send control 10b-10, the mobile phone will respond to the user's operation and send the text content displayed in the text input box 10b-1' to Zhang San as an SMS message.

[0129] Understandably, after the text message is successfully sent, the message content will appear in the text message chat interface between the user and Zhang San (not shown in the figure).

[0130] See also Figure 2b In example (2), when a user clicks the smart text style selection control 10b-93, the mobile phone responds to the user's operation and can display, as shown in the example (2). Figure 2b Interface 100b is shown in (5).

[0131] See Figure 2b In example (5), interface 100 may include text style selection windows 10b-11, and all content in interface 70b. Text style selection windows 10b-11 may include one or more text style options, such as automatic style, formal style, humorous style, literary style, etc. This embodiment of the application assumes that the selected text style is automatic by default.

[0132] This allows the system to generate text content related to the current creation type and the prompt based on the user's input and the selected creation type, thus facilitating quick information input for the user.

[0133] It should be understood that, Figure 2a ,as well as Figure 2b The scenario shown illustrates quick information input, using the Smart Assistant control 10b-2 to trigger the quick generation of text content as an example. In practical applications, controls for triggering the quick generation of images, documents, etc., can also be provided. Alternatively, the Smart Assistant control 10b-2 can be directly configured to trigger the quick generation of one or more of the following attributes: text content, images, and documents, to better meet the user's actual needs.

[0134] See Figure 3 This example illustrates a scenario where information can be quickly entered based on a global intelligent assistant.

[0135] It should be noted that, compared to Figure 2a and Figure 2b In the illustrated embodiment, the intelligent assistant is integrated into the keyboard corresponding to the input method (hereinafter referred to as: local intelligent assistant, which can be used when displaying the keyboard corresponding to the input method). Figure 3 The smart assistant in the illustrated embodiment is not integrated into the keyboard corresponding to the input method (hereinafter referred to as: global smart assistant, that is, it can be invoked and used on any interface).

[0136] Furthermore, it should be noted that in scenarios where the global intelligent assistant is used for quick information input, it can trigger the generation of text content, images, or documents. That is, in... Figure 1 , Figure 2a , Figure 2b The interface shown also allows for triggering quick access to text content, and / or images, and / or documents based on the global intelligent rental and sales system. However, the global intelligent assistant does not require a dedicated setting for display in the keyboard area.

[0137] For ease of explanation, this application embodiment takes the generation of an image triggered by a global intelligent assistant as an example.

[0138] In addition, it should be noted that Figure 3 Interfaces 10c to 60c shown can be understood as a series of SMS editing interfaces (or SMS chat interfaces) involved in the process of a user sending an SMS message to Petter using the SMS application.

[0139] See Figure 3 In example (1), after receiving a text message from Petter, the user can press and hold the power button for 1 second or speak the voice wake-up word of the global smart assistant to further confirm with Petter. In response to the user's action, the phone will activate the global smart assistant and display the global smart assistant operation window 10c-3 on the current interface. That is, the phone's user interface will change from interface 10c to... Figure 3 Interface 20c is shown in (2).

[0140] See Figure 3 In (2), for example, the global intelligent assistant operation window 10c-3 may include one or more of the following: prompt information displayed in the dashed box 10c-31, voice input control 10c-32, image input control 10c-33, intelligent information generation control 10c-34, etc.

[0141] The prompt information displayed within the dashed box 10c-31 can be information prompting the user to trigger an operation. In actual use, the prompt information within the dashed box 10c-31 can be any content that can be set, and is not limited to the content displayed in interface 20b.

[0142] It should be noted that the dotted line displayed in the global intelligent assistant operation window 10c-3 is for illustration only. That is, in actual use, the dotted frame 10c-31 is not displayed in the global intelligent assistant operation window 10c-3; instead, the prompt information is displayed directly in that area.

[0143] Furthermore, it should be noted that the dashed lines shown in other schematic diagrams of this application's embodiments are for illustrative purposes only. That is, they are not displayed in actual use.

[0144] The voice input control 10c-32 is used to trigger voice acquisition operations. That is, after the user operates the voice input control 10c-32, the mobile phone calls the audio module to acquire voice data.

[0145] The image input control 10c-33 is used to trigger the image acquisition operation. That is, after the user operates the image input control 10c-33, the mobile phone calls the camera to acquire an image.

[0146] See also Figure 3 In section (2), for example, when a user clicks the voice input control 10c-32, the mobile phone responds to the user's operation by calling the audio module. Taking the called audio module as an example, after the voice data is collected through the microphone, the mobile phone can perform voice-to-text processing on the voice data to obtain the corresponding text content, and display the obtained text content in the global intelligent assistant operation window 10c-3. For example, the obtained text content is displayed in the dashed box 10c-35 in the global intelligent assistant operation window 10c-3, for details please refer to Figure 3 The global intelligent assistant operation window 10c-3 is displayed on the interface 30c in the middle (3).

[0147] See Figure 3 In example (3), when the text content obtained from speech-to-text processing is displayed in the dashed box 10c-35, after the user clicks the intelligent information generation control 10c-34, the mobile phone responds to the user's operation and can display... Figure 3 The interface 40c shown in (4) is as follows. That is, the global smart assistant operation window 10c-3 can be transformed into the global smart assistant operation window 10c-3'.

[0148] See Figure 3 In example (4), the global intelligent assistant operation window 10c-3' displays images related to the text content displayed within the dashed box 10c-35, such as images A, B, C, and D shown in interface 40c. Among them, images A, B, C, and D are different images, but all include elements related to the text content displayed within the dashed box 10c-35.

[0149] Furthermore, it should be noted that in some embodiments of this application, after the user clicks the intelligent information generation control 10c-34, the prompt information displayed in the dashed box 10c-31 can be adaptively changed according to the text content displayed in the dashed box 10c-35. For example, if "Create image of tennis with pickles." is displayed in the dashed box 10c-35, the prompt information displayed in the dashed box 10c-31 can be updated to the prompt information in the dashed box 10c-31', indicating that the completed operation was based on the user's instruction (the text content in the dashed box 10c-35).

[0150] See also Figure 3 In example (4), the global smart assistant operation window 10c-3' may also include control 10c-36 (which generates more images related to the prompt after being triggered) and sharing control 10c-37.

[0151] It should be noted that when the global smart assistant operation window 10c-3' is displayed, the keyboard corresponding to the input method is collapsed (or hidden). Therefore, to better meet user needs, the keyboard input control 10c-38 can also be displayed in the global smart assistant operation window 10c-3'. When the user clicks the keyboard input control 10c-38, the phone responds to the user's action by pulling up the keyboard corresponding to the input method.

[0152] See also Figure 3 In example (4), when the user clicks on the image 10c-39 (i.e. image D) displayed in the global smart assistant operation window 10c-3', image 10c-39 will be selected. For example, the image 10c-39 shown in the global smart assistant operation window 10c-3' will be updated to the image 10c-39' shown in the global smart assistant operation window 10c-3".

[0153] See Figure 3 In section (5), for example, when a user clicks the share control 10c-37, the phone responds to the user's action by adding the user-selected image 10c-39 to the text input box 10c-1 and disabling the global smart assistant. For example, the phone's user interface will be updated from interface 50c to... Figure 3 Interface 60c is shown in (6).

[0154] The interface and operations involved in adding image 100c-39 to text input box 10c-1 after clicking the share control 10c-37 can be found in the operation logic of the share entry provided by the application that supports sharing function installed on the current mobile phone, and will not be described in detail here.

[0155] For example, a text input box that displays image 10c-39 (such as a thumbnail) can be as follows: Figure 3 In (6), the text input box 10c-1' is shown.

[0156] For example, in some embodiments of this application, to facilitate user operation, when image 10c-39 is displayed in text input box 10c-1', a delete control 10c-4 can also be displayed in the upper right corner of image 10c-39. When the user clicks the delete control 10c-4, the mobile phone responds to the user's operation by deleting image 10c-39 from text input box 10c-1', meaning text input box 10c-1' will revert to text input box 10c-1.

[0157] For example, when a user clicks the send control 10c-2 in interface 60c, the mobile phone responds to the user's operation by sending the image 10c-39 displayed in the text input box 10c-1' to Petter.

[0158] Understandably, after the message is successfully sent, the image (not shown in the image) will appear in the user's text message chat interface with Petter.

[0159] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended to be the sole limitation of this embodiment. In practical applications, when image 10c-39 is displayed in text input box 10c-1', the user can also operate the keyboard to input text content in text input box 10c-1', or switch out the global intelligent assistant again to quickly generate text content based on the global intelligent assistant, and then copy the generated text content into text input box 10c-1'. During the process of quickly generating text content based on the global intelligent assistant, user commands (the text content displayed in the dashed box 10c-35) can, for example, indicate that the content to be generated is text content. Other implementation details can be found in [reference needed]. Figure 3 The description of the illustrated embodiment will not be repeated here.

[0160] Therefore, based on the global intelligent assistant, content related to the prompt can be quickly generated by inputting a simple prompt.

[0161] See Figure 4 This example illustrates another type of global intelligent assistant, providing a scenario for quick information input.

[0162] For ease of explanation, this application's embodiment only uses the generation of text content triggered by a global intelligent assistant as an example. In practical applications... Figure 4 The scenario shown can also generate images and / or documents based on the global intelligent assistant.

[0163] It should be noted that, Figure 4 The interfaces 10d to 30d shown can be understood as the user interface involved in using the global intelligent assistant when a user is using a video application and watching a video.

[0164] See Figure 4 In example (1), when a user clicks on the discussion content editing area 10d-1 while viewing a sports event, the mobile phone responds to the user's operation by popping up the discussion content editing window 10d-2 on the current screen, as shown in the example. Figure 4 The interface 20d shown in (2) is shown in the middle.

[0165] For example, when the phone's user interface is interface 20d, after the user activates the global smart assistant or the phone automatically activates the global smart assistant, the phone's user interface will display the global smart assistant operation window 10d-3. That is, the phone's user interface will update from interface 20d to... Figure 4 Interface 30d is shown in (3).

[0166] See Figure 4 In (3), for example, the global intelligent assistant operation window 10d-3 may include one or more of the following: prompt information displayed in the dashed box 10d-31, voice input control 10d-32, image input control 10d-33, intelligent information generation control 10d-34, etc.

[0167] For example, in some embodiments of this application, the controls in the global intelligent assistant operation window 10d-3 are the same as those in the global intelligent assistant operation window 10c-3. For details regarding the purpose of each control in the global intelligent assistant operation window 10d-3, please refer to... Figure 3 The description of the global intelligent assistant operation window 10c-3 in the illustrated embodiment will not be repeated here.

[0168] See also Figure 4 In section (3), for example, when a user clicks the voice input control 10d-32, the mobile phone responds to the user's operation by calling the audio module. Taking the microphone as the audio module being called, after the voice data is collected through the microphone, the mobile phone can perform voice-to-text processing on the voice data to obtain the corresponding text content, and display the obtained text content in the global intelligent assistant operation window 10d-3. For example, the obtained text content is displayed in the dashed box 10d-35 in the global intelligent assistant operation window. For details, please refer to [link to relevant documentation]. Figure 4 The global smart assistant operation window 10c-3' is displayed on the interface 40d in the middle (4).

[0169] See Figure 4In example (4), when the text content obtained from speech-to-text processing is displayed in the dashed box 10d-35, after the user clicks the intelligent information generation control 10d-34, the mobile phone responds to the user's operation and can display... Figure 4 The interface 50d shown in (5) is as follows. That is, the global intelligent assistant operation window 10d-3' can be transformed into the global intelligent assistant operation window 10d-3".

[0170] See Figure 4 In (5), for example, the Global Smart Assistant Operation Window 10d-3” displays text content related to the text content displayed within the dashed box 10d-35.

