Interaction processing method and electronic equipment

Abstract

The invention discloses an interactive processing method and electronic equipment, and the method comprises the steps: responding to a text cursor appearing in an application interface of a first application, and controlling to output a first control; determining a first function triggered by an operation body based on the first control; in response to triggering of the first function, at least part of text content in a text input area of the application interface serves as prompt words to be input into an agent application, and the agent application and the first application run independently; obtaining a generation content returned by the agent application based on the cue word; and controlling the generated content to be displayed and output in the text input area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and more particularly, to an interaction processing method and an electronic device. BACKGROUND

[0002] Intelligent agent applications have been widely used in the work and life of users, bringing great convenience to the work and life of users. However, the current intelligent agent applications have certain limitations when used, such as the need to interact within the intelligent agent application, the need to manually operate the interaction content to complete the application, and the like. Therefore, the use and operation of intelligent agent applications are still relatively cumbersome, and the user experience needs to be further improved. SUMMARY

[0003] Therefore, the present application provides the following technical solutions.

[0004] The first aspect of the present application provides an interaction processing method, comprising:

[0005] In response to the appearance of a text cursor in the application interface of the first application, a first control is controlled to be output;

[0006] A first function triggered by the operation body based on the first control is determined;

[0007] In response to the triggering of the first function, at least part of the text content in the text input area of the application interface is input as a prompt word into an intelligent agent application, wherein the intelligent agent application and the first application run independently of each other;

[0008] The generated content returned by the intelligent agent application based on the prompt word is obtained;

[0009] The generated content is controlled to be displayed and output in the text input area.

[0010] In one possible implementation, in response to the appearance of a text cursor in the application interface of the first application, the first control is controlled to be output, comprising:

[0011] In response to the appearance of a text cursor in the application interface of the first application, the position of the text cursor is determined;

[0012] The output position of the first control is determined based on the position of the text cursor, the output position being close to the position of the text cursor and not occluding the text content in the text input area;

[0013] The first control is controlled to be output at the output position;

[0014] The determination of the output position of the first control based on the position of the text cursor comprises any one of the following:

[0015] determining a text line where the text cursor is located, and determining a region without text content at the beginning of the text line as an output position of the first control;

[0016] determining a region without text content around the text input region where no other control exists as the output position of the first control.

[0017] In one possible implementation, after inputting at least part of the text content in the text input region of the application interface as a prompt word to an intelligent agent, and before obtaining generated content returned by the intelligent agent based on the prompt word, the method further comprises repeatedly performing the following steps:

[0018] inputting first symbols into the text input region one by one, and deleting the input first symbols one by one after the first symbols reach a set number.

[0019] In one possible implementation, the determining operation comprises, based on a first function triggered by the first control:

[0020] in response to a first triggering operation on the first control, outputting an intelligent interaction function panel, the intelligent interaction function panel containing a plurality of intelligent interaction function controls;

[0021] obtaining a second triggering operation on any intelligent interaction function control, and determining that the first function is triggered.

[0022] In one possible implementation, the method further comprises at least one of the following:

[0023] adjusting display attributes of the at least part of the text content, so that the at least part of the text content has a first display effect;

[0024] controlling the generated content output displayed in the text input region to have a second display effect.

[0025] In one possible implementation, the controlling the generated content output displayed in the text input region comprises at least one of the following:

[0026] controlling the generated content to be output displayed after the prompt word in the text input region;

[0027] controlling the generated content to replace the prompt word to be output displayed in the text input region.

[0028] In one possible implementation, the method further comprises:

[0029] in response to appearance of a text cursor in an application interface of a second application, controlling the first control to be output;

[0030] Determine the first function triggered by the operator based on the first control;

[0031] In response to the first function being triggered, at least a portion of the text content in the text input area of ​​the second application is input as a prompt word into the agent application, wherein the agent application and the second application operate independently of each other;

[0032] Obtain the generated content returned by the intelligent agent application;

[0033] Control the display output of the generated content in the text input area of ​​the second application.

[0034] One possible implementation also includes:

[0035] The analysis determines the application type, contextual content, and / or user history interaction data of the first application;

[0036] Content requirements are determined based on the application type, contextual content, and / or user history interaction data.

[0037] The content requirements and at least a portion of the text content are synchronously input into the intelligent agent application so that the generated content has emotional expression characteristics that conform to the application type, context content and / or user historical interaction data.

