Interaction page display method and device, electronic equipment and storage medium

Abstract

The invention provides an interaction page display method and device, electronic equipment and a storage medium, according to the embodiment of the invention, a page loading end can firstly obtain interaction information input by a user based on a session box, and the session box takes a virtual object as an interaction main body to perform session interaction with the user; identifying the interaction information to trigger the calling of the function display component of the virtual object; then determining the function display component updated after the displayed function display component in the session box responds to the interaction information input by the user, and completely displaying the function display component in the session box; and finally, updating the display content of the session box according to the updated function display component. By adopting the scheme, whether the updated function display component is completely displayed in the session box or not can be judged according to the content increased by multiple rounds of sessions, and the updated function display component is displayed when the updated function display component is completely displayed, so that the amount of information which can be borne in each unit of screen is increased, time is saved, and user experience is improved.

Description

Technical Field

[0001] This application relates to the field of computer technologies, and in particular, to a method, apparatus, electronic device, and storage medium for displaying an interactive page. Background Art

[0002] With the development of Artificial Intelligence (AI) technology, users of computers or smartphones can conduct one-round or multi-round session interactions with the AI assistants (virtual objects) of corresponding service providers through page loading terminals such as website pages, computer software, and mobile software (APPs) to achieve purposes such as booking hotels, flights, shopping, etc. In this process, the page loading terminal can display the content of the session interaction between the user and the AI assistant through an interactive function display component, clearly display the key information during the session interaction, such as the booked flight number, departure time, seat, amount, etc., and provide corresponding confirmation buttons for the user to operate.

[0003] However, in the traditional display method through an interactive function display component, in a multi-round session scenario, each time the user converses with the AI assistant, a new one will pop up. Multiple interactive function display components occupy too much area of the display page of the page loading terminal, reducing the amount of information that can be carried per unit screen in the display page of the page loading terminal, and increasing the time cost for the user to obtain information; at the same time, in order to display new information, the display page needs to be refreshed over a large area, which will cause visual flickering and increase the health burden on the user for reading information; moreover, each time the page loading terminal creates a new interactive function display component, it requires additional time resources, resulting in an extended waiting time for the user; frequent card responses may also make it difficult for the user to quickly find the key information for positioning.

[0004] Therefore, there is an urgent need for a new display solution for interactive pages to solve one or more of the above problems. Summary of the Invention

[0005] Embodiments of this application provide a method, apparatus, electronic device, and storage medium for displaying an interactive page to solve one or more of the above technical problems.

[0006] In a first aspect, an embodiment of the present application provides a method for displaying an interactive page, which is applied to a page loading end. The method includes: obtaining interaction information input by a user based on a conversation box, where the conversation box uses a virtual object as an interaction subject to perform conversation interaction with the user; identifying that the interaction information triggers a call to a function display component of the virtual object; determining a function display component updated after the displayed function display component in the conversation box responds to the interaction information input by the user, and completely displaying it in the conversation box; and updating the display content of the conversation box according to the updated function display component.

[0007] In a second aspect, an embodiment of the present application provides a method for displaying an interactive page, which is applied to a server end. The method includes: obtaining interaction information input by a user based on a conversation box sent by a page loading end, where the conversation box uses a virtual object as an interaction subject to perform conversation interaction with the user; sending feedback information corresponding to the interaction information to the page loading end, so that after the page loading end identifies that the interaction information triggers a call to a function display component of the virtual object, when it is determined that the displayed function display component in the conversation box is updated in combination with the feedback information and completely displayed in the conversation box, the display content of the conversation box is updated according to the updated function display component.

[0008] In a third aspect, an embodiment of the present application provides a method for displaying an interactive page, which is applied to a page loading end. The method includes: obtaining first interaction information input by a user based on a conversation box; displaying the first interaction information in the visible area of the page loading end; displaying a function display component in the visible area of the page loading end according to the first interaction information, where the function display component displays information related to the first interaction information; obtaining second interaction information input by the user based on the conversation box; and at least partially updating the information of the function display component according to the second interaction information without changing the position of the function display component in the visible area.

[0009] In a fourth aspect, an embodiment of the present application provides a device for displaying an interactive page, which is applied to a page loading end. The device includes: an interaction information obtaining module, configured to obtain interaction information input by a user based on a conversation box, where the conversation box uses a virtual object as an interaction subject to perform conversation interaction with the user; an interaction information identifying module, configured to identify that the interaction information triggers a call to a function display component of the virtual object; a complete display determining module, configured to determine a function display component updated after the displayed function display component in the conversation box responds to the interaction information input by the user, and completely display it in the conversation box; and a display content updating module, configured to update the display content of the conversation box according to the updated function display component.

[0010] Fifth aspect, an embodiment of the present application provides a display device for an interactive page, which is applied to a server. The device includes: an interaction information acquisition module, configured to acquire interaction information input by a user based on a conversation box sent by a page loading end, where the conversation box uses a virtual object as an interaction subject to perform conversation interaction with the user; a feedback information sending module, configured to send feedback information corresponding to the interaction information to the page loading end, so that after the page loading end recognizes that the interaction information triggers the invocation of a function display component of the virtual object, and after determining that the displayed function display component in the conversation box is combined and updated with the feedback information and completely displayed in the conversation box, the display content of the conversation box is updated according to the updated function display component.

[0011] Sixth aspect, an embodiment of the present application provides a display device for an interactive page, which is applied to a page loading end. The device includes: a first interaction information acquisition module, configured to acquire first interaction information input by a user based on a conversation box; a first interaction information display module, configured to display the first interaction information in a visible area of the page loading end; a function display component display module, configured to display a function display component in the visible area of the page loading end according to the first interaction information, where the function display component displays information related to the first interaction information; a second interaction information acquisition module, configured to acquire second interaction information input by the user based on the conversation box; a function display component update module, configured to at least partially update the information of the function display component according to the second interaction information without changing the position of the function display component in the visible area.

[0012] Seventh aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory. When the processor executes the computer program, the method described in any one of the above is implemented.

[0013] Eighth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method described in any one of the above is implemented.

[0014] Ninth aspect, an embodiment of the present application provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the method described in any one of the above is implemented.

[0015] According to the embodiment of the present application, the page loading end can first obtain the interaction information input by the user based on the conversation box, wherein the conversation box uses the virtual object as the interaction subject to conduct a conversation interaction with the user; then identify the interaction information to trigger the call of the function display component of the virtual object; then determine the function display component that has been displayed in the conversation box and the function display component that has been updated after responding to the interaction information input by the user, and fully display it in the conversation box; finally, update the display content of the conversation box according to the updated function display component. By adopting the above scheme, during the interaction process of multiple rounds of conversations between the user and the virtual object (artificial intelligence assistant), according to the added conversation content, it can be determined whether the function display component that has been displayed in the current conversation box and the function display component that has been updated after responding to the interaction information input by the user are fully displayed in the conversation box, and if they are fully displayed, the content of the updated function display component (updated component) is displayed.

[0016] In addition, the embodiment of the present application can also generate another function display component (generation component) in response to the interactive information input by the user when it is determined that the updated function display component is not displayed or is not fully displayed in the conversation box, and mark the updated content, so that the display method of the interactive page is more flexible, and the amount of information that can be carried per unit screen in the conversation box on the page loading end is increased, so that the user can quickly find key information; since part of the content in the solution can be displayed by updating the function display component, the display page of the conversation box does not need to be refreshed over a large area, which reduces visual flicker and the additional time resources required to create a new function display component, reducing the time cost and health cost of users obtaining information, thereby optimizing the user's interactive experience with the artificial intelligence assistant.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments according to the present application and should not be regarded as limiting the scope of the present application.

[0019] Figure 1 A schematic diagram showing a flow chart of a display solution for an interactive page provided in an embodiment of the present application is shown;

[0020] Figure 2 A schematic diagram of the flow of front-end and back-end interactions of an interactive page display solution provided in an embodiment of the present application is shown;

[0021] Figure 3 shows a flowchart of a method for displaying an interactive page provided in an embodiment of the present application;

[0022] Figure 4 shows a schematic diagram of the display of a function display component in a display solution of an interactive page in a traditional multi-round dialogue scenario provided in an embodiment of the present application;

[0023] Figure 5 shows a schematic diagram of the display of a function display component in a display solution of an interactive page provided in an embodiment of the present application;

[0024] Figure 6 shows a schematic diagram for comparing the height of the display information after adding a function display component for feedback information in the page document flow with the height of the function display component for adding feedback information and the visible content height of the conversation box in a display solution of an interactive page provided in an embodiment of the present application;

[0025] Figure 7 shows a schematic diagram of adding a reminder display element to an updated function display component provided in an embodiment of the present application;

[0026] Figure 8 shows a flowchart of another method for displaying an interactive page provided in an embodiment of the present application;

[0027] Figure 9 shows a flowchart of yet another method for displaying an interactive page provided in an embodiment of the present application;

[0028] Figure 10 shows a block diagram of a display device for an interactive page provided in an embodiment of the present application;

[0029] Figure 11 shows a block diagram of another display device for an interactive page provided in an embodiment of the present application;

[0030] Figure 12 shows a block diagram of yet another display device for an interactive page provided in an embodiment of the present application; and

[0031] Figure 13 shows a block diagram of an electronic device for implementing an embodiment of the present application. Detailed Description of the Embodiments

[0032] In the following, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the concept or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary in nature and not restrictive.