[0171] See also Figure 4 In the example (5), the global smart assistant operation window 10d-3 may also include control 10d-36 (which is used to generate more text content related to the prompt after being triggered) and sharing control 10d-37.

[0172] It should be noted that when the global smart assistant operation window 10d-3” is displayed, the keyboard corresponding to the input method is collapsed (or hidden). Therefore, to better meet user needs, the keyboard input control 10d-38 can also be displayed in the global smart assistant operation window 10d-3”. When the user clicks the keyboard input control 10d-38, the phone will respond to the user's action by bringing up the keyboard corresponding to the input method.

[0173] See also Figure 4 In example (5), if a user clicks on the text content displayed in the global smart assistant operation window 10d-3, such as the second text content, and then clicks the share control 10d-37, the phone responds to the user's operation by adding the selected text content to the discussion content editing window and closing the global smart assistant. For example, the phone's user interface will update from interface 50d to... Figure 4 The interface 60d shown in (6) is as follows. That is, the discussion content editing window 10d-2 is updated to the style of the discussion content editing window 10d-2'.

[0174] For example, when the user interface of the mobile phone is interface 60d, the user clicks the "Publish" control in the discussion content editing window 10d-2', and the mobile phone responds to the user's operation and can publish the comment content to the discussion area of ​​interface 10d (not shown in the figure).

[0175] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the sole limitation of this embodiment. In practical applications, when the second text content copied from the global intelligent assistant operation window 10d-3” is displayed in the discussion content editing window 10d-2’, the user can also add other content in the discussion content editing window 10d-2’ based on the controls provided in the current interface (such as “image”, “emoticon”, “time mark”, “screenshot”, etc.) or the keyboard, and / or switch out the global intelligent assistant again to quickly generate an image based on the global intelligent assistant, and then copy the generated image into the discussion content editing window 10d-2’.

[0176] Therefore, based on the global intelligent assistant, content related to the prompt can be quickly generated by inputting a simple prompt.

[0177] See Figure 5 This example illustrates another type of global intelligent assistant, providing a scenario for quick information input.

[0178] For ease of explanation, this embodiment only uses the example of triggering the viewing of document content and generating corresponding text content based on a global intelligent assistant. In practical applications... Figure 5 The scenario shown can also be processed by a global intelligent assistant to identify and process the image and / or text content, and then provide a corresponding response.

[0179] It should be noted that, Figure 5 Interfaces 10e to 30e shown can be understood as the user interface involved in using the global intelligent assistant when a user is using a document application to view a PDF document.

[0180] See Figure 5 In example (1), when a user uses a document application to view a PDF (Portable Document Format) file, such as Pickleball document.pdf, after the user wakes up the global smart assistant or the phone automatically wakes up the global smart assistant, the current interface, such as interface 10e, can display the global smart assistant operation window 10e-1.

[0181] See also Figure 5 In example (1), the global smart assistant operation window 10e-1 may include a dashed box 10e-11, a voice input control 10e-13, an image input control 10e-14, a smart information generation control 10e-14, and the currently viewed file 10e-12.

[0182] For example, in some embodiments of this application, the controls in the global intelligent assistant operation window 10e-1, such as the dashed box 10e-11, the voice input control 10e-13, the image input control 10e-14, and the intelligent information generation control 10e-14, are the same as the corresponding controls in the global intelligent assistant operation window 10c-3. For details regarding the uses of the dashed box 10e-11, the voice input control 10e-13, the image input control 10e-14, and the intelligent information generation control 10e-14, please refer to [link / reference needed]. Figure 3 The description of the global intelligent assistant operation window 10c-3 in the illustrated embodiment will not be repeated here.

[0183] See also Figure 5 In example (1), when a user clicks the voice input control 10e-13, the mobile phone responds to the user's operation by calling the audio module. Taking the microphone as the called audio module, after the voice data is collected by the microphone, the mobile phone can perform voice-to-text processing on the voice data to obtain the corresponding text content, and display the obtained text content in the global intelligent assistant operation window 10e-1. For example, the obtained text content is displayed in the dashed box 10e-16 in the global intelligent assistant operation window. For details, please refer to [link to relevant documentation]. Figure 5 The global smart assistant operation window 10e-1' is displayed on the interface 20e in the middle (2).

[0184] See Figure 5 In example (2), when the text content obtained from speech-to-text processing is displayed in the dashed box 10e-16, the mobile phone responds to the user's operation by displaying the intelligent information generation control 10e-14 after the user clicks the control. Figure 5 The interface 30e shown in (3) is as follows. That is, the global smart assistant operation window 10e-1' can be transformed into the global smart assistant operation window 10e-1.

[0185] See Figure 5 In (3), for example, the Global Smart Assistant Operation Window 10e-1 displays text content related to the text content displayed within the dashed box 10e-16, which was found in the Pickleball document.pdf.

[0186] See also Figure 5 In (3), for example, the global smart assistant operation window 10e-1 can also include a sharing control 10e-18 and a copy control 10e-19.

[0187] It should be noted that when the global smart assistant operation window 10e-1” is displayed, the keyboard corresponding to the input method is collapsed (or hidden). Therefore, to better meet user needs, the keyboard input control 10e-17 can also be displayed in the global smart assistant operation window 10e-1”. When the user clicks the keyboard input control 10e-17, the phone will respond to the user's action by pulling up the keyboard corresponding to the input method.

[0188] See also Figure 5 In (3), for example, when a user clicks the share control 10e-18, the phone responds to the user's action by sharing the text content displayed in the dashed box 10e-11' to the target application, such as any application installed on the phone.

[0189] For example, when a user clicks the copy control 10e-19, the phone responds to the user's operation by copying the text content displayed in the dashed box 10e-11'. After the user opens the target application, they can paste the text content displayed in the dashed box 10e-11' to the target location using the paste operation.

[0190] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended to be the sole limitation of this embodiment. In practical applications, based on a global intelligent assistant, relevant images can also be found in a document and pasted into the target location.

[0191] Therefore, based on the global intelligent assistant, by inputting simple prompts, one can quickly find the target answer from the selected document.

[0192] pass Figure 2a , Figure 2b , Figure 3 , Figure 4 and Figure 5 As can be seen from the description of the illustrated embodiments, the content generated by the intelligent assistant is often only related to the creation type and / or prompts selected by the user, and the content viewed by the user in the app they are currently using still has poor relevance. That is, it cannot well meet the user's usage needs.

[0193] In view of this, the embodiments of this application provide a quick input method, which aims to enable the input method (which can be understood as a local entry point) or voice assistant (which can be understood as a global entry point) to automatically generate appropriate information based on the currently used application and the content displayed on the screen, thereby improving input efficiency and meeting user needs.

[0194] To better understand the technical solutions provided in the embodiments of this application, before describing the technical solutions of the embodiments of this application, the hardware structure of the electronic devices (e.g., mobile phones, tablets, touch-screen PCs, etc.) to which the embodiments of this application are applicable will first be described with reference to the accompanying drawings. For ease of explanation, Figure 6 Let's take a mobile phone as an example.

[0195] See Figure 6 The electronic device 100 may include: a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0196] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0197] See also Figure 6 For example, processor 110 may include one or more processing units, such as application processor (AP), modem, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, neural network processing unit (NPU), etc., which will not be listed here and this application does not limit them.

[0198] In some embodiments of this application, different processing units can be independent devices. That is, each processing unit can be considered as a processor. In other embodiments of this application, different processing units can also be integrated into one or more processors.

[0199] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0200] In addition, the processor 110 may also include one or more interfaces. These interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc., which will not be listed here, and this application does not impose any limitations on them.

[0201] In addition, the processor 110 may also include a memory for storing instructions and data. In some embodiments of this application, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0202] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to perform data storage.

[0203] The internal memory 121 can be used to store computer executable program code, which includes instructions. The processor 110 executes various functional applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121. The internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc. The data storage area may store data created during the use of the electronic device 100, etc. Furthermore, the internal memory 121 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0204] The wireless communication function of the electronic device 100 can be implemented through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor, and baseband processor.

[0205] like Figure 6 As shown, for example, the mobile communication module 150 can provide wireless communication solutions applied to the electronic device 100, including second-generation wireless telephone technology (2G), third-generation mobile communication technology (3G), fourth-generation mobile communication technology (4G), and fifth-generation mobile communication technology (5G).

[0206] It should be noted that, in some embodiments of this application, at least some functional modules of the mobile communication module 150 may be located in the processor 110.

[0207] In some other embodiments of this application, at least some functional modules of the mobile communication module 150 may be housed in the same device as at least some modules of the processor 110.

[0208] like Figure 6As shown, for example, the wireless communication module 160 can provide solutions for wireless communication applied to the electronic device 100, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc.

[0209] It should be noted that in some embodiments of this application, configuration information (which can be understood as a whitelist of applications) for applications supporting the quick input scheme provided in this application can be configured in the server. In this way, the electronic device 100 can communicate with the server via the mobile communication module 150 or the wireless communication module 160 to obtain the whitelisted applications from the server and store them locally in the electronic device 100, such as in the storage data area of ​​the internal memory 121. Thus, when the currently used application is a whitelisted application, the electronic device 100 can automatically and quickly input text content suitable for the current scenario based on the quick input method provided in this application.

[0210] In addition, it should be noted that the server storing the whitelisted applications can be a physical server or a motion server.

[0211] See also Figure 6 For example, the audio module 170 may include a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, etc.

[0212] The sensor module 180 may include pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, accelerometers, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, bone conduction sensors, etc., which will not be listed here, and this application does not limit them.

[0213] The camera 193 is used to capture still images or videos. The electronic device 100 can implement the shooting function through an ISP, camera 193, video codec, GPU, display screen 194, and application processor. In some embodiments of this application, the electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0214] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. In some embodiments of this application, the electronic device 100 may include one or N display screens 194, where N is a positive integer greater than 1. The electronic device 100 can implement display functions through a GPU, the display screen 194, and an application processor. The GPU is a microprocessor for image processing, connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. The processor 110 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0215] Furthermore, it should be noted that an operating system runs on top of the aforementioned components. Examples include Apple's iOS operating system, Google's Android open-source operating system, and Microsoft's Windows operating system. These operating systems can employ layered architectures, event-driven architectures, microkernel architectures, microservice architectures, or cloud architectures.

[0216] For ease of explanation, this application uses the layered architecture of the Android system as an example to illustrate the software structure of the electronic device 100.

[0217] It should be noted that although the embodiments of this application are described using the Android system as an example, the basic principles are also applicable to electronic devices based on operating systems such as iOS or Windows.

[0218] See Figure 7 This is a software structure block diagram of the electronic device 100 according to an embodiment of this application.

[0219] like Figure 7 As shown, the layered architecture of the electronic device 100 divides the software into several layers, each with a clear role and division of labor. Layers communicate with each other through software interfaces. In some embodiments of this application, the Android system is divided into five layers, from top to bottom: the application layer, the application framework layer, the Android runtime and system libraries, the Hardware Abstraction Layer (HAL), and the kernel layer.

[0220] The application layer can include a series of application packages. For example... Figure 7 As shown, the application package can include applications such as input methods and voice assistants.

[0221] See also Figure 7For example, in the technical solutions provided in the embodiments of this application, the application layer may also include an intelligent processing module (also known as an AI module), a feature extraction module, a prompt processing module, a text generation module, etc., for implementing the quick input scheme provided in the embodiments of this application.

[0222] The intelligent processing module, feature extraction module, prompt processing module, and text generation module can be called by applications installed in the application layer, thereby enabling quick input of information using a shortcut input scheme. For example, they can be called by various input method applications or voice assistants.

[0223] In the embodiments provided in this application, the intelligent processing module is used to implement functions such as status monitoring, information input, and user interface (UI) processing.