[0038] In one possible implementation, the step of inputting at least a portion of the text content in the text input area of ​​the application interface as prompt words into the intelligent agent application includes:

[0039] The target content outside the text input area in the application interface, together with at least a portion of the text content in the text input area, are used as prompt words to input intelligent agents into the application.

[0040] The target content is determined based on the first function.

[0041] A second aspect of this application provides an electronic device, including a display, at least one processor, and a memory connected to the processor, wherein:

[0042] The display is used to output display content;

[0043] The memory is used to store computer programs;

[0044] The processor is configured to execute the computer program to enable the electronic device to: control the output of a first control in response to the appearance of a text cursor in the application interface of a first application; determine a first function triggered by an operator based on the first control; input at least a portion of the text content in the text input area of ​​the application interface as a prompt word into the intelligent agent application in response to the first function being triggered; obtain generated content returned by the intelligent agent application based on the prompt word; and control the generated content to be displayed and output in the text input area. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0046] Figure 1 This is a flowchart of an interactive processing method disclosed in an embodiment of this application;

[0047] Figure 2 This is a flowchart of the first control for control output disclosed in an embodiment of this application;

[0048] Figure 3 This is an example diagram of the output position page of a first control disclosed in an embodiment of this application;

[0049] Figure 4 This is another example diagram of the first control output position page disclosed in an embodiment of this application;

[0050] Figure 5 This is a flowchart illustrating the determination of a first function as disclosed in an embodiment of this application;

[0051] Figure 6 This is a schematic diagram illustrating the display states at different stages of triggering the intelligent interaction function of the application interface disclosed in the embodiments of this application;

[0052] Figure 7 This is a schematic diagram of the structure of an interactive processing device disclosed in an embodiment of this application;

[0053] Figure 8 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0054] 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, and 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.

[0055] The embodiments of this application can be applied to electronic devices. This application does not limit the product form of the electronic device, which may include but is not limited to smartphones, tablets, wearable devices, personal computers (PCs), netbooks, etc., and can be selected according to application requirements.

[0056] Figure 1 This is a flowchart illustrating an interactive processing method disclosed in an embodiment of this application. See also... Figure 1 As shown, the interaction processing method may include:

[0057] Step 101: In response to the appearance of a text cursor in the application interface of the first application, control the output of the first control.

[0058] The type of the first application is not fixed and can be an office application, an instant messaging application, etc. As long as there is an application that requires text or voice input, it can be the first application.

[0059] The first application includes a text input area where users can input text. When a user clicks on the text input area, a text cursor appears and flashes to indicate the text input location.

[0060] In this application, when a text cursor appears in the text input area of ​​the first application, the application interface of the first application automatically brings up a first control. The first control is a prompt control of the intelligent agent application. Based on this first control, the user can call the intelligent agent application to perform artificial intelligence writing-related tasks.

[0061] Step 102: Determine the first function triggered by the operator based on the first control.

[0062] If a user needs to use the AI ​​writing function, they can click to trigger the first control and select the corresponding AI writing function. For example, AI writing functions include intelligent continuation writing, intelligent translation, and intelligent proofreading. If the user triggers the intelligent continuation writing function based on the first control, the first application will automatically call the intelligent agent application to perform the corresponding processing based on the intelligent continuation writing function triggered by the user.

[0063] Step 103: In response to the first function being triggered, at least a portion of the text content in the text input area of ​​the application interface is input as prompt words into the intelligent agent application.

[0064] After the user triggers the first function based on the first control, at least a portion of the content in the text input area of ​​the application interface is automatically input as prompt words into the intelligent agent application, so that the intelligent agent application performs the corresponding functional operation. The intelligent agent application and the first application run independently, but their collaborative operation is triggered by the user within the application interface of the first application; the user does not need to exit the first application interface or manually launch the intelligent agent application during the process.

[0065] Step 104: Obtain the generated content returned by the intelligent agent application based on the prompt word.

[0066] After receiving the prompt words of at least part of the text content, the intelligent agent application performs an intelligent generation task in conjunction with the first function selected by the user to obtain generated content, and directly transmits the obtained generated content to the first application.

[0067] Step 105: Control the generated content to be displayed and output in the text input area.

[0068] After receiving the generated content returned by the agent application, the first application controls the automatic display and output of the generated content in the text input area. Throughout the entire implementation of this application, the user does not "leave" the application interface of the first application. The invocation of the agent application, the return of generated content, and the display and output of the generated content in the text input area are all executed automatically without manual intervention from the user.