[0033] To facilitate the understanding of the technical solutions of the embodiments of the present application, the related technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the protection scope of the embodiments of the present application.

[0034] Figure 1 The flowchart shows a display scheme of an interactive page provided in an embodiment of the present application. As Figure 1 shown, the display method of the interactive page provided in the embodiment of the present application can be applied to the page loading end. After the user inputs interactive information for communicating with a virtual object (such as an artificial intelligence assistant, AI Agent) through a conversation box on the page loading end such as a website page, a computer software, or a mobile software (APP) (the user initiates the interaction), the page loading end can obtain the interactive information input by the user based on the conversation box and identify that the interactive information triggers the invocation of the function display component of the virtual object. For example, the page loading end can transmit the interactive information input by the user (in the form of text, voice, etc.) to the server end. The server end can obtain the reply of the virtual object's server to the interactive information input by the user and process the reply into message information and feedback it to the page loading end. In the message information fed back by the server end, it can include the unique identifier (UUID) of the reply mark of the virtual object, the service type (anchor type), the service information, etc. The page loading end can determine whether this round of interactive information belongs to the first interaction (whether it is the first time) according to the message information fed back by the server end. For example, after the user first sends the interactive information of "I want to record an entry" to the virtual object through the page loading end, the reply of the virtual object's server to the interactive information input by the user can be a sentence such as "May I ask how much is the amount to be recorded?" to guide the user to state necessary information such as the amount and the business area for recording the entry. At this time, since the information provided by the user for recording the entry is insufficient (not meeting the preset conditions for invoking the function display component in the business type of recording the entry), the message information fed back by the server end may not mark a unique identifier for this reply of the virtual object, but only handle it as an ordinary conversation, so the invocation of the function display component of the virtual object will not be triggered. If the interactive information between the user and the virtual object already includes all the necessary information in the preset conditions for recording the entry, the message information fed back by the server end can mark a unique identifier for the reply of the virtual object, thereby triggering the invocation of the function display component of the virtual object, that is, this round of interactive information belongs to the first interaction (whether it is the first time - yes) in the scenario of the "recording the entry" service type. At this time, the page loading end can invoke the function display component of the virtual object, generate an initial function display component and display it (generate an initial card - display the card).

[0035] Next, when it is determined that the updated functional display component after the displayed functional display component in the conversation box updates in response to the interaction information input by the user can be completely displayed in the conversation box, the display content of the conversation box can be updated according to the updated functional display component. For example, continuing with the previous example, another scenario is that when it is confirmed that this round of interaction information belongs to a non-first interaction (whether it is the first time - no) in the scenario of the "income entry" business type, it can be estimated based on the user input and the interaction information with the virtual object whether the position of the functional display component after adding the information (feedback information) required for a new round of interaction exceeds a preset threshold (dynamic threshold calculation), and whether it is still within the conversation box (screen space evaluation). If, after adding the information (feedback information) required for a new round of interaction, the updated functional display component of the displayed functional display component in the corresponding conversation box in response to the interaction information input by the user can be completely displayed in the conversation box, that is, it does not exceed the threshold (whether it exceeds the threshold - not exceeding the threshold), at this time, since the user can still see the functional display component before this round of interaction in the conversation box, that is, the functional display component before this round of interaction has not left the user's field of vision, there is no need to regenerate a functional display component according to the content of this round of interaction to occupy the visible area in the conversation box, but the relevant information can be directly updated on the original functional display component. For example, the user inputs "Please change the income entry category to a Chinese restaurant, not a Western restaurant", and the virtual object (such as an artificial intelligence assistant) replies "Okay, it has been updated for you". According to the usual solution, the conversation box on the page loading end will load the conversation between the user and the virtual object based on this round of interaction between the user and the virtual object and generate a new functional display component. Among them, the user's input may occupy the visible area in the conversation box with a height of 2 pixels, the reply of the virtual object may occupy the visible area in the conversation box with a height of 100 pixels, and the generated new functional display component may occupy the visible area in the conversation box with a height of 500 pixels. In this way, this round of interaction will occupy the visible area in the conversation box with a height of 800 pixels, reducing the amount of information that can be carried per unit screen in the visible area of the conversation box (the display page on the page loading end); while if the functional display component before this round of interaction is directly updated, this round of interaction will only occupy the visible area in the conversation box with a height of 300 pixels, greatly improving the amount of information that can be carried per unit screen.

[0036] Therefore, when it is determined that the updated functional display component after the displayed functional display component in response to the interaction information input by the user can be completely displayed in the conversation box, that is, when it does not exceed the threshold (whether it exceeds the threshold - not exceeding the threshold), the display content of the conversation box can be directly updated according to the updated functional display component (original card update).

[0037] On the updated function display component, a reminder display element (card update reminder method) can also be added. The reminder display element can indicate that the instruction corresponding to the interactive information input by the user has been completed, or prompt that the function display component has been updated, etc. The reminder display element can be displayed at the associated position of the function display component or the associated position of the interactive information. For example, it can be a weak reminder (Toast reminder, such as the weak reminder "Updated for you" indicating that the instruction corresponding to the interactive information input by the user has been completed), content change annotation (marking the updated content, such as the annotation indicating that the function display component has been updated), persistent reminder (update confirmation Done, such as reminder symbols for indicating that the function display component has been updated: check mark, Done, etc.), and other new interactive forms or inherent interactive forms such as dialog box reply (such as replying "Updated on the original card") to further increase the information density per unit area. These reminder display elements can be used alone or in combination (combinable selection), and the present application does not impose any restrictions on this. The display position of the reminder display element can be at the upper end of the conversation box, next to the current interactive information in the conversation box, or around the updated function display component; it can be displayed in a flashing manner or in a constant-on manner; it can be displayed for only a few seconds or be displayed persistently, etc.; the present application does not impose any restrictions on the position, display method, display time, etc. of the reminder display element. After updating the display content of the conversation box (original card update) according to the updated function display component and adding the reminder display element (card update reminder method), the user can have the next round of interaction (continue interaction) with the virtual object.

[0038] In addition, in the case where it is determined that the updated function display component after responding to the interactive information input by the user is not fully displayed or not displayed in the conversation box, that is, when exceeding the threshold (whether exceeding the threshold - exceeding the threshold), another function display component (generate a new card) can be generated in response to the interactive information input by the user, and the display content of the conversation box (update the original card) can be updated according to the other function display component (integrate the updated information). Then the user can have the next round of interaction (continue interaction) with the virtual object.

[0039] Figure 2The figure shows a schematic flow diagram of the front-end and back-end interactions of a display solution for an interactive page provided in an embodiment of the present application. First, after the page loading end (front-end) obtains the interactive information input by the user based on the conversation box (user - user issues an instruction - display the message sent by the user), the interactive information input by the user can be sent to the back-end server (forward the user instruction). Since the conversation box conducts session interaction with the user with a virtual object as the interaction subject, the responses or processing information given by the virtual object for the information input by the user (such as user questions, ticket booking information, etc.) can be generated by the back-end server that communicates with the page loading end, or can be generated by other back-end servers and then sent to the back-end server that communicates with the page loading end. The back-end server can accept the interactive information input by the user or the information fed back by the front-end from the page loading end (front-end), and can also receive the information sent by other servers (such as the server of the virtual object - artificial intelligence assistant) (such as the responses given by the virtual object to the user's questions and other interactive information for conversation with the user or for the user's reference), and the back-end server can also directly generate the interactive information for the virtual object to reply to the user. The present application does not impose any restrictions on this.

[0040] After receiving the user instruction, the back-end server can analyze the received interactive information (analyze the user instruction) and determine whether the conversation between the user and the virtual object is still in the current session (determine whether it is still in the current session). For example, if the user inputs "Thank you, goodbye", it can be determined that this round of interaction ends the previous round of interaction, that is, the judgment result is "no" (not in the current session), and it will not enter the next "business logic processing sub-process"; if the user inputs "I still want to look at the air tickets" or "Please modify the amount", etc., that is, when the conversation between the user and the virtual object has not ended, the judgment result can be "yes" (still in the current session), and at this time, it can enter the next "business logic processing sub-process".

[0041] After entering the business logic processing sub-process, the back-end server can determine which business logic processing sub-process to adopt according to one round or multiple rounds of interactive information between the user and the virtual object. For example, if the previous round of interactive information between the user and the virtual object is about hotel reservation, and the interactive information input by the user in this round is "I still want to look at the air tickets", since hotel reservation and air ticket reservation belong to two different businesses and their sub-processes of business processing logics are different, the previous round of interactive information adopts the business logic processing sub-process for hotel reservation, while the information in this round can adopt the business logic processing sub-process for air ticket reservation. These business logic processing sub-processes can be preset or retrieved temporarily. The present application does not impose any restrictions on this. Different business logic processing sub-processes can correspond to different business IDs or different processing flows. The present application does not impose any restrictions on this.