[0224] In the embodiments provided in this application, the feature extraction module is used to extract text content, page features, etc.

[0225] In the embodiments provided in this application, the prompt processing module is used to construct a prompt based on the features extracted in advance by the feature extraction module.

[0226] It should be noted that, in the embodiments provided in this application, the prompts may include user prompts and system prompts.

[0227] In the embodiments provided in this application, the text generation module is used to generate text content based on the prompt.

[0228] Furthermore, it should be noted that in the embodiments provided in this application, the intelligent processing module, feature extraction module, prompt processing module, and text generation module can be understood as software development kits (SDKs) providing corresponding functions. That is, in some embodiments of this application, the intelligent processing module can be understood as an AI SDK, the feature extraction module can be understood as a feature extraction SDK (e.g., a computer vision (CV) SDK), the prompt processing module can be understood as a prompt SDK, and the text generation module can be understood as a text generation SDK (in some embodiments, for example, a large language model (LLM) SDK).

[0229] The application framework layer provides application programming interfaces (APIs) and programming frameworks for applications within the application layer. In some embodiments of this application, these programming interfaces and frameworks can be described as functions. Figure 7As shown, the application framework layer may include window management services, input method management services, view systems, etc.

[0230] In the embodiments provided in this application, the window management service can obtain window information so that the intelligent processing module can process the information according to the window information, such as drawing and updating the UI.

[0231] In the embodiments provided in this application, the input method management service can listen for input events so that when the use of the input method application is detected, the keyboard corresponding to the input method is brought up so that the user can use the keyboard corresponding to the input method to input information.

[0232] The Android Runtime comprises the core libraries and the virtual machine. The Android Runtime is responsible for the scheduling and management of the Android system.

[0233] The core library consists of two parts: one part is the functionalities that need to be called by the Java language, and the other part is the Android core library.

[0234] The application layer and application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and application framework layer as binary files. The virtual machine is used to perform functions such as object lifecycle management, stack management, thread management, security and exception management, and garbage collection.

[0235] System libraries can include multiple functional modules. For example: surface manager, media libraries, 3D graphics processing libraries (e.g., OpenGL ES), 2D graphics engines (e.g., SGL), etc.

[0236] The Surface Manager is used to manage the display subsystem and provides the blending of 2D and 3D layers for multiple applications.

[0237] The media library supports playback and recording of various common audio and video formats, as well as still image files. It supports multiple audio and video encoding formats, such as MPEG4, H.264, MP3, AAC, AMR, JPG, and PNG.

[0238] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0239] Understandably, the 2D graphics engine mentioned above is a 2D drawing engine.

[0240] The kernel layer is the layer between hardware and software, and includes various hardware drivers and hardware management. For example... Figure 7As shown, the kernel layer can include display drivers, sensor drivers, camera drivers, power management drivers, etc.

[0241] This concludes the introduction to the software structure of electronic device 100. It is understandable that... Figure 7 The layers in the illustrated software structure and the components contained in each layer do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer layers than illustrated, and each layer may include more or fewer components; this application does not impose any limitations.

[0242] by Figure 6 The hardware structure shown and Figure 7 The electronic device with the software structure shown is a mobile phone. The quick input scheme provided by the embodiments of this application will be described in detail with reference to the accompanying drawings.

[0243] See Figure 8a and Figure 8b This illustration demonstrates a scenario where information is quickly inputted based on the shortcut input method provided in this application. Specifically, in this embodiment, the shortcut input method is triggered by an input method application installed on the mobile phone.

[0244] It should be noted that, Figure 8a and Figure 8b Interfaces 10f to 80f shown can be understood as the chat interfaces of instant messaging applications.

[0245] For example, in the embodiments of this application, the chat interface can be understood as an interface that can display chat content and conduct conversations (sending and receiving new chat content).

[0246] For example, in some embodiments of this application, the chat interface may be the interface where a user is currently having a conversation (chat) with a friend.

[0247] For example, in some other embodiments of the application, the chat interface may be the interface of a chat group that the user has currently opened.

[0248] For ease of explanation, this application embodiment uses the interface corresponding to the "group chat" chat group as an example for specific description.

[0249] See Figure 8a In example (1), when the user interface 10f is displayed on the mobile phone, after the user clicks the text input box 10f-1, the mobile phone responds to the user's operation and, in some embodiments of this application, will activate the keyboard corresponding to the input method, such as... Figure 8aThe keyboard 10f-2 shown in the interface 20f (2) is used to determine the position information of the shortcut input control based on the window information corresponding to the keyboard 10f-2.

[0250] Furthermore, after determining the location information of the shortcut input control, the shortcut input control will be displayed at the determined location. In this embodiment, taking the determined location information as the bottom of keyboard 10f-2 as an example, the displayed shortcut input control can be as follows: Figure 8a The shortcut input control 10f-3 is shown in the interface 30f (3).

[0251] For example, in some other embodiments of this application, when a user clicks the text input box 10f-1, the mobile phone, in response to the user's operation, can directly determine the position information of the shortcut input control based on the window information of the keyboard 10f-2 before displaying the keyboard 10f-2, and then directly display the shortcut input control 10f-3 when the keyboard 10f-2 is displayed. That is, when a user clicks the text input box 10f-1, the mobile phone, in response to the user's operation, directly updates the user interface from interface 10f to interface 30f.

[0252] Understandably, in the implementation where the user interface is directly updated from interface 10f to interface 30f, the time it takes for the user interface to change after the user clicks the text input box 10f-1 is longer than the time required for interface 10f to be updated to interface 20f first.

[0253] See Figure 8a In example (3), when multiple chat messages are already displayed in the interface 30f, in order to quickly generate chat messages related to the chat messages displayed in the interface 30f (which can be one or more of text messages, images, and documents), the user can enable the quick input function through the quick input control 10f-3 displayed in the interface 30f.

[0254] See also Figure 8a In example (3), after a user clicks the quick input control 10f-3, the mobile phone responds to the user's operation and can display something like this. Figure 8a Interface 40f is shown in (4).

[0255] See Figure 8a In (4), for example, interface 40f may include display elements 10f-9 and window W1 displayed on display elements 10f-9.

[0256] Among them, display elements 10f-9 can be understood as the interface after processing interface 30f, and all the elements included in them can be the same as the elements included in interface 30f.

[0257] Optionally, in some embodiments of this application (processing method 1), the processing of interface 30f may include, for example, adding a mask layer (with the same size as interface 30f) to interface 30f after the user clicks the shortcut input control 10f-3, then drawing the corresponding message box in the mask layer according to the coordinate information of the message box displaying chat content in interface 30f, and displaying the corresponding chat content in the drawn message box. Thus, display element 10f-9 in interface 40f is obtained. For ease of explanation, subsequent embodiments will directly use "mask layer" to refer to the display element, that is, display element 10f-9 can be called mask layer 10f-9. The subsequently appearing mask layer 10f-9' and mask layer 10g-4 can also be represented as display element 10f-9' and display element 10g-4.

[0258] To put it simply, adding a mask layer to interface 30f can be understood as adding a layer with a certain degree of transparency to interface 30f. Elements in interface 30f displayed below this layer cannot be interacted with by the user, but elements drawn on this layer, such as the message boxes mentioned above, can be interacted with by the user, such as being selected or deselected.

[0259] Optionally, in some other embodiments of this application (processing method 2), the processing of interface 30f may include, for example, taking a full-screen screenshot of interface 30f after the user clicks the shortcut input control 10f-3, then overlaying the full-screen screenshot onto interface 30f, adding a mask layer (with the same size as interface 30f) on the full-screen screenshot, and then drawing the corresponding message box in the mask layer according to the coordinate information of the message box of each chat content extracted from the full-screen screenshot, and displaying the corresponding chat content in the drawn message box. This ensures that the mask layer 10f-9 does not change during the content generation process using the shortcut input function. That is, even if new chat content is received, it will not affect the elements displayed in the mask layer 10f-9.

[0260] Optionally, in some other embodiments of this application (processing method 3), the processing of interface 30f may also include, for example, taking a full-screen screenshot of interface 30f after the user clicks the shortcut input control 10f-3, then blurring or fuzzing the full-screen screenshot, and overlaying the processed full-screen screenshot onto interface 30f. Then, based on the coordinate information of the message box of each chat content extracted from the full-screen screenshot, the corresponding message box is drawn in the overlay, and the corresponding chat content is displayed in the drawn message box.

[0261] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0262] Here, window W1 can be understood as the window corresponding to the shortcut input function. In some embodiments of this application, window W1 can be a floating window. That is, window W1 can be displayed at any position in the overlay 10f-1.

[0263] See also Figure 8a In (4), for example, window W1 may include one or more controls, such as a quick input text display box 10f-5, a select all control 10f-6, a deselect all control 10f-7, a prompt window 10f-8, etc.

[0264] See also Figure 8a In example (4), if the user does not select any chat content in any message box in interface 40f, the prompt content displayed in prompt window 10f-8 is, for example, "Please select text content".

[0265] See also Figure 8a In example (4), when a user clicks the select all control 10f-6, the phone responds to the user's action by selecting all message boxes displayed on interface 40f. In this case, the phone's user interface can change from interface 40f to... Figure 8a The interface 50f shown in (5) is shown in the middle.

[0266] Furthermore, it should be noted that users can also select message boxes by clicking on them in interface 40f. Understandably, the selected message box will change from the style shown in interface 40f to the style shown in interface 50f.

[0267] Furthermore, it should be noted that after any message box displayed in interface 40f is selected, window W1 can also display the answer generation control 10f-10. That is, window W1 can change to the style of window W2 displayed in interface 50f.

[0268] See Figure 8a In section (5), for example, when a user clicks the generate answer control 10f-10, the mobile phone responds to the user's operation by generating text content related to the chat content in the selected message box and displays the generated text content. For example, interface 50f will become... Figure 8a Interface 60f is shown in (6).

[0269] It should be noted that, in the embodiments of this application, interface 60f can be understood as the interface on which window W3 is displayed on the aforementioned interface 30f. Window W3 can be understood as the changed window W2. Compared to window W2, in window W3, the generated text content is displayed in the quick input text display box 10f-5, such as the quick input text display box 10f-5' in window W3. The select all control 10f-6 and deselect all control 10f-7 in window W2 are hidden in window W3, replaced by the reselect control 10f-11.

[0270] Optionally, the prompt content displayed in prompt window 10f-8 will be updated to prompt the user to reselect, such as "Wrong selection? You can select again" displayed in prompt window 10f-8'.

[0271] Specifically, when the user clicks to reselect control 10f-11, the phone responds to the user's operation, and the user interface will revert from interface 60f to interface 40f.

[0272] See also Figure 8a In example (6), when the quick input text display box 10f-5' displays long text content, a scroll bar 10f-13 can also be displayed in the quick input text display box 10f-5'. That is, by operating the scroll bar 10f-13, the user can slide up and down the text content displayed in the quick input text display box 10f-5' so that the user can view the complete text content.

[0273] See also Figure 8a (6) or Figure 8b In example (1), when the generated text content is displayed in the quick input text display box 10f-5', the window W3 can also display the insertion control 10f-12. When the user clicks the insertion control 10f-12, the mobile phone, in response to the user's operation, can copy the text content displayed in the quick input text display box 10f-5' to the text input box 10f-1 (e.g., ...). Figure 8b (2) The text input box 10f-1' in the interface 70f is shown.

[0274] It should be noted that the text input box 10f-1 (or text input box 10f-1') can automatically wrap lines according to the length of the text content.

[0275] In addition, it should be noted that as the text content automatically wraps in the text input box 10f-1', the area displaying the chat content on the current interface gradually shrinks, and the chat content in this area will be pushed upwards, that is, the chat content at the top will be removed from the visible area.