[0069] The interactive processing method described in this application automatically outputs a first control that can trigger the invocation of the intelligent agent application when a text cursor appears on the application interface. The user can directly input the prompt words of the intelligent agent application in the text input area of ​​the application interface and trigger the first control. After the intelligent agent application obtains and returns the generated content based on the prompt words, the generated content is directly displayed and output in the text input area of ​​the application interface. The user does not need to switch the application interface during the entire process, and the participation of the intelligent agent application is imperceptible to the user, thereby bringing the user a better artificial intelligence writing experience.

[0070] Figure 2 This is a flowchart of the first control for control output disclosed in an embodiment of this application. Figure 2 As shown, the response to the appearance of a text cursor in the application interface of the first application, controlling the output of the first control, may include:

[0071] Step 201: In response to the appearance of a text cursor in the application interface of the first application, determine the position of the text cursor.

[0072] The text cursor typically indicates the position where the user needs to enter text, or the input position when the user is typing.

[0073] Step 202: Determine the output position of the first control based on the position of the text cursor. The output position is close to the position of the text cursor and does not obscure the text content in the text input area.

[0074] The output position of the first control is close to the text cursor to easily alert the user to its presence and facilitate user operation. The input position of the first control does not obstruct the text content in the text input area, ensuring it does not interfere with the user's ongoing text writing or viewing of existing text. Furthermore, in this implementation, the output position of the first control will not obstruct any other content of substantial display significance outside the text input area of ​​the application interface.

[0075] Determining the output position of the first control can be achieved, for example, by determining the text line where the text cursor is located, and defining the area at the beginning of the text line without any text content as the output position of the first control. Figure 3 As shown. For example, the area without text content surrounding the text input area, where no other controls exist, can be defined as the output position of the first control, such as... Figure 4 As shown.

[0076] Step 203: Control the output of the first control at the output position.

[0077] Once the output position of the first control is determined, it can be directly displayed at that position for user use.

[0078] This embodiment does not impose a fixed restriction on the implementation of determining the output position of the first control. In practical applications, it can be flexibly configured based on the layout and display content of the application interface of the first application, as long as the output of the first control does not obstruct other display content in the application interface.

[0079] In some implementations, the first control can be a floating control. After the first control is output at the output position, the user can drag and drop the first control according to their own needs and place it anywhere in the application interface.

[0080] In one implementation, after inputting at least a portion of the text content in the text input area of ​​the application interface as a prompt word into the agent application, and before obtaining the generated content returned by the agent application based on the prompt word, the following steps are repeated: inputting first symbols one by one into the text input area, and deleting the input first symbols one by one after the first symbols reach a set number.

[0081] The first symbol can be, but is not limited to, ".". For example, before the intelligent generation task is triggered and the generated content is received, to optimize the user's waiting experience, "." can be displayed sequentially at fixed time intervals at the position where the generated content needs to be output. After the number of "." increases to a set number, such as 3 or 5, the displayed "." are then deleted one by one, thus simulating the effect of dynamic loading. Other methods that can reflect the effect of dynamic loading can also be used in the implementation, such as displaying a light spot that dynamically rotates along a ring at the position where the generated content is to be output.

[0082] Figure 5 This is a flowchart illustrating the determination of a first function as disclosed in an embodiment of this application. See also... Figure 5 As shown, in one implementation, the determination of the operation body based on the first function triggered by the first control may include:

[0083] Step 501: In response to the first trigger operation on the first control, output the intelligent interactive function panel, which contains a plurality of intelligent interactive function controls.

[0084] The first control is only a small control in the application interface, used only to indicate to the user that the control exists. When the user wants to use the AI ​​writing function, they can click to trigger the first control. After the user clicks the first control, a smart interaction function panel or menu pops up on one side of the first control, which includes multiple selectable smart interaction controls. Different smart interaction controls correspond to different smart interaction functions, such as smart continuation writing, smart translation, smart proofreading, etc.

[0085] Step 502: Obtain the second trigger operation for any smart interactive function control, and determine to trigger the first function.

[0086] Users select the corresponding intelligent interaction function from the intelligent interaction function panel based on their current needs, thereby determining to trigger the intelligent interaction function, which is the first function.

[0087] In practical applications, there are no fixed restrictions on the presentation format and method of intelligent interactive function panels or menus, as long as users can clearly understand what intelligent interactive functions are available in the intelligent interactive function panels or menus.