[0042] After entering the business logic processing sub - process, the back - end server can mark the interaction information of this session with a business instance ID (which can be a Universally Unique Identifier UUID, and the UUID can be used as the unique identifier for a user's business instruction) according to information such as business type and business ID (identification code). For example, in a multi - round session of a business scenario, the function display components of the virtual objects corresponding to each round of conversation can all have the same business instance ID. When the front - end receives the message information with the same business instance ID, it can only update the corresponding content in the function display component instead of creating a new function display component. Next, the back - end server can also obtain the type of the function display component (the function display component can also be called an "anchor point", and the type of the function display component can be called an "anchor point type"), business information, and other information according to the interaction information between the user and the virtual object, business type, business ID (identification code), business instance ID, etc., and form the business instance ID, the type of the function display component, business information, and other information into message information (construct message information) and send it back to the front - end (page loading end). Among them, the type of the function display component can correspond to different business types. For example, in a hotel scenario, checking out and checking in for an extended stay can be displayed by function display components of different types; business information can be the necessary information for forming the function display component under the corresponding business type. For example, it can include some business fields such as the amount of income and room number. The metadata of the data structure of the business information in the same type of function display component can be the same; other information can include operation feedback reminders, long - term information, replies, display marks, etc. For example, for an operation feedback reminder, it can be displayed on the front - end in a weak reminder manner; another example is long - term information, which can be displayed on the front - end in a permanent reminder manner, and this part of the information can exist in the front - end document flow.

[0043] Next, the backend can send the constructed message information to the frontend (returning the message information in the message format). The frontend (page loading end) can identify the interaction information and trigger the invocation of the function display component of the virtual object. That is, after analyzing the received message information (analyzing the message content), the frontend can determine whether to trigger the invocation of the function display component of the virtual object. For example, if the message content does not include the business instance ID (which can be the UUID of the function display component), it can indicate that the interaction information between the user and the virtual assistant in this round does not contain the updated content of the function display component or lacks the necessary information to form the function display component. In this case, the function display component of the virtual object does not need to be invoked, and the frontend can display the message content without using the function display component after analyzing the message content; if the message content includes the business instance ID (which can be the UUID of the function display component), it can indicate that the interaction information between the user and the virtual assistant in this round contains the updated content of the function display component or completes the necessary information to form the function display component. Then, the function display component of the virtual object can be invoked, and the frontend can display the message content in the form of the function display component after analyzing the message content (anchor information display sub-process).

[0044] Of course, the above process of the backend server identifying and processing the interaction information can also be completed by the frontend. For example, the frontend can perform semantic recognition on the interaction information to determine that the semantic content of the interaction information indicates at least one function of invoking the function display component of the virtual object, and then can enter the anchor information display sub-process.

[0045] Furthermore, after entering the anchor information display sub-process, the frontend (page loading end) can ensure that the updated function display component, which is the result of the previously displayed function display component in the conversation box in response to the user input interaction information, is fully displayed in the conversation box, and then update the display content of the conversation box according to the updated function display component. The method of ensuring that the updated function display component, which is the result of the previously displayed function display component in the conversation box in response to the user input interaction information, is fully displayed in the conversation box can first obtain the page source code segment corresponding to the previously displayed function display component from the page source file, and then add the feedback information corresponding to the interaction information to the corresponding position of the previously displayed function display component in the page source code segment. The feedback information can be obtained from the server corresponding to the page loading end. The feedback information here can be the message content, which can be in the format of HTML (HyperText Markup Language) or other formats, and this application does not impose any restrictions on this. Secondly, it can be determined that the function display component with the added feedback information is fully displayed in the conversation box.

[0046] For example, before the function display component that adds feedback information is rendered and displayed by the front end (page loading end), it can be stored and transmitted in the form of a document flow. The front end can first analyze whether there is an anchor component (function display component) with a relevant business instance ID in the current document flow. If it exists, it can indicate that before the user's current interaction with the virtual object, the necessary information for composing the function display component has been completely collected and the function display component has been displayed at least once. In this case, the previous function display component can be updated or a new one can be created as appropriate; if there is no anchor component (function display component) with a relevant business instance ID, it can be explained that the necessary information for composing the function display component has just been completely collected in this round of interaction. Therefore, a new function display component (constructing an anchor component according to the anchor type, business instance ID, and business information) can be directly created and rendered (rendering and displaying the newly added anchor component).

[0047] In the case where there is an anchor component with a relevant business instance ID, it can be divided into two situations: It can be determined whether to update the previous function display component or create a new function display component by further judging whether the function display component that adds feedback information is completely displayed in the conversation box. Among them, creating a new function display component can also include two situations: If it is determined that the function display component is not displayed in the conversation box, or the displayed function display component is not completely displayed in the conversation box, then another function display component that responds to the user input is generated, and the display content of the conversation box is updated according to the other function display component.

[0048] Exemplarily, it is possible to first determine whether the function display component in the current document stream is completely displayed in the conversation box, and then determine whether the function display component for adding feedback information is completely displayed in the conversation box. For example, first, by determining whether the anchor component of the business instance ID in the current document stream is completely contained within the visible area (SAREA area) of the conversation box. If the anchor component of the business instance ID in the current document stream is completely contained within the visible area (SAREA area) of the conversation box (exists), then according to the business information in the message information returned by the backend, feedback information (such as business information) can be added to the function display component (update the anchor component), and then further determine whether the anchor component of the business instance ID in the current document stream (the function display component for adding feedback information) is completely contained within the visible area (SAREA area). If it is contained (exists), then the display content of the conversation box can be directly updated according to the updated function display component (render and update the existing anchor component); if it is not contained (does not exist), then another function display component can be generated (construct a new anchor component). Among them, the visible area (SAREA area) of the conversation box can be a visible area calculated according to the size of the displayable area of the current device (the unit can be pixels, such as 1285*2778px) according to a preset threshold, which is suitable for users to read or for the function display component (anchor) to be displayed. The unit of this part of the visible area (SAREA area) can be pixels. Similarly, if the anchor component of the business instance ID in the current document stream cannot be completely contained within the visible area (SAREA area) of the conversation box (does not exist), then after updating the function display component according to the business information in the message returned by the backend, another function display component can be generated (construct a new anchor component). When generating another function display component, the content in the function display component for adding feedback information (the updated anchor component) can be directly copied to the new function display component (copy the updated anchor component from the previous step). After generating another function display component, the business instance ID in the message information is written into the generated another function display component (write and update the business instance ID to this anchor component), and then the generated another function display component is rendered and displayed (render and display the newly added anchor component).

[0049] After the above-mentioned rendering function display component, a reminder display element can be added to the updated function display component. The reminder display element can indicate that the instruction corresponding to the interaction information input by the user has been completed, or prompt that the function display component has been updated. The reminder display element can be displayed at the associated position of the function display component or the associated position of the interaction information. For example, after the above-mentioned rendering function display component (anchor component), it is possible to further check whether there is other information in the message content, such as weak reminders, resident information, etc., as reminder display elements. If present, for weak reminders (toast), they can be displayed in the form of toast, and the display method can be to display the information in a floating and fading manner out of the document flow; for resident information, it can be to display the resident information in the document flow.

[0050] The execution subject of the embodiments of the present application can be an application program, a service, an instance, a software-form function module, a virtual machine (Virtual Machine, VM), a container, a cloud server, etc., or a hardware device with data processing capabilities (such as a server or a terminal device) or a hardware chip (such as a CPU, GPU, FPGA, NPU, AI acceleration card, or DPU), etc. The device for implementing the display of the interactive page can be deployed on the computing device of the application party providing the corresponding service or on a cloud computing platform providing computing power, storage, and network resources.

[0051] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for the user to choose to authorize or refuse.

[0052] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the foregoing technical problems. The several specific embodiments listed can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following will describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0053] The embodiments of the present application provide a method for displaying an interactive page, which is applied to a page loading end, such as Figure 3 As shown in the flowchart of the method 300 for displaying an interactive page according to an embodiment of the present application, the method 300 may include:

[0054] In step S301, obtain the interaction information input by the user based on the session box, where the session box uses a virtual object as the interaction subject to conduct session interaction with the user.

[0055] In the embodiments of the present application, the virtual object involved can be an object simulated by using technologies such as artificial intelligence for conversation interaction with humans. For example, it can be an artificial intelligence AI implemented by invoking a large language model. Such virtual objects can be pre-trained AIs for specific types of conversation interaction with humans in specific business scenarios. For example, in the scenario where an artificial intelligence AI implemented by invoking a large language model converses with humans, the content input by the user into the client front-end such as a conversation box (input data in non-text forms such as voice and pictures can be converted into text forms) can be transmitted to the back-end, and by invoking the artificial intelligence AI (which can be implemented by a large language model), corresponding answers can be generated according to the content input by the user. Taking the example of a buyer (user) booking a hotel through a mobile software, the specific scenario can be that the user has multiple rounds of conversations with the artificial intelligence (AI). During the multiple rounds of conversations, the user can input or transmit images, voices, and / or texts to the client front-end. The client back-end can invoke a pre-trained large language model (artificial intelligence assistant) to give answers to the client's input and transmit them to the client front-end. Thus, single-round or multiple-round conversations can be carried out through the user's input and the answers of the artificial intelligence assistant, and the interaction information of the single-round or multiple-round conversations can be displayed in the conversation box of the client front-end. The client back-end can use the content (interaction information) of the single-round or multiple-round conversations obtained from the client front-end as the basis for further processing.