[0276] See Figure 8b In example (2), when the user clicks the "send" button, the mobile phone responds to the user's operation and can send the text content displayed in the text input box 10f-1' to the chat content display area of ​​the current interface, such as the area above the text input box 10f-1.

[0277] For example, after the text content displayed in the text input box 10f-1' is sent to the chat content display area of ​​the current interface, the phone's user interface will change from interface 70f to... Figure 8b Interface 80f is shown in (3).

[0278] Furthermore, it should be noted that when the shortcut input control 10f-3 is displayed, a back control can also be displayed on the current screen, such as the back control 10f-4 on screen 30f. Specifically, when window W1, W2, or W3 is displayed on the current screen, clicking the back control 10f-4 will cause the phone to respond to the user's action by canceling the display of window W1, W2, or W3 on the current screen. For example, the user interface will revert from screen 40f, 50f, or 60f back to screen 30f.

[0279] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended to be the sole limitation of this embodiment. In practical applications, based on the chat content selected by the user in the message box on interface 40f, not only text content, but also images, documents, etc., can be generated.

[0280] The following combination Figure 9a and Figure 9b ,right Figure 8a and Figure 8b The specific processing logic for implementing quick input in the scenario shown is explained.

[0281] See Figure 9a The quick input method provided in this application embodiment specifically includes:

[0282] S101, Input method management service registration for input method monitoring of input method applications.

[0283] For example, in some embodiments of this application, when an electronic device, such as a mobile phone, is started, the input method application can call the interface / function / method provided in the intelligent processing module for user status monitoring to send a registration input method listening request to the input method management server.

[0284] Understandably, an input method monitoring request can be used to instruct the input method management server to monitor user actions performed by the user on the phone's user interface. For example, monitoring user clicks or touches on the phone's user interface, such as the text input box 10f-1 displayed on interface 10f.

[0285] Accordingly, after receiving the input method registration listening request, the input method management service can send a registration listening receipt to the input method application and register the input method listening.

[0286] Understandably, a registration listener receipt can be used to indicate that the input method management service has successfully received the registration input method listener request sent by the input method application through the interface / function / method provided by the intelligent processing module for status monitoring.

[0287] Furthermore, it can be understood that in this embodiment, the input method application calls the interface / function / method provided by the intelligent processing module for status monitoring to send a registration input method monitoring request to the input method management server. Therefore, the registration monitoring receipt sent by the input method management service can specifically be sent to the intelligent processing module.

[0288] S102, After registering the input method listener, the input method management service will pop up the keyboard corresponding to the input method when it detects user operation on the text input box corresponding to the input method.

[0289] It should be noted that user operations on the text input box corresponding to the input method, such as the text input box 10f-1 in interface 10f, can be click operations or touch operations, etc.

[0290] Furthermore, it should be noted that in the technical solutions provided in this application, the input method application can be any input method application installed on the mobile phone. That is, it can be a system input method application (provided by the mobile phone manufacturer) or a third-party input method application (provided by other manufacturers).

[0291] Furthermore, it should be noted that in the technical solutions provided in the embodiments of this application, the keyboard corresponding to the input method, such as keyboard 10f-2 in interface 20f, can be understood as a soft keyboard.

[0292] For details on the specific implementation logic of the InputMethodManagerService (IMMS) invoking the keyboard corresponding to the input method, please refer to the user documentation of InputMethodManagerService (IMS) and InputMethodManager (IMM). It will not be elaborated here.

[0293] For example, taking the text input area clicked by the user as text input area 10f-1 in interface 10f, after the input method management service calls up the keyboard 10f-2 corresponding to the input method, the current interface will change from interface 10f to interface 20f.

[0294] S103, when the keyboard corresponding to the input method is displayed, the intelligent processing module obtains the window information of the current interface from the window management service.

[0295] The window management service is responsible for managing the display and layout of windows. In some embodiments of this application, the window management service can be understood as a window manager, responsible for handling operations such as creating, displaying, hiding, moving, and resizing application windows. Therefore, the intelligent processing module sends a window information acquisition request to the window management service. In response to this request, the window management service can feed back the window information corresponding to the current interface, such as the package name information of the application to which the current interface belongs, and the coordinate information of each control in the interface (such as the coordinate information of each user avatar, message box, text input box, and keyboard in interface 30f), to the intelligent processing module.

[0296] S104, the intelligent processing module determines the position information of the shortcut input control based on the obtained window information, and transmits the position information to the window management service.

[0297] Specifically, in some embodiments of this application, the intelligent processing module can determine the position information of the shortcut input control based on the coordinate information of the keyboard corresponding to the input method.

[0298] Understandably, a shortcut input control can be understood as an entry point for enabling the shortcut input function provided in the embodiments of this application, such as the shortcut input control 10f-3 shown in interface 30f. Describing it as a shortcut input control in the embodiments of this application is only for better describing the technical solution of the embodiments of this application and is not intended to limit it.

[0299] For example, in some embodiments of this application, the intelligent processing module determines the position information of the shortcut input control based on the coordinate information of the keyboard corresponding to the input method, for example, it is located between the keyboard 10f-2 and the text input box 10f-1 corresponding to the input method.

[0300] For example, in some other embodiments of this application, the intelligent processing module determines the position information of the shortcut input control based on the coordinate information of the keyboard corresponding to the input method, for example, it is located at the bottom of the keyboard 10f-2.

[0301] For example, in some other embodiments of this application, the intelligent processing module determines the position information of the shortcut input control based on the coordinate information of the keyboard corresponding to the input method. For example, it floats on the edge of the current interface in the form of a floating ball, such as the right or left edge of the current interface.

[0302] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0303] For ease of explanation, this embodiment of the application takes the location information of a certain shortcut input control as the bottom of the keyboard 10f-2 as an example, that is, the interface of the shortcut input control 10f-3 is finally displayed, as shown in interface 30f.

[0304] S105, the window management service creates a window to display the shortcut input controls based on the location information determined by the intelligent processing module, and displays the shortcut input controls in the created window.

[0305] S106: Upon receiving a user operation on the shortcut input control, take a screenshot of the current interface and transmit the screenshot to the feature extraction module.

[0306] Understandably, the screenshot taken of the current interface is a full-screen screenshot. For example Figure 8a The embodiment shown describes capturing interface 30f and obtaining a full-screen screenshot corresponding to interface 30f.

[0307] S107, the feature extraction module performs feature extraction processing on the screenshot of the current interface, extracts the text content and page features of the current interface, and transmits the extracted feature information to the intelligent processing module.

[0308] For example, in some embodiments of this application, the feature extraction module is, for example, a CV SDK. The CV SDK can extract text content contained in a screenshot corresponding to the current interface based on OCR (Optical Character Recognition) technology.

[0309] For example, in some embodiments of this application, after the feature extraction module extracts the text content contained in the screenshot, it can determine the business scenario corresponding to the current interface based on the text content. For example, it can determine that the business scenario corresponding to the current interface is a chat scenario based on the extracted "group chat", "when was born", "October 1st", "China Merchants Bank or China Construction Bank?", "China Construction Bank", "what does this mean?", and the user name corresponding to each chat content, such as "Petter", "Alie", "John", etc.

[0310] In addition, the feature extraction module can also process the screenshot using technologies such as computer vision and image processing, and then extract the page features of the corresponding interface from the screenshot, such as the coordinate information of the message box corresponding to each chat content, the location information of the avatar and username corresponding to each chat content, and can establish a mapping relationship between each message box and the corresponding chat content, avatar, and username.

[0311] Furthermore, it should be noted that in some embodiments of this application, in order to reduce the amount of data processing and improve the feature extraction speed, the intelligent processing module may extract features only from the chat content display area.

[0312] To better understand, the following will be combined with Figure 9b Step S107 of the feature extraction module is explained.

[0313] See Figure 9b For example, after the feature extraction module obtains the screenshot corresponding to the current interface, such as the screenshot corresponding to interface 30f, it performs image recognition processing on the screenshot, such as OCR text recognition processing (to obtain text features), and page feature extraction processing, thereby obtaining the text features and page features included in the screenshot.

[0314] For example, for the screenshot corresponding to interface 30f, the text features extracted by the feature extraction module include, for example, the chat content displayed in message box M1, message box M2, message box M3, message box M4, message box M5, etc.

[0315] The page features extracted by the feature extraction module include, for example, a set of coordinate information corresponding to message box M1, the username corresponding to message box M1, and an image (user account name and avatar of the user sending the chat content in message box M1), a set of coordinate information corresponding to message box M2, the username corresponding to message box M2, and an image (user account name and avatar of the user sending the chat content in message box M2), a set of coordinate information corresponding to message box M3, the username corresponding to message box M3, and an image (user account name and avatar of the user sending the chat content in message box M3), a set of coordinate information corresponding to message box M4, the username corresponding to message box M4, and an image (user account name and avatar of the user sending the chat content in message box M4), and a set of coordinate information corresponding to message box M5, the username corresponding to message box M5, and an image (user account name and avatar of the user sending the chat content in message box M5).

[0316] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0317] S108, the intelligent processing module performs masking processing on the current interface based on the feature information extracted by the feature extraction module, and displays a floating window corresponding to the quick input function on the mask.

[0318] It should be noted that, in the embodiments of this application, applying a mask to the current interface can be understood as processing the current interface using processing method 1, processing method 2, or processing method 3 as described in the above embodiments.

[0319] For ease of explanation, this application's embodiments take processing method 2 as an example, combined with... Figure 9b Please provide a detailed explanation.

[0320] See Figure 9b For example, after receiving the feature information extracted by the feature extraction module, the intelligent processing module can first overlay the corresponding screenshot on the current interface. That is, overlay the screenshot corresponding to interface 30f on interface 30f, and then add a mask layer on the screenshot. Next, based on the feature information extracted by the feature extraction module, draw each message box included in the screenshot on the mask layer, and display the corresponding text content, i.e., the chat content, in the drawn message boxes.

[0321] For example, based on a set of coordinate information of message box M1, a message box M1' corresponding to message box M1 is drawn on the overlay, and the text content extracted from message box M1 is displayed in message box M1'.

[0322] For example, based on a set of coordinate information of message box M2, a message box M2' corresponding to message box M2 is drawn on the overlay, and the text content extracted from message box M2 is displayed in message box M2'.

[0323] For example, based on a set of coordinate information of message box M3, a message box M3' corresponding to message box M3 is drawn on the overlay, and the text content extracted from message box M3 is displayed in message box M3'.

[0324] For example, based on a set of coordinate information of message box M4, a message box M4' corresponding to message box M4 is drawn on the overlay, and the text content extracted from message box M4 is displayed in message box M4'.

[0325] For example, based on a set of coordinate information of message box M5, a message box M5' corresponding to message box M5 is drawn on the overlay, and the text content extracted from message box M5 is displayed in message box M5'.

[0326] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended to be the sole limitation of this embodiment. In practical applications, the corresponding chat content may not be displayed in the message box drawn in the overlay. Instead, the user selects the message box in the overlay, triggering the generation of text / image / document. For example, after clicking the generate answer control 10f-10, the text content (chat content) corresponding to the selected message box can be directly obtained based on the mapping relationship between the feature information fed back by the feature extraction module.

[0327] Furthermore, it should be understood that since the current chat interface, such as interface 30f, is overlaid with the corresponding full-screen screenshot of interface 30f (i.e., the same size), and the overlay is directly added to the entire full-screen screenshot, after drawing the message boxes in the overlay based on the coordinate information of each message box extracted from the full-screen screenshot, the position of the message box displayed in the overlay completely overlaps with the message boxes in the full-screen screenshot below the overlay. For example, message box M1' overlaps with message box M1, message box M2' overlaps with message box M2, message box M3' overlaps with message box M3, message box M4' overlaps with message box M4, and message box M5' overlaps with message box M5. Thus, visually, the same content is displayed in the same position.