[0088] In one implementation, the interaction processing method may further include: adjusting the display attributes of the at least part of the text content to give the at least part of the text content a first display effect.

[0089] Understandably, intelligent agent applications require different prompt words when performing different intelligent interaction functions. For example, for intelligent continuation writing tasks, it may be necessary to input all the preceding text in the text input area as prompt words into the intelligent agent application so that the application can generate higher-quality continuation content based on all the preceding text. However, for tasks with direct instructions, that is, tasks where the user directly writes down the question or request, only the question or instruction entered by the user needs to be used as prompt words, such as "Please write a poem praising the magnificence of mountains and rivers" entered by the user in the text input area.

[0090] To help users more intuitively understand which part of the content is the prompt word for the current intelligent interaction task, the display attributes of the text content used as the prompt word in the text input area can be adjusted to be different from the display attributes of other content or different from the display attributes of regular text. The display attributes may include, but are not limited to, at least one of the following: font color, font display format (such as italic, bold), font background color, etc.

[0091] In one implementation, the interactive processing method may further include: controlling the generated content displayed in the text input area to have a second display effect.

[0092] Similarly, when the generated content is displayed in the text input area, it can also be presented in a way that distinguishes it from other content display attributes or regular text content display attributes, so as to indicate which part of the content in the user's text input area is the content generated by the agent application.

[0093] Figure 6 This document presents schematic diagrams illustrating the display states at different stages of triggering the intelligent interaction function in the application interface disclosed in this application embodiment. The left image is an example of a user triggering the first control to display the intelligent interaction function panel; the middle image is an example of a user clicking and selecting an intelligent interaction function and waiting for the returned generated content; and the right image is an example of the generated content returned by the intelligent agent application being displayed and output on the application interface. This can be combined with… Figure 6 Understand the content described in this embodiment.

[0094] In other implementations, the step of using at least a portion of the text content in the text input area of ​​the application interface as prompt words to input intelligent agents may include: using target content outside the text input area of ​​the application interface and at least a portion of the text content in the text input area together as prompt words to input intelligent agents; wherein the target content is determined based on the first function.

[0095] In other words, the content input as prompts into an intelligent agent application can also include content outside the text input area. For example, in an instant messaging application, if you type "Check the definition of the technical name that Zhang San just sent" in the text input area, it will output both "Check the definition of the technical name that Zhang San just sent" in the text input area and the chat history box outside the text input area (such as...). Figure 4 The message content (target content) sent by Zhang San in the middle (indicated by the label) is used as a prompt word to input the intelligent agent application.

[0096] In one implementation, controlling the display of the generated content in the text input area may include: controlling the generated content to be displayed after the prompt word in the text input area. For example... Figure 6 As shown in the middle right figure, the generated content is displayed after the original text content in the text input area.

[0097] In other implementations, controlling the display of the generated content in the text input area may also include: controlling the generated content to replace the prompt word in the text input area. For example, as mentioned above, if the user enters "Please write a poem praising the magnificence of mountains and rivers" in the text input area, after the intelligent agent application generates a poem, the generated poem will replace the content "Please write a poem praising the magnificence of mountains and rivers" in the text input area of ​​the first application's interface, that is, delete "Please write a poem praising the magnificence of mountains and rivers", and display the poem generated by the intelligent agent application in the same position.

[0098] Of course, the above implementations are just two examples. In other implementations, the generated content can be displayed in the text input area in other ways. For example, translating the chat history content in a chat history box (not the text input area) can result in the result being displayed directly below the corresponding chat history content (not in the text input area).

[0099] In other implementations, after controlling the generated content to be displayed and output in the text input area, it may further include: inputting at least one indicator control (such as...) in the text input area. Figure 6 The right-hand side of the figure shows the Reject control and the Try again control. Different indicator boxes are used to indicate different processing operations. The processing operations include at least one of the following: withdrawing the generated content (corresponding to the Reject control), trying to generate again (corresponding to the Try again control), and using the currently generated content.

[0100] In other implementations, the interaction processing method may further include: analyzing and determining the application type, context content, and / or user historical interaction data of the first application; determining content requirements based on the application type, context content, and / or user historical interaction data; and synchronously inputting the content requirements and at least part of the text content into the agent application so that the generated content has emotional expression characteristics that conform to the application type, context content, and / or user historical interaction data.

[0101] For example, if the first application is a work assistant application, the generated content will conform to the language habits and tone of the work scenario when using the intelligent interaction function; if the first application is a social interaction application, the generated content will conform to the language habits and tone of daily communication.