[0056] The conversation box involved in the present application can be the visible area of a page loading end such as a website page, a computer software, or a mobile software (APP). The size of the conversation box can be determined according to the device model. Taking a smart phone as an example, before processing the interaction information input based on the conversation box, the device model of the smart phone can be obtained first, and the size of the visible area of the smart phone can be obtained according to the device model (the unit can be pixels, for example, 1284*2778px, that is, 1284px in width and 2778px in height). The obtained size of the visible area of the smart phone can be used as the size of the conversation box. It is also possible to select a specific area in the visible area of the smart phone as the conversation box according to a preset ratio. The size of this conversation box can be the size of the selected specific area, and the unit can be pixels. For example, a specific area of 1200*2778 is selected from the visible area of 1284*2778 as the conversation box.

[0057] In step S302, it is recognized that the interaction information triggers the invocation of the function display component of the virtual object.

[0058] In a possible implementation manner, the above-mentioned manner of recognizing that the interaction information triggers the invocation of the function display component of the virtual object can be to perform semantic recognition on the interaction information to determine that the semantic content of the interaction information indicates at least one function of invoking the function display component of the virtual object.

[0059] In the embodiments of the present application, the process of identifying interaction information can be completed by the client front-end or by the back-end server. In the case of identifying at the client front-end, a large language model can be called to perform semantic recognition on the interaction information, and necessary information for forming a function display component of a specific type can be extracted from the interaction information. The extraction process can be to first process the interaction information into a text form, and then extract keywords that conform to preset rules from the text. These keywords can be used as the necessary information for forming a function display component of a specific type, and thus it can be determined what type of function display component needs to be called, and what function in the function display component needs to be called.

[0060] The large language model involved in the embodiments of the present application can be a large-scale artificial intelligence model, especially a model in the field of natural language processing (NLP). Such models have a very large number of parameters, which can reach billions or even trillions of parameters. Due to their large scale, these models usually require very high computing resources for training and running. That is to say, the large language model can be a deep learning model or a neural network model trained with a large amount of text data, etc. It works by analyzing a large amount of text data and learning the patterns of language use, and can generate natural language text or understand the meaning of language text. The generated text is very close to what humans say or write. It is mainly divided into models based on autoencoders, sequence-to-sequence models, models based on Transformers, recurrent neural network models, and hierarchical models, etc. Different large language models are good at different types of tasks. For example, models based on autoencoders encode the input text into a lower-dimensional representation and then generate new text from this representation, which is suitable for tasks such as text summarization or content generation, and can be used for content generation of various content types related to the list; models based on Transformers adopt a neural network architecture and are good at understanding long-range dependencies in text data, and are suitable for various language tasks such as generating text, translating languages, and answering questions, and can be used for content generation of various content types related to the list. In specific implementations, the corresponding large language model can be selected according to needs, and the present application does not limit this. The large language model for semantic recognition can be a large language model pre-trained with a large amount of data. The training data required for training the large language model can be a single data point or sample in a large dataset, including at least one question and the expected answer; during the process of training the large language model, the large language model can also be fine-tuned, that is, additional training is performed on the basis of a pre-trained large model to adapt to a specific task. The pre-trained model used can be pre-trained with a large amount of data, and the pre-trained model has learned generalized feature representations. The purpose of fine-tuning is to allow the large language model to further utilize a small amount of data for the target task to optimize and improve.

[0061] In step S303, determine the function display component updated after the function display component already displayed in the session box responds to the interaction information input by the user, and completely display it in the session box.

[0062] In the traditional multi-round conversation scenario, the display scheme of the interaction page does not determine whether the function display component already displayed before this round of conversation will still be completely displayed in the session box after this round of conversation. Instead, without making a judgment, a new function display component is directly popped up after each round of conversation. For example, Figure 4 shows a schematic diagram of the display of the function display component in the display scheme of the interaction page in a traditional multi-round conversation scenario provided in the embodiment of the present application. In Figure 4 , the initial interaction information of the user with the artificial intelligence assistant (AI agent) is "The restaurant receipt is 500 yuan, help me record it". The initial function display component records "Receipt application operation, receipt category: Western restaurant, amount: 500, date: 2024-08-19", and at the same time, a button "Confirm and submit" that can be operated by the user is also displayed; then in the second round of conversation interaction, the user inputs "I said the amount wrong, the amount is 5000", and at this time, a new function display component is shown again, and it records "Receipt application operation, receipt category: Western restaurant, amount: 5000, date: 2024-08-19", and at the same time, a button "Confirm and submit" that can be operated by the user is also displayed; in the third round of conversation, the user inputs "Sorry, it's not today's receipt record, it's to make up yesterday's account", and at this time, another new function display component pops up again, and it records "Receipt application operation, receipt category: Western restaurant, amount: 5000, date: 2024-08-18", and at the same time, a button "Confirm and submit" that can be operated by the user is also displayed. It can be seen that this scheme of popping up a new function display component after each round of interaction has many drawbacks in the multi-round conversation scenario: for example, multiple interactive function display components occupy too much area of the display page at the page loading end, resulting in a reduction in the amount of information that can be carried per unit screen, and there is a lot of duplicate information, such as "Receipt application operation, receipt category: Western restaurant, amount, date", etc.; and the display page needs to be refreshed on a large scale; each time a new interactive function display component is created, it requires additional time resources; there are multiple buttons "Confirm and submit" that can be operated by the user, which is easy to confuse the user, increasing the time cost and mental cost for the user to obtain information, resulting in a poor user experience.

[0063] In the embodiment of the present application, by determining whether the function display component that has been displayed before this round of conversation will still be completely displayed in the conversation box after this round of conversation, that is, the step of determining that the updated function display component of the function display component that has been displayed in the conversation box after responding to the interaction information input by the user is completely displayed in the conversation box, it is possible to decide whether to update the displayed function display component or create a new function display component according to the judgment result of whether it is completely displayed or not.

[0064] Figure 5 shows a display schematic diagram of a function display component in a display scheme of an interaction page provided in an embodiment of the present application. As Figure 5 shown, take Figure 4 as an example. Figure 5 Also in the scenario of multi-round conversation for restaurant entry, the initial interaction information of the user with the artificial intelligence assistant (AI agent) is also "The restaurant entry is 500 yuan, help me record it". The initial function display component records "Entry application operation, entry category: Western restaurant, amount: 500, date: 2024-08-19", and at the same time, a button "Confirm and submit" that can be operated by the user is also displayed; then in the second-round conversation interaction, the user inputs "I made a mistake in the amount, the amount is 5000". In the embodiment of the present application, after rule judgment, it is not necessary to display a new function display component, and only need to update the displayed function display component. After the update, permanent reminders such as "Done@AI agent" can be marked under the information input by the user, and content change marking symbols such as "√" can be marked at the corresponding updated positions on the updated function display component. For example Figure 5In the second round of conversation, the user inputs "I said the amount wrong, the amount is 5000". Through the preset rule judgment, it is determined that the function display component that has been displayed in the conversation box can be completely displayed in the conversation box after responding to the second round of interaction information input by the user. The updated function display component is the "Account application operation, account category: Western restaurant, amount: 5000 (√), date: 2024-08-19" function display component with a content change mark symbol. Therefore, the display content of the conversation box can be directly updated according to the updated function display component. Similarly, the third round of interaction information is user input "Oh, Agent, I forgot to say, this is Ruzhaang's supplement from the day before yesterday, please help me change the date to the day before yesterday", and the fourth round of interaction information is user input "I have transferred to the Chinese restaurant, please help me change it to the Chinese restaurant". Similarly, through the preset rules, it is determined that the function display components displayed in the conversation box can be updated after responding to the third and fourth rounds of interaction information input by the user. The function display components can also be fully displayed in the conversation box. The updated function display components are "Account application operation, account category: Chinese restaurant (√), amount: 5000 (√), date: 2024-08-17 (√)" function display components with content change mark symbols, and after the third and fourth rounds of updates, permanent reminders such as "Done@AI agent" can also be marked under the information entered by the user, which will not be repeated here.