[0328] Among them, the floating window corresponding to the shortcut input function displayed on top of the mask is, for example, window W1 displayed in interface 40f.

[0329] It should be noted that, regarding the message boxes drawn on the overlay, the displayed window W1 can call the UI interfaces / methods / functions provided by the intelligent processing module to realize the drawing of these UI elements.

[0330] For example, after the intelligent processing module executes step S108, the user interface displayed on the mobile phone is, for example, interface 40f as described in the above embodiment. For a detailed description of the floating window corresponding to the quick input function, please refer to the description of window W1 in interface 40f above; it will not be repeated here.

[0331] S109, the intelligent processing module responds to the user's selection of the content displayed in the overlay by displaying a text generation control on the current interface.

[0332] This includes user selection operations on content displayed in the overlay, such as operations performed on the select all control 10f-6 in interface 40f, or on the five message boxes displayed in overlay 10f-9, such as... Figure 9b The selection operation (such as a click operation) of any one or more of the message boxes M1', M2', M3', M4', and M5' mentioned in the text.

[0333] Among them, the text generation control displayed on the current interface is, for example, the answer generation control 10f-10 displayed on interface 50f.

[0334] Furthermore, in some embodiments of this application, after the user selects the message box displayed in the overlay, the intelligent processing module will expand the associated content based on the chat content in the selected message box. For example, the sender information corresponding to each chat message will be anonymously completed based on the avatar and nickname (username).

[0335] It should be noted that, in the embodiments of this application, anonymous completion based on avatar and nickname (username) can be understood as determining the sender of each chat message based on the username and avatar corresponding to each chat message extracted from the screenshot. Then, a number or identifier is assigned to each sender to identify them. Based on the correspondence between each identifier and each sender, and between each chat message and each sender, a correspondence between each identifier and each chat message can be established. This achieves the goal of identifying the relationship between each chat message and its sender without revealing the user's real avatar and name.

[0336] For example, taking the five message boxes displayed in the user-selected overlay 10f-9 as an example, that is, when overlay 10f-9 is updated to overlay 10f-9' in interface 50f, the sender "Petter" of the chat content displayed in message box M1' and message box M3' can be identified as "User A", the sender "Alie" of the chat content displayed in message box M2' and message box M4' can be identified as "User B", and the sender "John" of the chat content displayed in message box M5' can be identified as "User C".

[0337] The final anonymously completed text content (text content after related content expansion processing) would be, for example, “User A: When were you born?”, “User B: October 1st”, “User A: China Merchants Bank or China Construction Bank?”, “User B: China Construction Bank”, “User C: What does this mean?”.

[0338] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0339] Furthermore, in some other embodiments of this application, the aforementioned related content expansion operation can also be triggered when the user clicks on a text generation control displayed on the current interface, such as the answer generation control 10f-10. That is, when the user clicks on the answer control 10f-10, the related content expansion operation is executed first, and then step S110 is executed.

[0340] In addition, it should be noted that, in order to protect user privacy, the operation of expanding the associated content of each chat message based on the avatar and nickname is completed locally on the mobile phone, that is, the user information such as the identified avatar and nickname is not uploaded to the server.

[0341] S110, when the user operates the text generation control, the intelligent processing module sends a prompt construction instruction to the prompt processing module.

[0342] Optionally, in some embodiments of this application, the prompt construction instruction sent by the intelligent processing module to the prompt processing module carries the chat content in the selected message box in the overlay, application information determined based on the page features extracted by the feature extraction module, etc.

[0343] Optionally, in some embodiments of this application, the chat content in the selected message box in the overlay carried in the prompt construction instruction sent by the intelligent processing module to the prompt processing module is specifically the text content after expanding the associated content (such as anonymous completion, resulting in "User A: When were you born?", "User B: October", "User A: China Merchants Bank or China Construction Bank?", "User B: China Construction Bank", "User C: What does this mean?").

[0344] For example, in some embodiments of this application, the determined application information includes, for example, application registration, Avtivity information corresponding to the current interface, etc.

[0345] S111, the prompt processing module constructs a prompt based on the information carried in the prompt construction instruction, and feeds back the constructed prompt to the intelligent processing module.

[0346] In the embodiments of this application, to ensure the validity of the constructed prompts, the prompt processing module can first preprocess the information carried in the prompt construction instructions, such as desensitizing the text content (e.g., the text content obtained through anonymous completion) and page features.

[0347] Optionally, in some embodiments of this application, the text content and page features are desensitized, for example, by deleting sensitive words in the text content, deleting sensitive features (such as images, icons, text, etc.) in the page features, or by replacing these sensitive information.

[0348] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0349] After anonymizing the text content and page features, the resulting text content can be assembled, for example, into a complete message according to the order in which it was received. Then, the assembled content undergoes intent recognition processing.

[0350] Understandably, in some embodiments of this application, the prompt processing module may call the intent recognition module / model to perform intent recognition processing on the assembled content, thereby determining the user's intent.

[0351] Finally, after determining the user's intent, user prompts can be constructed based on the assembled content and the user's intent.

[0352] For example, given the following content: "User A: When were you born?", "User B: October 1st", "User A: China Merchants Bank or China Construction Bank?", "User B: China Construction Bank", and "User C: What does this mean?", the intent recognition module can determine the type of each chat message by analyzing its content. Based on grammar and tone, it can identify that "User A: When were you born?", "User A: China Merchants Bank or China Construction Bank?", and "User C: What does this mean?" are question-type statements, while "User B: October 1st" and "User B: China Construction Bank" are statement-type statements.

[0353] After determining the type of each chat message, the intent recognition module can further process chat messages belonging to the question type to determine the final question asked. Then, based on the final question asked, the user's intent is determined.

[0354] For example, in some implementations of this application, when determining the final question to be asked, a chronological order principle can be followed, with the statement of the last question type in the chronological order being taken as the question to be answered, i.e., the final question to be asked.

[0355] For example, in some other implementations of this application, when determining the final question to be asked, a complex algorithm can be used to analyze which question type statement is not closed in the context, i.e. has not received a response (answer), and then the statement of the unclosed question type is taken as the question to be answered, i.e. the final question to be asked.

[0356] Taking the statements whose question types were identified by the intent recognition module as "User A: When were you born?", "User A: China Merchants Bank or China Construction Bank?", and "User C: What does this mean?" as examples, further analysis can determine that User C's "What does this mean?" belongs to the final question asked.

[0357] Next, the intent recognition module can determine the user's intent based on the question. For example, the determined user intent might be "How to answer question C".

[0358] Therefore, after completing the above processing, the prompt processing module can construct user prompts based on the assembled content and user intent.

[0359] Furthermore, it should be noted that in this embodiment, the user prompt is determined after processing the chat content in the message box selected by the user in the overlay. It is used to identify or limit the topic of the text content to be generated by the text generation module. In other words, in this embodiment, the user prompt can be understood as the keywords used by the text generation module when generating text content. That is, the text generation module derives and expands text content related to the chat content in the selected message box based on the user prompt.

[0360] For example, in some embodiments of this application, the user prompt constructed by the prompt processing module can be as follows:

[0361] User prompt{

[0362] User A: When were you born?

[0363] User B: Eleven

[0364] User A: China Merchants Bank or China Construction Bank?

[0365] User B: China Construction Bank

[0366] User C: What does this mean?

[0367] How to answer user C's question

[0368] }

[0369] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0370] Furthermore, to ensure that the text content generated based on the prompts is more relevant to the current business scenario, the prompt processing module can also generate system prompts. Specifically, the prompt processing module can determine the type of content to be answered based on the intent recognition module and generate the corresponding system prompt.

[0371] For example, in some embodiments of this application, different types of system prompts can be pre-stored in the storage space corresponding to the prompt processing module. In this way, after determining the user's intent, the prompt processing module can find the matching system prompt from the corresponding storage space based on the type of the content to be answered corresponding to that user intent.

[0372] For example, for question-type questions, a system prompt such as "You are knowledgeable and learned; please answer the above questions as objectively and accurately as possible" can be pre-stored. For writing-type questions, a system prompt such as "You are a professional writer; based on the provided information, complete a high-quality written work" can be pre-stored.

[0373] Furthermore, it should be noted that when the user's intent is unclear, the user prompt can be the assembled text content, while the system prompt defaults to the casual conversation type. For casual conversation types, a message such as "You are a talkative friend, please smoothly and coherently continue the above information and make the other party want to continue chatting with you" can be pre-stored.

[0374] Furthermore, it should be noted that in some embodiments of this application, as the user uses the application, the intent recognition module continuously iterates and learns. When more types are recognized, the pre-stored system prompts can be expanded according to the recognized types, thereby better adapting to the diverse usage needs of users.

[0375] Taking the question "What does this mean?" posed by user C as an example, when the chat content is a question, the system prompt determined by the prompt processing module might be something like, "You are knowledgeable and learned; please answer the above question as objectively and accurately as possible." That is, the system prompt that the prompt processing module feeds back to the intelligent processing module could be as follows:

[0376] System prompt{

[0377] You are a learned and knowledgeable person; please answer the above questions as objectively and accurately as possible.

[0378] }

[0379] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended to be the sole limitation of this embodiment. In practical applications, system prompts may be predefined according to different types, such as "formal," "humorous," or "literary," and this application does not impose any restrictions on this.

[0380] Furthermore, it's worth noting that in practical applications, application information determined by the de-identified page features can also be incorporated when generating system prompts. That is, when generating system prompts, not only the type of content to be answered corresponding to the user's intent is considered, but also application information determined by page features (such as the application name) and the current business scenario. Thus, even if the type of content to be answered corresponding to the user's intent is the same, the final generated system prompt will differ depending on the corresponding application and business scenario. For example, the system prompt generated for a question-type content will be different for a work-related application and business scenario compared to the system prompt generated for an entertainment-related application and business scenario.

[0381] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0382] For ease of explanation, this embodiment uses system prompts to determine the content to be answered corresponding to the user's intent based on the selected chat content, and the application information and business scenario corresponding to the page features. That is, the system prompts, determined based on the selected chat content and page features, are used to instruct the text generation model on the creation type to follow when generating text content.

[0383] S112, the intelligent processing module sends a text generation instruction to the text generation module.

[0384] In one embodiment of this application, the text generation instruction issued by the intelligent processing module to the text production module may, for example, carry user prompts and system prompts fed back by the prompt processing module.

[0385] For example, the text generation module can parse the following content from the text generation instructions:

[0386] User prompt{

[0387] User A: When were you born?

[0388] User B: Eleven

[0389] User A: China Merchants Bank or China Construction Bank?

[0390] User B: China Construction Bank

[0391] User C: What does this mean?

[0392] How to answer user C's question

[0393] }

[0394] System prompt{

[0395] You are a learned and knowledgeable person; please answer the above questions as objectively and accurately as possible.

[0396] }

[0397] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0398] S113, the text generation module generates text content that meets the requirements of the user prompt and the system prompt based on the prompt carried in the text generation instruction, and feeds back the generated text content to the intelligent processing module.

[0399] For example, in the embodiments provided in this application, the text generation module is, for example, a Large Language Model (LLM).

[0400] For example, based on the user prompt above, LLM can determine that the response to be generated is for the text content "What is the relationship between the birth of a child and China Merchants Bank and China Construction Bank?"

[0401] S114, the intelligent processing module displays the generated text content in the quick input text display box.

[0402] That is, after the user clicks the generate answer control on interface 50f, the mobile phone responds to the user's operation and executes steps S112 to S114. The corresponding interface change during this process is, for example, the user interface is updated from interface 50f to interface 60f.

[0403] Understandably, after the generated text content is displayed in the quick input text display box, if the user clicks the insert control 10f-12, the phone responds to the user's operation by copying the text content in the quick input text display box 10f-5', pasting the copied text content into the text input box 10f-1, and collapsing the floating window corresponding to the quick input function. If window W3 is collapsed, the user interface updates from interface 60f to interface 70f.