[0102] For example, in chat applications, it is possible to obtain the user's history and the communication content of the interaction partners, analyze language features, clarify the current interaction atmosphere, and obtain the corresponding generated content based on the intelligent agent application.

[0103] In other implementations, the interaction processing method may further include: responding to the appearance of a text cursor in the application interface of the second application, controlling the output of the first control; determining a first function triggered by the operator based on the first control; responding to the first function being triggered, inputting at least a portion of the text content in the text input area of ​​the second application as a prompt word into the agent application, wherein the agent application and the second application run independently of each other; obtaining the generated content returned by the agent application; and controlling the generated content to be displayed and output in the text input area of ​​the second application.

[0104] The solution disclosed in this application can bring up the first control to display the output on the corresponding application interface when a text cursor appears in the application interface of different applications. This supports users to conveniently and immersively use the intelligent interaction function. During the process, users do not need to exit the application interface to manually call the intelligent agent application, nor do they need to manually obtain the content generated by the intelligent agent application. The overall implementation process is very user-friendly.

[0105] The technical solution disclosed in this application, through a more immersive operating experience and a shorter operation process, achieves an embedded system-level AI writing experience within mainstream software on PCs, mobile phones, and tablets. The entire operation process is shorter, and the experience is more immersive and faster. Furthermore, when the first control is triggered, it can obtain the user's current software and context, and after corresponding processing and analysis, the intelligent agent application can automatically generate the corresponding tone and text according to different scenarios.

[0106] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0107] The methods described in the above-disclosed embodiments of this application are detailed in terms of their specific implementation methods. These methods can be implemented using various types of devices. Therefore, this application also discloses a device, and specific embodiments are given below for detailed explanation.

[0108] Figure 7 This is a schematic diagram of the structure of an interactive processing device disclosed in an embodiment of this application. See also... Figure 7 As shown, the interactive processing device 70 may include:

[0109] Control output module 701: In response to the appearance of a text cursor in the application interface of the first application, control the output of the first control.

[0110] Function determination module 702: Determines the first function triggered by the operation body based on the first control.

[0111] The prompt word processing module 703 is used to respond to the first function being triggered by inputting at least a portion of the text content in the text input area of ​​the application interface as prompt words into the intelligent agent application, wherein the intelligent agent application and the first application operate independently of each other.

[0112] Content acquisition module 704: Acquires the generated content returned by the intelligent agent application based on the prompt words.

[0113] Display output module 705: controls the generated content to be displayed and output in the text input area.

[0114] The interactive processing device described in this application automatically outputs a first control that can trigger the invocation of the intelligent agent application when a text cursor appears on the application interface. The user can directly input the prompt words of the intelligent agent application in the text input area of ​​the application interface and trigger the first control. After the intelligent agent application obtains and returns the generated content based on the prompt words, the generated content is directly displayed and output in the text input area of ​​the application interface. The user does not need to switch the application interface during the entire process, and the participation of the intelligent agent application is imperceptible to the user, thereby bringing the user a better artificial intelligence writing experience.

[0115] The specific implementation of the above-mentioned interactive processing device and its various modules, as well as other possible implementation methods, can be found in the relevant sections of the method embodiments, and will not be repeated here.

[0116] Any of the interactive processing devices described in the above embodiments includes a processor and a memory. The control output module, function determination module, prompt word processing module, content acquisition module, display output module, etc. in the above embodiments are all stored as program modules in the memory, and the processor executes the above program modules stored in the memory to realize the corresponding functions.

[0117] The processor contains a kernel, which retrieves the corresponding program modules from memory. One or more kernels can be configured, and the processing of backtracking data can be achieved by adjusting kernel parameters.

[0118] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0119] In an exemplary embodiment, a computer-readable storage medium is also provided, which can be directly loaded into the internal memory of a computer, and contains software code. After being loaded and executed by the computer, the computer program can implement the steps shown in any of the embodiments of the above-described interactive processing method.

[0120] In an exemplary embodiment, a computer program product is also provided, which can be directly loaded into the internal memory of a computer and contains software code. After being loaded and executed by the computer, the computer program can implement the steps shown in any embodiment of the interactive processing method described above.

[0121] Furthermore, embodiments of this application provide an electronic device. Figure 8 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. See also... Figure 8 As shown, the electronic device 80 includes a display 801, at least one processor 802, at least one memory 803 connected to the processor, and a bus 804; wherein the display, processor, and memory communicate with each other through the bus.