[0065] In the above rule judgment, the specific rules involved can determine whether a new function display component needs to be created based on the area or height of the conversation box (front display screen) occupied by the function display component (the screen length Clen occupied by the latest interactive component in this round), the area or height of the conversation box (front display screen) occupied by the user and the artificial intelligence assistant for multiple rounds of conversation after the displayed function display component (the length of subsequent rounds of conversation Blen), and the area or height of the conversation box (front display screen) itself (the maximum length Mlen that the screen can accommodate). Figure 5, Continuing with the previous example, assume that in the fifth round of interaction information, the user inputs "Change the date to yesterday again". The AI assistant is expected to reply "Okay, the card has been updated according to the latest requirements. Please check it." (predicting the length Plen required for this update). At this time, since the sum of the length Blen of the interaction information already displayed in the conversation box, the length Clen of the function display component that is expected to be updated after the function display component already displayed in the conversation box responds to the user input (the length Clen of the interaction component occupied by the latest round), and the length Plen required for this update is greater than the total length Mlen of the conversation box (the maximum length Mlen that the screen can accommodate). At this time, if the already displayed function display component is directly updated as in the previous four rounds of conversations, part of the function display component may be "squeezed out" of the screen of the conversation box after the update, that is, the already displayed function display component will not be completely displayed in the conversation box after the fifth round of conversation. Therefore, in this case, a new function display component needs to be created. At the same time, to save screen space, the AI assistant's reply "Okay, the card has been updated according to the latest requirements. Please check it." can be simplified to "It doesn't matter. I've helped you update it." and can be displayed in a weak reminder manner at the associated position of the function display component or the associated position of the interaction information, such as Figure 5 , it can be displayed flashing at the top of the screen. A judgment rule involved here can be to judge whether to update on the card according to a threshold. For example, when Clen + Blen + Plen > Mlen·X, the rule is triggered and a new card is created (generate another function display component); when Clen + Blen + Plen ≤ Mlen·X, update on the original card (update the existing function display component), where X in the formula can be an adjustment threshold, such as the height of the top of the function display component (anchor point) information after the update can be less than X% of the maximum bearing height of the screen space at the page loading end of the entire page loading end screen space Mlen. Such a setting can make the height for the user to view the function display component more reasonable and is conducive to improving the user experience. Correspondingly, on the other function display component (new card) generated corresponding to the fifth round of interaction, there can be recorded "Incoming account application operation, incoming account category: Chinese restaurant, amount: 5000, date: 2024-08-18 (√)", and there is also a button "Confirm and submit" that can be operated by the user; at the same time, a reminder display element can also be added next to the user input information "Change the date to yesterday again" to indicate that the instruction corresponding to the user input interaction information has been completed, or to prompt that the function display component has been updated, such as Figure 5 the mark "Done@AI agent" and other permanent reminders in

[0066] By adopting the above solution, during the interaction process of multiple rounds of conversations between the user and the virtual object (artificial intelligence assistant), based on the increased conversation content, it can be determined whether the function display components already shown in the current conversation box and the function display components updated after responding to the interaction information input by the user are completely shown in the conversation box. If they are completely shown, the content of the updated function display components will be displayed. Additionally, when it is determined that the updated function display components are not shown or not completely shown in the conversation box, another function display component that responds to the interaction information input by the user can be generated and the updated content can be marked, making the display method of the interaction page more flexible, increasing the amount of information that can be carried per unit screen within the conversation box on the page loading end, enabling the user to quickly find key information; since some content in the solution can be shown by updating the function display components, the display page of the conversation box does not need to be refreshed on a large scale, reducing visual flickering and also reducing the additional time resources consumed for creating new function display components, reducing the time cost and health cost for the user to obtain information, thereby optimizing the interaction experience between the user and the artificial intelligence assistant.

[0067] In a possible implementation manner, the method for determining that the function display components already shown in the conversation box and the function display components updated after responding to the interaction information input by the user are completely shown in the conversation box can be as follows: first, obtain the page source code segment corresponding to the function display components already shown from the page source file; then add the feedback information corresponding to the interaction information to the corresponding position of the function display components already shown in the page source code segment, where the feedback information is obtained from the server corresponding to the page loading end; finally, determine that the function display components with the added feedback information are completely shown in the conversation box.

[0068] In the embodiments of the present application, the language of the page source file can be a page source file recorded in computer languages such as HTML (HyperText Markup Language) or XML (a subset of the Standard Generalized Markup Language), and the present application does not impose any restrictions on this. The page source file can be recorded in the file style of Cascading Style Sheets (CSS) (CSS document flow). CSS can not only statically modify web pages but also dynamically format various elements of web pages in cooperation with various scripting languages.

[0069] Since in the CSS document flow, each functional display component, interactive information input by the user, and interactive information output by the virtual object can be recorded at fixed positions in the CSS document flow, the page loading end only needs to load and render the display content of a specific segment of the document flow. Therefore, after obtaining the page source code segment corresponding to the displayed functional display component (which can be the corresponding segment in the CSS document flow) from the page source file, it is possible to update the display, or determine whether the displayed functional display component or the updated functional display component is completely displayed in the session box.

[0070] Specifically, the way to update the functional display component can be to add the feedback information corresponding to the interactive information to the corresponding position of the displayed functional display component in the page source code segment. For example, add the answer (feedback information) of the virtual object (artificial intelligence assistant) to the interactive information input by the user to the corresponding position of the displayed functional display component in the CSS document. After completing the update of the displayed functional display component in this way, it is then rendered and displayed. Among them, the feedback information can be obtained from the server corresponding to the page loading end, and the server can process the updated HTML file into the form of a message and send it to the page loading end. The message information can include the feedback information, business instance ID, type of functional display component, business information, and other information, etc.

[0071] For example, the server (backend server) can, according to information such as the business type and business ID (identification code) displayed in the updated HTML file, mark the interaction information of this round of session with a business instance ID in the message information (which can be a Universally Unique Identifier UUID, and the UUID can be used as the unique identifier for a user's business instruction). For example, in multiple rounds of sessions in a business scenario, the function display components corresponding to the virtual objects in each round of conversation can all have the same business instance ID. When the front end receives the message information with the same business instance ID, it can only update the corresponding content in the function display component instead of creating a new function display component. Next, the backend server can also obtain the type of the function display component (the function display component can also be called an "anchor point"), business information, and other information based on the interaction information between the user and the virtual object, business type, business ID (identification code), business instance ID, etc., and form a message information by combining the business instance ID, the type of the function display component, business information, and other information and send it back to the page loading end. Among them, the type of the function display component can correspond to different business types. For example, in the scenario of booking air tickets, booking air tickets of different airlines can be displayed by different types of function display components; business information can be the necessary information for forming the function display component under the corresponding business type. For example, it can include some business fields such as the amount credited, room number, departure time, arrival time, stopover station, etc. The metadata of the data structure of the business information in the same type of function display component can be the same (it can all be in HTML format); other information can include reminder display elements such as operation feedback reminders, persistent information, replies, display marks, etc., which are used to indicate that the instruction corresponding to the interaction information input by the user has been completed, or to prompt that the function display component has been updated. For example, the operation feedback reminder can be displayed on the front end in a weak reminder manner; another example is the persistent information, which can be displayed on the front end in a persistent reminder manner, and this part of the information can exist in the document flow of the front end. Specific embodiments can refer to the description of Figure 2 in the specification of this application, which will not be elaborated here.

[0072] In some embodiments, before obtaining the page source code segment corresponding to the displayed function display component from the page source file, determining that the displayed function display component in the conversation box is updated after responding to the interaction information input by the user and is completely displayed in the conversation box may further include: determining that there is a function display component displayed in the conversation box of the page loading end and the displayed function display component is completely displayed in the conversation box.

[0073] There can be multiple specific determination methods. For example, the relative position of the function display components already shown in the session box at the page loading end can be compared. The relative position can be determined by the coordinates, height, or area of the function display components already shown in the session box. It can also be determined by comparing the position height of the function display components already shown in the page document flow (such as the CSS document flow) with the position height of the session box relative to the CSS document flow, so as to determine that there are function display components already shown in the session box at the page loading end and the function display components already shown are completely shown in the session box.

[0074] Figure 6 It shows a schematic diagram of comparing the height of the display information after adding the function display components with feedback information in the page document flow and the height of the function display components with feedback information with the visible content height of the session box in a display scheme of an interactive page provided in an embodiment of the present application. As Figure 6 shown, the method for determining that there are function display components already shown in the session box at the page loading end and the function display components already shown are completely shown in the session box can be to compare the relative position of the function display components already shown in the session box at the page loading end. The relative position can be determined by the coordinates, height, or area of the function display components already shown in the session box. For example, it is set that the height of the visible area in the session box is Mlen. The visible area can include a part of the blank area before some of the function display components already shown, the existing content area before the function display components already shown, the function display component area (anchor component area, the height can be Clen), and the existing content area after the function display components already shown (the occupied space, the height can be Blen). At this time, even if the blank area before the function display components already shown and the existing content area before the function display components already shown are "pushed out" of the visible area by the updated content, the function display components already shown will still be shown in the session box. Therefore, the heights of these two parts can be not calculated. After receiving the interaction content of a new round of interaction, the height Plen of the session box (visible area) that the interaction content of the new round of interaction (to be output, updated content) may occupy can be estimated first, that is, height estimation is performed, and the sizes of Clen + Blen + Plen and Mlen are calculated. When Clen + Blen + Plen > Mlen (exceeding the visible area), the updated function display components of the function display components already shown in response to the interaction information input by the user will not be completely shown in the session box. Therefore, another function display component (new anchor) needs to be created, as Figure 5Among them, the previously existing content area (which was an anchor point, i.e., a displayed function display component) is no longer displayed in the conversation box. In the current conversation box, after the existing content area (the space that has been occupied, with a height that can be Blen) and the new round of interaction content (to be output, updated content) after the displayed function display component, another function display component is newly created, which is the anchor component area. When Clen + Blen + Plen ≤ Mlen (not exceeding the visible area), that is, the function display component updated after the displayed function display component in response to the interaction information input by the user can still be completely displayed in the conversation box, and it can be updated on the original card (update the existing function display component).

[0075] Exemplarily, for the method of determining that the function display component for adding feedback information is completely displayed in the conversation box, the page document flow displayed in the conversation box can be updated first according to the page source code segment for adding feedback information; then, the height of the display information after the function display component for adding feedback information in the page document flow and the height of the function display component for adding feedback information are compared with the visible content height of the conversation box to determine that the function display component for adding feedback information is completely displayed in the conversation box.