[0404] Therefore, based on the quick input method provided in this application embodiment, information that matches the current application and the content displayed on the screen can be quickly generated without the user needing to input prompts.

[0405] It should be noted that, in the embodiments provided in this application, Figure 9a The provided shortcut input method is for Figure 8a and Figure 8b The illustrated scenario is a chat scenario using any instant messaging application installed on a mobile phone. In other embodiments of this application, Figure 9aThe provided shortcut input method can also be adapted to business scenarios involving other types of applications, such as discussion forum reply scenarios in video applications (e.g. Figure 4 (Scene shown).

[0406] In other words, the quick input method provided in this application embodiment can assemble different user prompts and system prompts according to different types of applications, business scenarios, and screen content, and then call the text generation module to generate text content that meets user needs.

[0407] Furthermore, since the entire process does not require users to input prompts or select a creation type, it avoids situations where the generated text content is unsatisfactory due to inappropriate user input or selection of a creation type.

[0408] However, in practical applications, users may not select all message boxes in the overlay 10f-9 using the select all control 10f-6, or the chat content in the selected message boxes may not be sufficient to determine the user's intent. This results in the prompts being inappropriate based on the text content and page features in the selected message boxes, which in turn leads to the final generated text content not matching the current app, business scenario, or screen content, thus affecting the user experience.

[0409] In view of this, embodiments of this application provide a quick input method to solve the aforementioned technical problems. To better understand the technical solutions provided by embodiments of this application, the following will still refer to... Figure 6 The hardware structure shown and Figure 7 The electronic device with the software structure shown is a mobile phone. Taking the shortcut input method triggered by the input method application installed on the mobile phone as an example, combined with... Figure 10 The quick input scheme provided in the embodiments of this application will be described in detail.

[0410] See Figure 10 In example (1), interface 30f' is similar to interface 30f. For the purpose and usage of the same controls in these two interfaces, please refer to the description of interface 30f in the above embodiments, which will not be repeated here.

[0411] See also Figure 10 In example (1), when a user clicks the quick input control 10f-3, the phone responds to the user's action by updating the phone's user interface from interface 30f' to... Figure 10 The interface 40f' shown in (2) is shown.

[0412] See Figure 10In example (2), interface 40f' is similar to interface 40f. The difference is that, in the embodiments provided in this application, the floating window corresponding to the quick input function may include, in addition to the quick input text display box 10f-5, the select all control 10f-6, the cancel select all control 10f-7, and the prompt window 10f-8, a prompt input box 10f-14. That is, in the embodiments of this application, the floating window displayed on the overlay 10f-9 in interface 40f' is window W4.

[0413] Among them, the prompt input boxes 10f-14 are used for users to manually input prompts.

[0414] It should be noted that in some embodiments of this application, the prompt input box 10f-14 can be optional, that is, the user can choose not to input a prompt in the prompt input box 10f-14, but directly select all the message boxes displayed in the overlay 10f-9 through the select all control 10f-6, or manually select the message boxes.

[0415] In addition, it should be noted that before the user enters a prompt in the prompt input box 10f-14, a prompt message such as "Please enter a prompt (optional)" can be displayed in the prompt input box 10f-14 to prompt the user to manually enter a prompt.

[0416] Furthermore, regarding the uses and usage of the quick input text display box 10f-5, the select all control 10f-6, the deselect all control 10f-7, and the prompt window 10f-8, please refer to the description of interface 40f in the above embodiments, which will not be repeated here.

[0417] For example, in some embodiments of this application, when a user clicks the select all control 10f-6 to select all the message boxes displayed in the overlay 10f-9, the user can use voice input (focusing the cursor on the prompt input box 10f-14, using a voice assistant to recognize the user's voice data, and then converting it into corresponding text content as a prompt) or text input (focusing the cursor on the prompt input box 10f-14, pulling up the keyboard to input the corresponding text content as a prompt) to input a prompt in the prompt input box 10f-14.

[0418] If the user enters the message "What does this mean?" in the prompt input box 10f-14, then the user interface is... Figure 10 Taking the prompt displayed in the prompt input box 10f-14' of the interface 50f' shown in (3) as an example, after the user clicks to generate answer 10f-10, the mobile phone responds to the user's operation and displays the generated text in the quick input text display box 10f-5, as shown in the quick input text display box 10f-5' of the interface 60f.

[0419] Therefore, by constructing the user prompts and system prompts required for the final generated text content based on the message content selected by the user and the prompts entered, it is ensured that the generated text content can not only meet the user's needs, but also be relevant to the current APP, business scenario and screen content.

[0420] The following combination Figure 11 ,right Figure 10 The specific processing logic for implementing quick input in the scenario shown is explained.

[0421] See Figure 11 The quick input method provided in this application embodiment specifically includes:

[0422] S201, Input Method Management Service Registration: Input method monitoring for input method applications.

[0423] S202, After registering the input method listener, the input method management service will pop up the keyboard corresponding to the input method when it detects user operation on the text input box corresponding to the input method.

[0424] S203, when the keyboard corresponding to the input method is displayed, the intelligent processing module obtains the window information of the current interface from the window management service.

[0425] S204, the intelligent processing module determines the position information of the shortcut input control based on the obtained window information, and transmits the position information to the window management service.

[0426] S205, the window management service creates a window to display shortcut input controls based on the location information determined by the intelligent processing module, and displays the shortcut input controls in the created window.

[0427] S206: Upon receiving a user operation on the shortcut input control, take a screenshot of the current interface and transmit the screenshot to the feature extraction module.

[0428] S207, the feature extraction module performs feature extraction processing on the screenshot of the current interface, extracts the text content and page features of the current interface, and transmits the extracted feature information to the intelligent processing module.

[0429] It should be noted that steps S201 to S207 in the embodiments of this application are different from those in the present application. Figure 9a Steps S101 to S107 in the illustrated embodiment are the same. For specific implementation details, please refer to the description of steps S101 to S107 in the above embodiment, which will not be repeated here.

[0430] S208, the intelligent processing module performs masking processing on the current interface based on the feature information extracted by the feature extraction module, and displays a floating window corresponding to the quick input function on the mask.

[0431] It should be noted that, in the embodiments provided in this application, the masking processing performed on the current interface is the same as... Figure 9a The masking process performed in step S108 in the illustrated embodiment is the same. For specific implementation details, please refer to the description of step S108 in the above embodiment, which will not be repeated here.

[0432] Furthermore, it should be noted that in the embodiments provided in this application, the floating window corresponding to the shortcut input function displayed on the overlay is, for example, window W4 displayed in interface 40f'. That is, in the embodiments provided in this application, the floating window corresponding to the shortcut input function includes not only the content in window W1, but also the prompt input box.

[0433] For details regarding the prompt input box, please refer to the description of the prompt input box 10f-14 in the above embodiments, which will not be repeated here.

[0434] S209, the intelligent processing module responds to the user's selection of content displayed in the overlay and / or input of prompts in the prompt input box by displaying a text generation control on the current interface.

[0435] For ease of explanation, this embodiment of the application uses the example where the user has both selected the content displayed in the overlay and entered a prompt message in the prompt message input box, such as... Figure 10 The interface 50f' shown in (3) is shown.

[0436] For the related content expansion process performed after selecting the content displayed in the overlay, please refer to the description of step S109 in the above embodiments, which will not be repeated here.

[0437] S210, when the user operates the text generation control, the intelligent processing module sends a prompt construction instruction to the prompt processing module.

[0438] Understandably, when a prompt is entered in the prompt input box, the prompt construction instruction sent by the intelligent processing module to the prompt processing module will include not only the information selected by the user and page features, but also the prompt entered by the user in the prompt input box.

[0439] S211, the prompt processing module constructs a prompt based on the information carried in the prompt construction instruction, and feeds back the constructed prompt to the intelligent processing module.

[0440] Understandably, after receiving the prompt construction instruction from the intelligent processing module, the prompt processing module can also preprocess the information carried in the instruction, such as desensitizing the text content and page features. Then, the desensitized content is assembled. Next, intent recognition processing is performed on the assembled content. Finally, after determining the user's intent, a user prompt can be constructed based on the assembled content and the user's intent, and a system prompt can be constructed based on the page features and the user's intent.

[0441] For details regarding the processing of information carried in the prompt construction instruction by the prompt processing module, please refer to the description of step S111 in the above embodiments, which will not be repeated here.

[0442] For example, if the user selects "User A: When were you born?", "User B: October", "User A: China Merchants Bank or China Construction Bank?", "User C: ?", and the user inputs the prompt "What does this mean?", the final question to be answered is how to answer "What does this mean?", and the constructed user prompt would be as follows:

[0443] User prompt{

[0444] User A: When were you born?

[0445] User B: Eleven

[0446] User A: China Merchants Bank or China Construction Bank?

[0447] User B: China Construction Bank

[0448] What does this mean?

[0449] How to answer the question "What does this mean?"

[0450] }

[0451] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0452] Taking the above user prompt as an example, since the type of content to be answered is a question, in some embodiments of this application, the final system prompt may be as follows:

[0453] System prompt{

[0454] You are a learned and knowledgeable person; please answer the above questions as objectively and accurately as possible.

[0455] }

[0456] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0457] S212, the intelligent processing module sends a text generation instruction to the text generation module.

[0458] In one embodiment of this application, the text generation instruction issued by the intelligent processing module to the text production module may, for example, carry user prompts and system prompts fed back by the prompt processing module.

[0459] For example, the text generation module can parse the following content from the text generation instructions:

[0460] User prompt{

[0461] User A: When were you born?

[0462] User B: Eleven

[0463] User A: China Merchants Bank or China Construction Bank?

[0464] User B: China Construction Bank

[0465] What does this mean?

[0466] How to answer the question "What does this mean?"

[0467] }

[0468] System prompt{

[0469] You are a learned and knowledgeable person; please answer the above questions as objectively and accurately as possible.

[0470] }

[0471] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0472] S213, the text generation module generates text content that meets the requirements of the user prompt and the system prompt based on the prompt carried in the text generation instruction, and feeds back the generated text content to the intelligent processing module.

[0473] S214, the intelligent processing module displays the generated text content in the quick input text display box.

[0474] For details on the specific implementation of steps S213 and S214, please refer to the description of steps S113 and S114 in the above embodiments, which will not be repeated here.

[0475] Therefore, based on the quick input method provided in this application embodiment, system prompts and user prompts are generated according to the message content selected by the user, the input prompt, and the page feature information of the current APP. This ensures that the generated user prompts and system prompts not only cover the user's original intention but also are relevant to the current APP, business scenario, and screen content. Thus, the text content generated based on the generated user prompts and system prompts can both meet user needs and match the current APP, business scenario, and content displayed on the screen, further improving the user experience.

[0476] Furthermore, considering different business scenarios and varying user speaking styles, and to better enhance the user experience, some embodiments of this application also provide an entry point for users to select text styles. This allows users to modify the text style as needed, making the generated text content more suitable for their usage requirements.

[0477] To better understand the technical solutions provided in the embodiments of this application, the following will still refer to... Figure 6 The hardware structure shown and Figure 7 The electronic device with the software structure shown is a mobile phone. Taking the shortcut input method triggered by the input method application installed on the mobile phone as an example, combined with... Figure 12 The quick input scheme provided in the embodiments of this application will be described in detail.

[0478] See Figure 12 In example (1), when a user clicks the quick input control 10f-3, the phone responds to the user's action by updating the phone's user interface from interface 30f to... Figure 12 Interface 40f is shown in (2).