[0122] The display is used to output display content;

[0123] The memory is used to store computer programs;

[0124] The processor is configured to execute the computer program to enable the electronic device to: control the output of a first control in response to the appearance of a text cursor in the application interface of a first application; determine a first function triggered by an operator based on the first control; input at least a portion of the text content in the text input area of ​​the application interface as a prompt word into the intelligent agent application in response to the first function being triggered; obtain generated content returned by the intelligent agent application based on the prompt word; and control the generated content to be displayed and output in the text input area.

[0125] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0126] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0128] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An interaction processing method, comprising: in response to a text cursor appearing in an application interface of a first application, controlling output of a first control; determining a first function triggered by an operation body based on the first control; in response to the first function being triggered, inputting at least part of text content in a text input area of the application interface as a prompt word into an intelligent body application, wherein the intelligent body application and the first application run independently of each other; obtaining generated content returned by the intelligent body application based on the prompt word; controlling display output of the generated content in the text input area.

2. The interaction processing method of claim 1, wherein the response to the text cursor appearing in the application interface of the first application, controlling output of the first control, comprises: in response to the text cursor appearing in the application interface of the first application, determining a position of the text cursor; determining an output position of the first control based on the position of the text cursor, the output position being close to the position of the text cursor and not occluding the text content in the text input area; controlling output of the first control at the output position; wherein the determination of the output position of the first control based on the position of the text cursor comprises any one of the following: determining a text line where the text cursor is located, and determining a region without text content at a beginning of the text line as the output position of the first control; determining a region without text content around the text input area as the output position of the first control.

3. The interaction processing method of claim 1, wherein after the inputting of the at least part of the text content in the text input area of the application interface as the prompt word into the intelligent body application, and before the obtaining of the generated content returned by the intelligent body application based on the prompt word, the method further comprises repeatedly performing the following steps: inputting first symbols one by one into the text input area, and deleting the input first symbols one by one after the first symbols reach a set number.

4. The interaction processing method of claim 1, wherein the determination of the first function triggered by the operation body based on the first control comprises: in response to a first trigger operation for the first control, outputting an intelligent interaction function panel, the intelligent interaction function panel containing a plurality of intelligent interaction function controls; obtaining a second trigger operation for any intelligent interaction function control, and determining the first function triggered.

5. The interaction processing method of claim 1, further comprising at least one of the following: adjusting display properties of the at least part of the text content, so that the at least part of the text content has a first display effect; controlling the generated content displayed and output in the text input area to have a second display effect.

6. The interaction processing method of claim 1, wherein the controlling of the display output of the generated content in the text input area comprises at least one of the following: controlling the display output of the generated content after the prompt word in the text input area; controlling the display output of the generated content to replace the prompt word in the text input area.

7. The interaction processing method of claim 1, further comprising: In response to the appearance of a text cursor in the application interface of the second application, the first control is outputted; A first function triggered by the operation body based on the first control is determined; In response to the triggering of the first function, at least part of the text content in the text input area of the second application is inputted into the agent application as a prompt word, wherein the agent application and the second application are independently operated; The generated content returned by the agent application is obtained; The generated content is outputted and displayed in the text input area of the second application.

8. The interaction processing method of claim 1, further comprising: determining the application type, context content and / or user historical interaction data of the first application; determining content requirements based on the application type, context content and / or user historical interaction data; synchronizing the content requirements and the at least part of the text content into the agent application, so that the generated content has emotional expression characteristics conforming to the application type, context content and / or user historical interaction data.

9. The interaction processing method of claim 1, wherein the inputting of the at least part of the text content in the text input area of the application interface into the agent application as a prompt word comprises: inputting target content outside the text input area in the application interface and the at least part of the text content in the text input area into the agent application as a prompt word together; wherein the target content is determined based on the first function.

10. An electronic device comprising a display, at least one processor and a memory connected to the processor, wherein: the display is used to output display content; the memory is used to store a computer program; the processor is used to execute the computer program, so that the electronic device can realize: in response to the appearance of a text cursor in the application interface of a first application, a first control is outputted; a first function triggered by the operation body based on the first control is determined; in response to the triggering of the first function, at least part of the text content in the text input area of the application interface is inputted into the agent application as a prompt word; the generated content returned by the agent application based on the prompt word is obtained; and the generated content is outputted and displayed in the text input area.

Images