[0076] For example, the first line of the CSS document flow can be used as the starting coordinate axis (X-axis), and the height of the CSS document flow can be the Y-axis relative to the X-axis. Thus, the coordinates of the content recorded in the first line of the CSS document flow, which is also the starting sentence of the first round of the multi-round session, are (0, 1). And so on, for each additional sentence or functional display component, the Y-axis coordinate will increase accordingly. Since the position height of the displayed functional display component in the CSS document flow is fixed, the page loading end can directly obtain the position height of the displayed functional display component from the CSS document flow. Assume that the coordinates of the displayed functional display component in the CSS document flow are from the 10th line to the 15th line (at this time, the Y-axis coordinate is 10 - 15, which can be that the displayed functional display component occupies the pixel points in the 10 - 15 height range of the CSS document flow). At the same time, the page loading end can also obtain its own position height relative to the CSS document flow. For example, the page loading end is displaying the content from the 8th line to the 28th line of the CSS document flow (the corresponding Y-axis coordinate is 8 - 28, which can be that the page loading end is displaying the pixel points in the 8 - 28 height range of the CSS document flow). Among them, the total height of the CSS document flow can be higher than 28 or the same as 28. For example, if the total height of the CSS document flow is 40, it means that the page the user is currently viewing is not the latest round of interaction messages (the user is viewing the content in lines 8 - 28); if the total height of the CSS document flow is 28, it means that the page the user is currently viewing is the latest round of interaction messages. The total height of the CSS document flow does not affect the above judgment on whether the displayed functional display component is completely displayed in the page loading end. Further, the position height of the displayed functional display component in the CSS document flow (10 - 15) can be compared with the position height of the page loading end itself relative to the CSS document flow (8 - 28). It can be seen that in this example, 10 > 8 and 15 < 28. Therefore, it can be concluded that the displayed functional display component in the session box of the page loading end is completely displayed in the session box. If the position height of the displayed functional display component in the CSS document flow is 5 - 10, and the position height of the page loading end itself relative to the CSS document flow is still 8 - 28. At this time, 5 < 8 and 10 < 28, indicating that the displayed functional display component in the session box of the page loading end is not completely displayed in the session box, which does not conform to the above situation.

[0077] Of course, since the total height of the function display component (e.g., the height of 15 - 10 = 5 pixel points) is generally less than the total height of the conversation box, it is also possible to only compare the starting height of the displayed function display component in the CSS document flow (e.g., 10) with the starting height of the page loading end itself relative to the CSS document flow (e.g., 8). When the starting height of the displayed function display component in the CSS document flow is greater than or equal to the starting height of the page loading end itself relative to the CSS document flow (10 ≥ 8), it can be concluded that the displayed function display component in the conversation box of the page loading end is fully displayed in the conversation box; when the starting height of the displayed function display component in the CSS document flow is less than the starting height of the page loading end itself relative to the CSS document flow (5 < 8), it can be concluded that the displayed function display component in the conversation box of the page loading end is not fully displayed or not displayed in the conversation box. Furthermore, the displayed function display component can be updated in different cases or another function display component can be created.

[0078] In some embodiments, before adding the feedback information corresponding to the interaction information to the corresponding position of the displayed function display component in the page source code segment, where the feedback information is obtained from the server corresponding to the page loading end, determining that the updated function display component of the displayed function display component in the conversation box after responding to the interaction information of the user is fully displayed in the conversation box further includes: sending the interaction information of the user to the corresponding server and obtaining the message information returned by the server corresponding to the interaction information; extracting the feedback information from the message information.

[0079] Continuing with the previous example, the message information returned by the server may include feedback information according to the virtual object, as well as the business instance ID, the type of the function display component, business information, and other information extracted from the session interaction information in previous sessions of this multi-round session. After creating the message information, the backend can send the constructed message information to the page loading end. After analyzing the received message information, the page loading end can determine whether to trigger the call of the function display component of the virtual object. Among them, the page loading end can use the business instance ID in the message information to determine whether to trigger the call of the function display component of the virtual object and whether to update the function display component or create another function display component; it can determine which function display component to call, which function in the function display component to call, and the height of the function display component according to the type of the function display component in the message information; it can also determine the feedback information such as the content to be displayed in the function display component according to the business information in the message information; it can also determine to add a reminder display element on the function display component and the display position, display method, display content, display time, etc. of the reminder display element according to the other information in the message information. For specific embodiments, reference can be made to the description in the specification of this application regarding Figure 2The description thereof will not be repeated here.

[0080] In step S304, update the display content of the session box according to the updated function display component.

[0081] In some embodiments, the manner of updating the display content of the session box according to the updated function display component may be to first modify the first function component identifier of the function display component already displayed in the page source code segment of the added feedback information to the second function component identifier of the function display component of the added feedback information (the component for adding feedback may not be considered a completely updated component, but the updated and the component for adding feedback may have the same identifier); then reload the page source code segment with the updated function component identifier to update the display content of the session box.

[0082] In the embodiments of the present application, the first function component identifier and the second function component identifier may be the same or different. The first function component identifier and the second function component identifier may represent the business type of the function display component (such as hotel reservation, flight reservation, posting operation, etc.), that is, the business scenario corresponding to the current multi-round conversation. The first function component identifier and the second function component identifier may be obtained from the message information returned by the server. For example, it may be the business instance ID in the message information returned by the server (which may be the UUID of the function display component and has a unique directivity). In the case of updating the function display component, the first function component identifier and the second function component identifier may be the same. For example, the first function component identifier and the second function component identifier may be marked with the same UUID; in the case of creating another function display component, the first function component identifier and the second function component identifier may be different. For example, the first function component identifier and the second function component identifier may be marked with different UUIDs. For specific embodiments, reference may be made to the description in the specification of the present application regarding Figure 2 The description thereof will not be repeated here.

[0083] In a possible implementation manner, the display scheme of the interaction page provided in the embodiments of the present application may further include: determining that a function display component is not displayed in the session box, or the displayed function display component is not completely displayed in the session box, then generating another function display component for interacting with the user input, and updating the display content of the session box according to the other function display component.

[0084] As described above, generating another function display component for interacting with the user input, that is, creating a new function display component, may correspond to two situations: one is that no function display component is displayed in the session box, and the other is that the displayed function display component is not completely displayed in the session box. In both of these situations, a new function display component needs to be created instead of updating the function display component (the updated function display component is different from the other function display component).

[0085] The situation where the function display component is not shown in the conversation box can include two cases: One is that before this round of conversation, no function display component related to this multi-round conversation has ever been generated. For example, after several rounds of conversation between the user and the virtual object, the necessary information (such as amount, date, etc.) to complete the function display component has not been filled in all the time; The other is that before this round of conversation, a function display component that has been shown and is related to this multi-round conversation has been generated, but due to the subsequent interaction content after the shown function display component, the shown function display component has been "pushed out" of the visible area range of the conversation box. In both of these cases, it is necessary to newly create another function display component to facilitate the user's viewing and operation. For specific embodiments, reference can be made to the description in the specification of this application regarding Figure 2 , which will not be elaborated here.

[0086] In a possible implementation manner, the display scheme of the interaction page provided in the embodiments of this application may further include: adding a reminder display element to the updated function display component, where the reminder display element indicates that the instruction corresponding to the interaction information input by the user has been completed, or prompts that the function display component has been updated, and the reminder display element is displayed at an associated position of the function display component or an associated position of the interaction information.

[0087] The reminder display elements involved in the embodiments of this application may include weak reminders, content change markings, persistent reminders, dialog box responses, etc. Among them, the weak reminder may be a Toast reminder, such as the weak reminder "Updated for you" indicating that the instruction corresponding to the interaction information input by the user has been completed; The content change marking can mark the updated content, such as the marking indicating that the function display component has been updated; The persistent reminder may be a mark or symbol such as Update Confirmation Done, etc., such as the reminder symbol indicating that the function display component has been updated: tick, Done and other marks, etc.; The dialog box response may be normal response content, such as replying "Updated in the original card", etc. These reminder display elements can be used alone or in combination (combinable selection), and this application does not impose any restrictions on this. The display position of the reminder display element can be at the upper end of the conversation box, or next to the current interaction information in the conversation box, or around the updated function display component; It can be displayed in a flashing manner or in a constant-on manner; It can be displayed for only a few seconds or be displayed persistently; It can be displayed in the original page document flow or on the upper layer of the page document flow, etc.; This application does not impose any restrictions on the position, display method, display time, etc. of the reminder display element. Adding a reminder display element to the updated function display component can further increase the information density per unit area of the overall page loading end and improve the user experience.

[0088] Figure 7 shows a schematic diagram of adding a reminder display element to the updated function display component provided in the embodiments of this application. AsFigure 7 As shown, in the conversation between the user and the AI agent, when the user inputs "The restaurant income is 500 yuan, please help me record it" during the first round of interaction, based on the displayed function display component "Income application operation, income category: Western restaurant, amount: 500 yuan, date: 2024-08-19, confirmation submission button", when the user inputs "I misspoke the amount, the amount is 5000" during the second round of interaction, at this time, at the associated position of the function display component, such as on the right side of "Amount: 5000" in the updated function display component, reminder display elements of content change annotation can be added. The content change annotation can use a specific icon, such as "√"; it can also be at the associated position of the interaction information, such as adding reminder display elements of resident reminder type (executing resident reminder - Done comment identifier) below the user's second-round input of "I misspoke the amount, the amount is 5000", such as updated confirmation Done and other marks or symbols (Done@AI agent). Such resident reminders can be interactive screen components that can be clicked by the user to expand (expand the component) to revoke the modification or view the details of this modification; it can also add reminder display elements of weak reminder type at the topmost of the display interface at the page loading end. For example, the content of the virtual object's (artificial intelligence assistant) response to the user's second-round input "It doesn't matter, I have updated it for you" can be displayed as a weak reminder to the user, and it can be in the form of a pop-up reminder and displayed in the previous display layer of the page document flow (such as the CSS document flow) (user weak reminder, Toast pop-up reminder).