[0479] See Figure 12 In example (2), interface 40f” is similar to interface 40f. The difference is that, in the embodiments provided in this application, the floating window corresponding to the quick input function may include, in addition to the quick input text display box 10f-5, the select all control 10f-6, the cancel select all control 10f-7, and the prompt window 10f-8, a text style selection control 10f-15. That is, in the embodiments of this application, the floating window displayed on the overlay 10f-9 in interface 40f” is window W5.

[0480] The text style selection control 10f-15 is for user operation, and it pops up the text style window 10f-16 on the current interface, such as... Figure 12 The interface 50f” in the middle (3) is shown.

[0481] The uses and usage of the quick input text display box 10f-5, the select all control 10f-6, the cancel select all control 10f-7, and the prompt window 10f-8 can be found in the description of interface 40f in the above embodiments, and will not be repeated here.

[0482] Furthermore, it is noted that in some other embodiments of this application, text style selection controls 10f-15 may also be provided in the interface 40f'.

[0483] For ease of explanation, this application embodiment takes the addition of text style selection controls 10f-15 to interface 40f as an example.

[0484] For example, in some embodiments of this application, when a user clicks the select all control 10f-6 to select all message boxes on the overlay 10f-9 displayed in interface 40f", and then clicks the text style selection control 10f-15, the user interface will update from interface 40f to Figure 12 The interface shown in (3) is 50f”, which means that the text style window 10f-16 is displayed in the current interface.

[0485] See Figure 12 In (3), for example, the text style window 10f-16 may include one or more text styles, such as detailed, moderate, concise, etc.

[0486] See also Figure 12 In section (3), for example, if a user selects the "Moderate" style provided in text style windows 10f-16, the mobile phone responds to this user operation, and the user interface will be updated from interface 50f to Figure 12 The interface 50f* shown in (4) is as follows. That is, the text style displayed in the text style selection control 10f-15 will be updated from "detailed" to "moderate", as shown in the text style selection control 10f-15'.

[0487] After starting with the shortcut input function, based on Figure 9a The shortcut input method provided in the illustrated embodiment generates text content with a default style of "detailed". For example, after a user sets the text style to "moderate" using the text style selection control 10f-15 and text style window 10f-16 provided in this embodiment, when the user clicks the generate answer control 10d-10, the mobile phone responds to the user's operation by generating text content that matches the current APP, business scenario, and screen content, and describes it as "moderate," based on the content selected by the user and page characteristics. Figure 12In the interface shown in (5), the shortcut input text display box 10f-5 in the middle displays the following: "In China, sometimes people use 'CCB' to refer to having a boy and 'CMBO' to refer to having a girl. This saying originates from the idea that boys have more economic burdens when they grow up, such as buying a house and getting married, so they are likened to 'CCB' (CCB), while girls are considered to have less economic pressure and are likened to 'CMBO' (CMBO)."

[0488] For example, after the generated text content is displayed in the quick input text display box, the user can manually modify the text content displayed in the quick input text display box, or they can generate text content that meets the requirements by modifying the text style again. For example, if the user feels that the text content corresponding to the "moderate" style is still too long, in this case, the user can operate the text style selection control and the text style window, reselect the text style, such as the "concise" style, and then click the generate answer control 10f-10 again to generate more concise text content, such as "This saying originates from the concept that boys have more economic burdens when they grow up, such as buying a house and getting married, and are therefore compared to "China Construction Bank" (CCB), while girls are considered to have less economic pressure and are compared to "China Merchants Bank" (CMB).

[0489] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0490] Therefore, by adding a text style selection control, users can easily adjust the text style according to the actual scenario, thereby ensuring that the generated text content better meets the user's needs.

[0491] Furthermore, it should be noted that in some other embodiments of this application, for different apps, business scenarios, and user expression habits, after activating the quick input function, i.e., after using the quick input control to access the interface 40f", the text style displayed in the text style selection controls 10f-15 can be automatically switched to a text style suitable for the current app, business scenario, and user expression habits.

[0492] For example, when users are chatting on instant messaging apps, such as with friends, the text style can be automatically updated to the "concise" type.

[0493] For example, in scenarios where users reply to work emails using email apps, the text style can be automatically updated to the "detailed" type.

[0494] For example, in scenarios where users post comments on video apps, the text style can be automatically updated to the "humorous" type.

[0495] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0496] The following combination Figure 13 ,right Figure 12 The specific processing logic for implementing quick input in the scenario shown is explained.

[0497] See Figure 13 The quick input method provided in this application embodiment specifically includes:

[0498] S301, Input Method Management Service Registration: Input method monitoring for input method applications.

[0499] S302, After registering the input method listener, the input method management service will pop up the keyboard corresponding to the input method when it detects user operation on the text input box corresponding to the input method.

[0500] S303, when the keyboard corresponding to the input method is displayed, the intelligent processing module obtains the window information of the current interface from the window management service.

[0501] S304 The intelligent processing module determines the position information of the shortcut input control based on the obtained window information and transmits the position information to the window management service.

[0502] S305, the window management service creates a window to display shortcut input controls based on the location information determined by the intelligent processing module, and displays the shortcut input controls in the created window.

[0503] It should be noted that steps S301 to S305 in the embodiments of this application are different from those in the present application. Figure 9a Steps S101 to S105 in the illustrated embodiment are the same. For specific implementation details, please refer to the description of steps S101 to S105 in the above embodiment, which will not be repeated here.

[0504] S306, upon receiving a user operation on the shortcut input control, takes a screenshot of the current interface and transmits the screenshot to the feature extraction module.

[0505] S307, the feature extraction module performs feature extraction processing on the screenshot of the current interface, extracts the text content and page features of the current interface, and transmits the extracted feature information to the intelligent processing module.

[0506] It should be noted that steps S301 to S307 in the embodiments of this application are different from those in the present application. Figure 9aSteps S101 to S107 in the illustrated embodiment are the same. For specific implementation details, please refer to the description of steps S101 to S107 in the above embodiment, which will not be repeated here.

[0507] S308, the intelligent processing module performs masking processing on the current interface based on the feature information extracted by the feature extraction module, and displays a floating window corresponding to the quick input function on the mask.

[0508] It should be noted that, in the embodiments provided in this application, the masking processing performed on the current interface is the same as... Figure 9a The masking process performed in step S108 in the illustrated embodiment is the same. For specific implementation details, please refer to the description of step S108 in the above embodiment, which will not be repeated here.

[0509] Furthermore, it should be noted that in the embodiments provided in this application, the floating window corresponding to the shortcut input function displayed on the overlay is, for example, window W5 displayed in interface 40f". That is, in the embodiments provided in this application, the floating window corresponding to the shortcut input function includes not only the content in window W1, but also a text style selection control.

[0510] For details regarding the text style selection control, please refer to the description of the text style selection controls 10f-15 in the above embodiments; it will not be repeated here.

[0511] S309, the intelligent processing module responds to the user's selection of the content displayed in the overlay by displaying a text generation control on the current interface.

[0512] S310, when the user operates the text generation control, the intelligent processing module sends a prompt construction instruction to the prompt processing module.

[0513] S311, the prompt processing module constructs a prompt based on the information carried in the prompt construction instruction, and feeds back the constructed prompt to the intelligent processing module.

[0514] It should be noted that steps S309 to S311 in the embodiments of this application are different from those in the present application. Figure 9a Steps S109 to S111 in the illustrated embodiment are the same. For specific implementation details, please refer to the description of steps S107 to S111 in the above embodiment, which will not be repeated here.

[0515] S312, the intelligent processing module sends a text generation instruction to the text generation module.

[0516] Specifically, after the user clicks the generate answer control 10f-10, the intelligent processing module sends a prompt construction instruction to the prompt processing module and receives the prompt from the prompt processing module, the intelligent processing module will send a text generation instruction to the text generation module, carrying the user prompt, the system prompt, and the text style currently displayed in the text style selection control 10f-15.

[0517] Understandably, text style modifications can be made at any time after the text style selection control 10f-15 is displayed on the current interface and before the user clicks the generate answer control 10f-10.

[0518] S313, the text generation module generates text content that meets the requirements of the user prompt, system prompt, and selected text style according to the prompt carried in the text generation instruction, and feeds back the generated text content to the intelligent processing module.

[0519] S314, the intelligent processing module displays the generated text content in the quick input text display box.

[0520] For details on the specific implementation of steps S313 and S314, please refer to the description of steps S113 and S114 in the above embodiments, which will not be repeated here.

[0521] Therefore, based on the quick input method provided in this application embodiment, text content is generated according to the text style selected by the user and the automatically generated prompts. This makes the generated text content not only match the current APP, business scenario, and screen content, but also better fit the user's expression habits, thereby better meeting the user's usage needs and improving the user experience.

[0522] Furthermore, it should be noted that the shortcut input method provided in this application embodiment can be applied to various input method applications. Specifically, the shortcut input function's activation entry point, such as the shortcut input control 10f-3 mentioned in the above embodiment, is associated with the input method keyboard. The shortcut input control 10f-3 is only drawn and displayed based on the window information of the current interface when the input method keyboard is displayed on the current screen. It can also be used as a global intelligent assistant (voice assistant) to achieve the shortcut input experience described in the above embodiments.

[0523] To better understand this implementation method, the following will combine... Figure 14 and Figure 15 The use cases and specific implementation logic of the proposed implementation method are explained.

[0524] See Figure 14In example (1), when the phone's user interface is Interface 10g, if the user presses and holds the power button for 1 second or speaks a specified wake-up word, the phone will respond to the user's action and activate the voice assistant application. Accordingly, the user interface can be updated from Interface 10g to... Figure 14 The interface 20g is shown in (2).

[0525] See Figure 14 In example (2), the window 10g-2 corresponding to the voice assistant application displayed in the interface 20g may include one or more controls, such as a recommendation control (the control on the bottom left of the window 10g-2, used for user operation to trigger the operation of entering the recommendation interface corresponding to the voice assistant application), a voice acquisition control (the control in the middle of the bottom of the window 10g-2, used for user operation to trigger the operation of voice acquisition), a personal center control (the control on the bottom right of the window 10g-2, used for user operation to trigger the operation of entering the personal center interface corresponding to the voice assistant application), and controls for recommending events performed by the user, such as the control 10g-3 that triggers the quick input function provided in this application embodiment, and the control that triggers viewing Olympic events, etc.

[0526] It should be noted that the control for recommending user events provided in window 10g-2 can be determined based on multiple factors such as current real-time news, user preferences, currently running applications in the foreground, and the current business scenario.

[0527] For example, in some embodiments of this application, when the currently running application is a whitelisted application and the current business scenario is a whitelisted business scenario (such as a scenario involving editing text content), when the voice assistant application is invoked and window 10g-2 is displayed, control 10g-3 can be displayed in window 10g-2. Otherwise, control 10g-3 is not provided.

[0528] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0529] See also Figure 14 In (2), for example, when a user clicks control 10g-3, the phone responds to the user's action by activating a quick input function, for example, the user interface can be updated from interface 20g to... Figure 14 The interface 30g is shown in (3).

[0530] See Figure 14 In example (3), after the shortcut input function is started, the interface 20g can be processed by the processing method 1, processing method 2, or processing method 3 described in the above embodiments.

[0531] For ease of explanation, this application embodiment still uses processing method 2 as an example. Regarding the processing of interface 20g using processing method 2, please refer to the above embodiments for details. Figure 9b The description of the processing of interface 30f using processing method 2 shown is not repeated here.

[0532] See also Figure 14 In (3), for example, after processing the interface 20g using processing method 2 to obtain the mask layer 10g-4, the select all control 10g-5 and the deselect all control 10g-6 can be displayed on the mask layer 10g-4.

[0533] It should be noted that the Select All control 10g-5 in this embodiment has the same function as the Select All control 10f-6 in the above embodiment, and the Cancel Select All control 10g-6 has the same function as the Cancel Select All control 10f-7. For specific implementation details, please refer to the description of Select All control 10f-6 and Cancel Select All control 10f-7 in the above embodiment, which will not be repeated here.