[0089] The embodiment of the present application also provides a display method for an interactive page, which is applied to the server side, as Figure 8 shown in the flowchart of the display method 800 of the interactive page according to an embodiment of the present application. The method 800 may include:

[0090] In step S801, obtain the interaction information input by the user based on the conversation box sent by the page loading end. The conversation box uses the virtual object as the interaction subject to conduct conversation interaction with the user.

[0091] In step S802, send feedback information corresponding to the interaction information to the page loading end, so that after the page loading end recognizes that the interaction information triggers the call of the function display component of the virtual object, when it is determined that the displayed function display component in the conversation box is updated in combination with the feedback information and is completely displayed in the conversation box, update the display content of the conversation box according to the updated function display component. Specific embodiments can refer to the foregoing embodiments of the specification of the present application and the description about Figure 2 which will not be elaborated here.

[0092] In a possible implementation manner, the method of sending feedback information corresponding to the interaction information to the page loading end may be to generate feedback information corresponding to the interaction information; at least generate message information based on the feedback information and the second function component identifier corresponding to the updated function display component, and send it to the page loading end.

[0093] The embodiment of the present application further provides a method for displaying an interaction page, which is applied to a page loading end. As Figure 9 shown in the flowchart of the method 900 for displaying an interaction page according to an embodiment of the present application. The method 900 may include:

[0094] In step S901, obtain first interaction information input by the user based on the conversation box.

[0095] In the embodiment of the present application, the first interaction information may be the interaction information of the user's first conversation with the artificial intelligence assistant. For example, it may be the first interaction information sent by the user based on the conversation box to have a conversation with the artificial intelligence assistant. For example, it may be the interaction information input by the user based on the conversation box before inputting all the necessary information in the preset condition for calling the function display component corresponding to a specific service type; or it may be all the necessary information in the preset condition for calling the function display component corresponding to a specific service type input by the user. After the user inputs all the necessary information, the function display component corresponding to the specific service type may be called to display information related to the first interaction information.

[0096] In step S902, display the first interaction information within the visible area of the page loading end.

[0097] In step S903, display a function display component within the visible area of the page loading end according to the first interaction information, and the function display component displays information related to the first interaction information.

[0098] In step S904, obtain second interaction information input by the user based on the conversation box.

[0099] Among them, the second interaction information may be the second or other subsequent interaction information sent by the user after sending the first interaction information based on the conversation box. For example, in the scenario where the user has multiple rounds of conversations with the artificial intelligence assistant, the interaction information sent by the user based on the conversation box to change some information in the function display component. For example, the user inputs "Please change the posting category to Chinese restaurant, not Western restaurant", "I made a mistake about the amount, the amount is 5000" and so on based on the conversation box. Specific embodiments may refer to the description of the foregoing embodiments of the specification of the present application, and will not be elaborated here.

[0100] In step S905, according to the second interaction information, at least part of the information of the function display component is updated without changing the position of the function display component in the visible area.

[0101] In the embodiments of the present application, the situation of "not changing the position of the function display component in the visible area" may be that the coordinates of the top end of the function display component in the visible area are not changed. That is to say, the change in the displayed content in the function display component (for example, the increase in the displayed content causes the area occupied by the function display component to become larger) will not cause the coordinate of the top end position of the function display component in the visible area to change.

[0102] In the case of adopting the form of CSS document flow, the situation of "not changing the position of the function display component in the visible area" may be that the position of the function display component in the CSS document flow remains unchanged. Correspondingly, when the function display component in the CSS document flow is displayed in the visible area, the relative position of the CSS document flow and the visible area can be adjusted to display the function display component in the visible area so that the display position of the function display component does not change.

[0103] Corresponding to the above examples and method embodiments provided by the embodiments of the present application, the embodiments of the present application further provide a display device for an interactive page, which is applied to a page loading end. As Figure 10 As shown in the structural block diagram of the display device 1000 for an interactive page according to an embodiment of the present application. The device 1000 may include: an interaction information acquisition module 1001, configured to acquire interaction information input by a user based on a conversation box, where the conversation box uses a virtual object as an interaction subject to perform conversation interaction with the user; an interaction information recognition module 1002, configured to recognize that the interaction information triggers a call to a function display component of the virtual object; a complete display determination module 1003, configured to determine a function display component updated after the function display component already displayed in the conversation box responds to the interaction information input by the user, and completely display it in the conversation box; a display content update module 1004, configured to update the display content of the conversation box according to the updated function display component.

[0104] In a possible implementation manner, the above interaction information recognition module 1002 may include: a semantic recognition sub-module, configured to perform semantic recognition on the interaction information to determine that the semantic content of the interaction information indicates at least one function of calling a function display component of the virtual object.

[0105] In a possible implementation manner, the above-mentioned complete display determination module 1003 may include: a page source code segment acquisition sub-module, configured to acquire the page source code segment corresponding to the displayed function display component from the page source file; a feedback information addition sub-module, configured to add the feedback information corresponding to the interaction information to the corresponding position of the displayed function display component in the page source code segment, where the feedback information is acquired from the server corresponding to the page loading end; a complete display determination sub-module, configured to determine that the function display component with the added feedback information is completely displayed in the session box.

[0106] In some embodiments, before acquiring the page source code segment corresponding to the displayed function display component from the page source file, the above-mentioned complete display determination module 1003 may further include: a complete display determination sub-module for the displayed function display component, configured to determine that there is a function display component displayed in the session box of the page loading end and the displayed function display component is completely displayed in the session box.

[0107] In a possible implementation manner, the above-mentioned device may further include: another function display component generation module, configured to determine that there is no function display component displayed in the session box, or the displayed function display component is not completely displayed in the session box, then generate another function display component in response to the interaction information input by the user, and update the display content of the session box according to the another function display component.

[0108] In some embodiments, before adding the feedback information corresponding to the interaction information to the corresponding position of the displayed function display component in the page source code segment, where the feedback information is acquired from the server corresponding to the page loading end, the above-mentioned complete display determination module 1003 may further include: a message information acquisition sub-module, configured to send the interaction information input by the user to the corresponding server and acquire the message information returned by the server corresponding to the interaction information; a feedback information extraction sub-module, configured to extract the feedback information from the message information.

[0109] In some embodiments, the above-mentioned complete display determination sub-module may include: a page document flow update unit, configured to update the page document flow displayed in the session box according to the page source code segment with the added feedback information; a complete display determination unit, configured to compare the height of the display information after the function display component with the added feedback information in the page document flow and the height of the function display component with the added feedback information with the visible content height of the session box, and determine that the function display component with the added feedback information is completely displayed in the session box.

[0110] In some embodiments, the above display content update module 1004 may include: a function component representation modification sub-module, configured to modify a first function component identifier of a displayed function display component in a page source code segment with added feedback information to a second function component identifier of a function display component with added feedback information; and a display content update sub-module, configured to reload the page source code segment with the updated function component identifier to update the display content of the session box.

[0111] In a possible implementation manner, the above device may further include: a reminder display element adding module, configured to add a reminder display element to the updated function display component, where the reminder display element indicates that an instruction corresponding to the interaction information input by the user has been completed, or prompts that the function display component has been updated, and the reminder display element is displayed at an associated position of the function display component or an associated position of the interaction information.

[0112] Corresponding to the above examples and method embodiments provided in the embodiments of the present application, the embodiments of the present application further provide a display device for an interactive page, which is applied to a server. As Figure 11 shown in the structural block diagram of a display device 1100 for an interactive page according to an embodiment of the present application, the device 1100 may include:

[0113] An interaction information acquisition module 1101, configured to acquire interaction information input by a user based on a session box sent by a page loading end, where the session box uses a virtual object as an interaction subject to perform session interaction with the user; and a feedback information sending module 1102, configured to send feedback information corresponding to the interaction information to the page loading end, so that after the page loading end recognizes that the interaction information triggers a call to a function display component of the virtual object, and after determining that a displayed function display component in the session box is combined and updated with the feedback information and is completely displayed in the session box, the display content of the session box is updated according to the updated function display component.

[0114] In a possible implementation manner, the above feedback information sending module 1102 may include: a feedback information generation sub-module, configured to generate feedback information corresponding to the interaction information; and a message information sending sub-module, configured to generate message information at least according to the feedback information and a second function component identifier corresponding to the updated function display component and send it to the page loading end.

[0115] Corresponding to the above examples and method embodiments provided in the embodiments of the present application, the embodiments of the present application further provide a display device for an interactive page, which is applied to a page loading end. As Figure 12 shown in the structural block diagram of a display device 1200 for an interactive page according to an embodiment of the present application, the device 1200 may include:

[0116] The first interaction information acquisition module 1201 is configured to acquire first interaction information input by a user based on a session box; the first interaction information display module 1202 is configured to display the first interaction information within a visible area of the page loading end; the function display component display module 1203 is configured to display a function display component within the visible area of the page loading end according to the first interaction information, and the function display component displays information related to the first interaction information; the second interaction information acquisition module 1204 is configured to acquire second interaction information input by the user based on the session box; the function display component update module 1205 is configured to at least partially update information of the function display component according to the second interaction information without changing a position of the function display component within the visible area.

[0117] For the functions of the modules in each device of the embodiments of the present application, reference may be made to the corresponding descriptions in the above methods, and they have corresponding beneficial effects, which will not be elaborated here.

[0118] Figure 13 The block diagram of the electronic device for implementing the embodiments of the present application is shown as Figure 13 shown. The electronic device includes: a memory 1301 and a processor 1302. The memory 1301 stores a computer program that can run on the processor 1302. When the processor 1302 executes the computer program, the method in the above embodiments is implemented. The number of the memory 1301 and the processor 1302 may be one or more.

[0119] The electronic device further includes:

[0120] a communication interface 1303, configured to communicate with external devices and perform data interaction and transmission.

[0121] If the memory 1301, the processor 1302, and the communication interface 1303 are implemented independently, the memory 1301, the processor 1302, and the communication interface 1303 may be connected to each other through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 13 only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0122] Optionally, in a specific implementation, if the memory 1301, the processor 1302, and the communication interface 1303 are integrated on a single chip, the memory 1301, the processor 1302, and the communication interface 1303 can communicate with each other through an internal interface.

[0123] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the method provided in the embodiment of the present application.

[0124] An embodiment of the present application further provides a computer program product including a computer program, which when executed by a processor implements the method provided in any embodiment of the present application.

[0125] An embodiment of the present application further provides a chip including a processor for calling and running instructions stored in a memory, so that a communication device equipped with the chip executes the method provided in the embodiment of the present application.

[0126] An embodiment of the present application further provides a chip including: an input interface, an output interface, a processor, and a memory. The input interface, the output interface, the processor, and the memory are connected through an internal connection path. The processor is configured to execute code in the memory, and when the code is executed, the processor is configured to execute the method provided in the embodiment of the present application.

[0127] It should be understood that the above-mentioned processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced reduced instruction set machine (ARM) architecture.

[0128] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0129] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0130] In the description of this specification, the descriptions with reference to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0131] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present application, "a plurality of" means two or more unless otherwise specifically defined.

[0132] Any process or method described in the flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where the functions may be performed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed.

[0133] The logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with such instruction execution systems, apparatus, or devices.

[0134] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the method in the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0135] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, an optical disc, or the like.

[0136] As mentioned above, it is only an exemplary embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope recorded in the present application can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for displaying an interactive page, applied to a page loading end, the method comprising: Acquiring interaction information input by a user based on a conversation box, wherein the conversation box uses a virtual object as an interaction subject to conduct a conversation interaction with the user; Identifying that the interaction information triggers a call to a function display component of the virtual object; Determine that the function display component displayed in the conversation frame is updated in response to the interactive information input by the user, and completely display it in the conversation frame; The displayed content of the conversation box is updated according to the updated function display component.

2. The method according to claim 1, wherein: The identifying the interaction information triggering the calling of the function display component of the virtual object includes: Semantic recognition is performed on the interaction information to determine that the semantic content of the interaction information indicates calling at least one function of the function presentation component of the virtual object.

3. The method according to claim 1, wherein: The step of determining that the function display component displayed in the conversation frame is updated after responding to the interactive information input by the user, and the function display component is completely displayed in the conversation frame includes: Obtaining a page source code fragment corresponding to the displayed function display component from a page source file; Adding feedback information corresponding to the interaction information to a corresponding position of the function display component displayed in the page source code fragment, wherein the feedback information is obtained from a server corresponding to the page loading end; Determine that the function display component for adding feedback information is completely displayed in the conversation box.

4. The method according to claim 3, wherein: Before obtaining the page source code fragment corresponding to the displayed function display component from the page source file, determining that the function display component displayed in the session frame is updated after responding to the interactive information input by the user, and the function display component is fully displayed in the session frame also includes: It is determined that a function display component has been displayed in the session frame of the page loading end and the displayed function display component is completely displayed in the session frame.

5. The method according to claim 1, wherein: The method further comprises: If it is determined that the function display component is not displayed in the conversation box, or the displayed function display component is not fully displayed in the conversation box, another function display component is generated in response to the interactive information input by the user, and the display content of the conversation box is updated according to the other function display component.

6. The method according to claim 3, wherein: Before the step of adding the feedback information corresponding to the interactive information to the corresponding position of the function display component displayed in the page source code fragment and obtaining the feedback information from the server corresponding to the page loading end, the step of determining that the function display component displayed in the dialog box is updated after responding to the interactive information input by the user and is fully displayed in the dialog box also includes: Send the interaction information input by the user to the corresponding server, and obtain the message information returned by the server corresponding to the interaction information; Extract feedback information from the message information.

7. The method according to claim 3, wherein: The function display component for determining to add feedback information is fully displayed in the conversation frame and includes: updating the page document flow displayed in the conversation box according to the page source code fragment with added feedback information; The height of the display information after the function display component for adding feedback information in the page document flow and the height of the function display component for adding feedback information are compared with the height of the visible content of the conversation box to determine that the function display component for adding feedback information is completely displayed in the conversation box.

8. The method according to claim 3, wherein: The updating of the display content of the conversation box according to the updated function display component includes: Modify the first functional component identifier of the functional display component displayed in the source code fragment of the page for adding feedback information to the second functional component identifier of the functional display component for adding feedback information; The reload function component identifies the updated page source code fragment to update the display content of the conversation box.

9. The method according to claim 1, wherein: The method further comprises: A reminder display element is added to the updated function display component, and the reminder display element indicates that the instruction corresponding to the interactive information input by the user has been completed, or prompts that the function display component has been updated. The reminder display element is displayed at the associated position of the function display component or the associated position of the interactive information.

10. A method for displaying an interactive page, applied to a server, the method comprising: Acquiring interactive information sent by the page loading end and input by the user based on the conversation box, wherein the conversation box uses the virtual object as the interaction subject to conduct conversation interaction with the user; Feedback information corresponding to the interaction information is sent to the page loading end, so that after the page loading end identifies that the interaction information triggers a call to the function display component of the virtual object, and after determining that the displayed function display component in the conversation box is updated in combination with the feedback information and is fully displayed in the conversation box, the display content of the conversation box is updated according to the updated function display component.

11. The method according to claim 10, wherein: The sending feedback information corresponding to the interaction information to the page loading end includes: generating feedback information corresponding to the interaction information; Message information is generated at least according to the feedback information and the second functional component identifier corresponding to the updated functional display component and sent to the page loading end.

12. A method for displaying an interactive page, applied to a page loading end, the method comprising: Acquire first interaction information input by the user based on the conversation box; Displaying the first interactive information in a visible area of ​​the page loading end; Displaying a function display component in a visible area of ​​the page loading end according to the first interaction information, wherein the function display component displays information related to the first interaction information; Acquire second interaction information input by the user based on the conversation box; According to the second interaction information, the information of the function display component is at least partially updated without changing the position of the function display component in the visible area.

13. A display device for interactive pages, applied to a page loading end, the device comprising: An interaction information acquisition module, used to acquire interaction information input by a user based on a conversation box, wherein the conversation box uses a virtual object as an interaction subject to conduct a conversation interaction with the user; An interaction information identification module, used to identify the interaction information triggering the call of the function display component of the virtual object; A complete display determination module, used for determining the function display components that have been displayed in the conversation frame and are updated in response to the interactive information input by the user, and completely displaying them in the conversation frame; The display content updating module is used to update the display content of the conversation box according to the updated function display component.

14. A display device for interactive pages, applied to a server, the device comprising: An interactive information acquisition module, used to acquire interactive information sent by a page loading end and input by a user based on a conversation box, wherein the conversation box uses a virtual object as an interactive subject to conduct a conversation interaction with the user; A feedback information sending module is used to send feedback information corresponding to the interaction information to the page loading end, so that after the page loading end identifies that the interaction information triggers the call of the function display component of the virtual object, and after determining that the displayed function display component in the conversation box is updated in combination with the feedback information and is fully displayed in the conversation box, the display content of the conversation box is updated according to the updated function display component.

15. A display device for interactive pages, applied to a page loading end, the device comprising: A first interaction information acquisition module, used to acquire first interaction information input by the user based on the conversation box; A first interactive information display module, used to display the first interactive information in a visible area of ​​the page loading end; A function display component display module, used to display a function display component in a visible area of ​​the page loading end according to the first interaction information, wherein the function display component displays information related to the first interaction information; A second interaction information acquisition module, used to acquire second interaction information input by the user based on the conversation box; The function display component updating module is used to at least partially update the information of the function display component according to the second interaction information without changing the position of the function display component in the visible area.

16. An electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 12 when executing the computer program.

17. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

18. A computer program product, comprising a computer program / instruction, wherein the computer program / instruction implements the method according to any one of claims 1 to 12 when executed by a processor.

Images