[0534] See also Figure 14 In example (3), when a user clicks the select all control 10g-5, the phone responds to the user's operation by selecting all message boxes displayed in the overlay 10g-4, such as... Figure 14 The overlay 10g-4' in the interface 40g shown in (4) is displayed, and the answer generation control 10g-7 is displayed on the current interface.

[0535] See Figure 14 In example (4), when a user clicks the Generate Answer control 10g-7, the mobile phone responds to the user's operation by generating a prompt based on the content selected by the user and generating matching text content based on the generated prompt.

[0536] For example, after generating text content based on the prompts selected by the user, the user interface will update from interface 40g to... Figure 14 The interface 50f shown in (5) is as follows. That is, the overlay displayed on the current chat interface is canceled, and window 10g-2 is updated to the style of window 10g-2'.

[0537] See Figure 14 In example (5), window 10g-2' displays a quick input text display box 10g-8 and a copy control 10g-9. The text display area 10g-8 displays text content generated based on a prompt selected by the user.

[0538] See also Figure 14In example (5), when the user clicks the copy control 10g-9, the mobile phone responds to the user's operation by copying the text content displayed in the quick input text display box 10g-8, collapsing the window 10g-2', and automatically pasting the copied text content into the text input box 10g-1, such as... Figure 14 The text input box 10g-1' shown in the interface 60f (6) is shown.

[0539] For example, in some other embodiments of this application, after a user clicks the copy control 10g-9 to copy the text content displayed in the quick input text display box 10g-8, when the user clicks an area outside window 10g-2' in the current interface, such as the area displaying chat content, the mobile phone responds to the user's operation and collapses window 10g-2'. That is, the user interface can be restored from interface 50g to interface 10g.

[0540] For example, when a user long-presses the text input box 10g-1 in interface 10g, the phone responds to the user's action by displaying a paste entry. For example, when the user clicks the paste entry, the phone responds to the user's action by pasting the text content copied from the quick input text display box 10g-8 into the text input box 10g-1, that is, text input box 10g-1 updates text input box 10g-1'.

[0541] It should be understood that the above description is merely an example provided to better understand the technical solution of this embodiment, and is not intended as the only limitation on this embodiment.

[0542] This enables users to quickly input text using voice assistant applications, making it applicable to more business scenarios and better meeting diverse user needs.

[0543] The following combination Figure 15 ,right Figure 14 The specific processing logic for implementing quick input in the scenario shown is explained.

[0544] See Figure 15 The quick input method provided in this application embodiment specifically includes:

[0545] S401, in response to the operation of waking up the voice assistant application, the intelligent processing module obtains the window information of the current interface from the window management service.

[0546] For example, a user can press and hold the power button for 1 second, or use a pre-set voice wake-up word to activate the voice assistant application.

[0547] For details on the specific implementation of the intelligent processing module obtaining window information of the current interface from the window management service, please refer to the description of step S103 in the above embodiments, which will not be repeated here.

[0548] S402, the intelligent processing module determines the position information of the shortcut input control based on the obtained window information, and transmits the position information to the window management service.

[0549] S403, the window management service creates a window to display shortcut input controls based on the location information determined by the intelligent processing module, and displays the shortcut input controls in the created window.

[0550] Understandably, the shortcut input control in the embodiments of this application is, for example, control 10g-3 displayed on window 10-2 corresponding to the voice assistant application.

[0551] S404: Upon receiving a user operation on the shortcut input control, take a screenshot of the current interface and transmit the screenshot to the feature extraction module.

[0552] Understandably, in the embodiments of this application, the captured current interface is, for example, the chat interface below the layer where window 10g-2 is located, such as interface 10g.

[0553] S405, the feature extraction module performs feature extraction processing on the screenshot of the current interface, extracts the text content and page features of the current interface, and transmits the extracted feature information to the intelligent processing module.

[0554] S406, the intelligent processing module performs masking processing on the current interface based on the feature information extracted by the feature extraction module.

[0555] It should be noted that, in the embodiments of this application, the masking processing performed on the current interface is the same as... Figure 9a The masking process performed in step S108 in the illustrated embodiment is the same. For specific implementation details, please refer to the description of step S108 in the above embodiment, which will not be repeated here.

[0556] In addition, it should be noted that after applying a mask to the current interface, corresponding controls for quick input functions, such as select all and deselect all controls, can be displayed on the resulting mask.

[0557] For details regarding the Select All and Deselect All controls, please refer to the descriptions of the Select All control 10g-5 and Deselect All control 10g-6 in the above embodiments; they will not be repeated here.

[0558] S407, the intelligent processing module responds to the user's selection of the content displayed in the overlay by displaying a text generation control on the current interface.

[0559] S408, when the user operates the text generation control, the intelligent processing module sends a prompt construction instruction to the prompt processing module.

[0560] S409, the prompt processing module constructs a prompt based on the information carried in the prompt construction instruction, and feeds back the constructed prompt to the intelligent processing module.

[0561] S410, the intelligent processing module sends a text generation instruction to the text generation module.

[0562] S411, the text generation module generates text content that meets the requirements of the user prompt and the system prompt based on the prompt carried in the text generation instruction, and feeds back the generated text content to the intelligent processing module.

[0563] For details on the specific implementation of steps S402 to S411, please refer to the description of steps S104 to S113 in the above embodiments, which will not be repeated here.

[0564] S412, the intelligent processing module displays the received text content in the corresponding quick input text display box of the voice assistant application.

[0565] For example, display the quick input text display box 10g-8 in window 10g-2'.

[0566] For instructions on adding the generated text content to the quick input text display box 10g-8, please refer to [link / reference]. Figure 14 In the embodiment shown, the user interface is updated from interface 50f to the description of interface 60, which will not be repeated here.

[0567] Therefore, based on the quick input method provided in this application embodiment, information that matches the current application and the content displayed on the screen can be quickly generated without the user needing to input prompts.

[0568] Furthermore, since the quick input method provided in this application embodiment does not require launching an input method application, the text content can be automatically generated by using a globally available voice assistant application, thus making it applicable to more business scenarios and better meeting the diverse usage needs of users.

[0569] In addition, it should be noted that the quick input method implemented using the voice assistant application described above can also provide a prompt input box 10f-14 and / or a text style selection control 10f-15 in the user interface displayed after operating the control 10g-3.

[0570] Furthermore, it is understood that, in order to achieve the aforementioned functions, the electronic device includes hardware and / or software modules corresponding to the execution of each function. Based on the algorithmic steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware-driven or software-driven manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in conjunction with the embodiments, but such implementation should not be considered beyond the scope of this application.

[0571] Furthermore, it should be noted that in practical application scenarios, the shortcut input methods provided in the above embodiments implemented by electronic devices can also be executed by a chip system included in the electronic device, wherein the chip system may include a processor. The chip system can be coupled to a memory, enabling the chip system to call a computer program stored in the memory during runtime to implement the steps executed by the electronic device. The processor in the chip system can be an application processor or a non-application processor.

[0572] In addition, this application embodiment also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device performs the above-mentioned related method steps to implement the shortcut input method in the above embodiment.

[0573] In addition, this application also provides a computer program product that, when run on an electronic device, causes the electronic device to perform the aforementioned steps to achieve the shortcut input method described in the above embodiments.

[0574] In addition, embodiments of this application also provide a chip (which may also be a component or module), which may include one or more processing circuits and one or more transceiver pins; wherein the transceiver pins and the processing circuits communicate with each other through internal connection paths, and the processing circuits execute the above-mentioned related method steps to implement the quick input method in the above embodiments, so as to control the receiving pin to receive signals and control the transmitting pin to transmit signals.

[0575] Furthermore, as can be seen from the above description, the electronic devices, computer-readable storage media, computer program products, or chips provided in the embodiments of this application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0576] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A shortcut input method, characterized by, The method comprises: displaying a first interface, the first interface comprising chat content and a text input box; after receiving a first operation, displaying a shortcut input control; after receiving a second operation on the shortcut input control, displaying a second interface, the second interface comprising a first selection box, the chat content being displayed in the first selection box; after receiving a third operation on the first selection box, displaying a shortcut content generation control and displaying the chat content in a selected state; after receiving a fourth operation on the shortcut content generation control, displaying target chat content, the target chat content being associated with the chat content; after receiving a fifth operation on the target chat content, displaying the target chat content in the text input box; wherein the generation process of the target chat content comprises: after receiving the fourth operation on the shortcut content generation control, pre-processing the chat content in the selected state and the page features of the first interface extracted from a first interface screenshot to obtain a pre-processing result; wherein the pre-processing of the chat content and the page features to obtain a pre-processing result comprises deleting sensitive information in the chat content and deleting sensitive information in the page features; or replacing sensitive information in the chat content and replacing sensitive information in the page features performing intent recognition processing on the pre-processing result to determine a user intent; constructing a first prompt according to the pre-processing result and the user intent, the first prompt being used to identify the theme of the target chat content to be generated; constructing a second prompt according to the user intent and the page features, the second prompt being used to indicate the creative type corresponding to the target chat content to be generated; generating target chat content matching the theme identified by the first prompt and having the creative type indicated by the second prompt according to the first prompt and the second prompt.

2. The method of claim 1, wherein, The displaying of the second interface after receiving the second operation on the shortcut input control comprises: after receiving the second operation on the shortcut input control, performing a screenshot operation on the first interface to obtain a first interface screenshot corresponding to the first interface; performing feature extraction on the first interface screenshot to extract the chat content and message box information corresponding to the chat content included in the first interface screenshot; overlaying the first interface screenshot on the first interface; adding a mask layer to the first interface screenshot according to the chat content and the message box information corresponding to the chat content to obtain the second interface.

3. The method of claim 2, wherein, The adding of the mask layer to the first interface screenshot according to the chat content and the message box information corresponding to the chat content comprises: adding a layer to the first interface screenshot, the layer having a certain transparency; drawing the first selection box on the layer according to the message box information corresponding to the chat content; displaying the corresponding chat content in the first selection box.

4. The method according to any one of claims 1 to 3, characterized in that, The first operation is a user operation for waking up a voice assistant application.

5. The method of claim 4, wherein, The displaying the shortcut input control after receiving the first operation comprises: After receiving the first operation, an operation window corresponding to the voice assistant application is displayed on the first interface, and the operation window comprises the shortcut input control.

6. The method of claim 5, wherein, The second interface further comprises a global selection control, and the third operation on the first selection box is an operation on the global selection control.

7. The method according to any one of claims 1 to 3, characterized in that, The first operation is a user operation on the text input box. The displaying the shortcut input control after receiving the first operation comprises: After receiving the first operation, a keyboard corresponding to an input method application is displayed on the first interface, and the shortcut input control is displayed on a region corresponding to the keyboard.

8. The method of claim 7, wherein, The second interface further comprises a shortcut input window, and the shortcut input window comprises a global selection control, and the third operation on the first selection box is an operation on the global selection control.

9. The method of claim 8, wherein, The shortcut input window is a floating window.

10. The method according to claim 8 or 9, characterized in that, The shortcut input window further comprises a prompt input box, and the prompt input box is used for inputting a prompt by a user. After displaying the prompt input by the user in the prompt input box, the shortcut content generation control is displayed.

11. The method according to claim 8 or 9, characterized in that, The shortcut input window further comprises a text style selection control, and the text style selection control is used for selecting a representation style of the target chat content by a user.

12. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory and the processor are coupled, the memory stores program instructions, and the program instructions are executed by the processor to enable the electronic device to perform the shortcut input method in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that, The computer program enables an electronic device to perform the shortcut input method in any one of claims 1 to 11 when the computer program is executed on the electronic device.

Images