Page interaction method, device and electronic equipment

Abstract

The application discloses a page interaction method and device and electronic equipment. It is related to the field of artificial intelligence, and the method comprises the following steps: receiving a page access request, and identifying the device information of a login device used by a target user and the user information of the target user according to the page access request; generating a display page according to the device information and the user information; receiving an interaction instruction, and judging whether the interaction instruction is abnormal; in the case that the interaction instruction is abnormal, generating a virtual person in the display page, generating first feedback information according to the interaction instruction, and outputting second feedback information through the virtual person in the case that a new instruction is received; in the case that the interaction instruction is not abnormal, generating third feedback information in the display page according to the interaction instruction. Through the application, the problem that the interface interaction process in the related art has obstacles and leads to low efficiency of handling business through the interaction interface is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a page interaction method, device, and electronic device. Background Technology

[0002] As the number of passengers taking flights continues to increase, airline apps and websites typically feature numerous service modules to allow passengers to handle most transactions. However, this proliferation of modules can make it particularly inconvenient for elderly passengers. Current solutions involve automatically switching the interface to an assistive mode when the user is identified as elderly. However, if the user's information is incomplete or the user has special needs, the system may fail to switch to assistive mode promptly, further complicating the process and reducing efficiency.

[0003] There is currently no effective solution to the problem that obstacles exist in the interface interaction process of related technologies, resulting in low efficiency in handling business through the interactive interface. Summary of the Invention

[0004] This application provides a page interaction method, apparatus, and electronic device to solve the problem that obstacles exist in the interface interaction process in related technologies, resulting in low efficiency in handling business through the interactive interface.

[0005] According to one aspect of this application, a page interaction method is provided. The method includes: receiving a page access request, and identifying device information of a login device used by a target user and user information of the target user based on the page access request, wherein the page access request is sent by the target user through a user-end device; generating a display page based on the device information and user information, wherein the display page displays page content using a preset display method; receiving an interaction instruction, and determining whether the interaction instruction is abnormal, wherein the interaction instruction is sent by the target user based on the display page; if the interaction instruction is abnormal, generating a virtual person on the display page, generating first feedback information based on the interaction instruction, and outputting second feedback information through the virtual person upon receiving a new instruction, wherein the first feedback information is used to instruct the target user to input a new instruction via voice; and if the interaction instruction is not abnormal, generating third feedback information on the display page based on the interaction instruction.

[0006] Optionally, generating a display page based on device information and user information includes: determining the page elements to be displayed on the display page and the preset display method of the page elements based on the user information; determining the page size of the display page and the number of page elements on the display page based on the device information; and generating the display page based on the preset display method and number of page elements and the page size.

[0007] Optionally, determining the page elements to be displayed on the display page based on user information includes: determining the user profile of the target user based on user information and obtaining the target user's historical browsing information; selecting candidate recommendation information from multiple preset recommendation information based on historical browsing information and user profile, and determining the preset page content of the display page indicated by the page access request; determining the filling position of the promotional information on the display page based on the initial element carried in the preset page content; selecting target recommendation information from the candidate recommendation information based on the number of filling positions, and determining the target recommendation information and the initial element as the page elements to be displayed on the display page.

[0008] Optionally, when the interaction instruction is a click instruction, determining whether the interaction instruction is abnormal includes: determining the click position of the click instruction and determining whether there are page elements in the preset area where the click position is located; if there are no page elements, obtaining the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain the target number; if the target number is less than the number threshold, determining that the interaction instruction is not abnormal; if the target number is greater than or equal to the number threshold, determining that the interaction instruction is abnormal.

[0009] Optionally, when the interaction instruction is a text instruction, determining whether the interaction instruction is abnormal includes: inputting the text instruction into the large language model and obtaining the recognition result of the large language model; if the recognition result indicates that the content of the text instruction is question information, determining that the interaction instruction is abnormal; if the recognition result indicates that the content of the text instruction is operation information, determining that the interaction instruction is not abnormal.

[0010] Optionally, upon receiving a new instruction, the second feedback information output by the virtual human includes: extracting keywords from the new instruction and determining the operation content indicated by the new instruction based on the keywords; if the operation content is a page jump, displaying the page jump on the display page and determining the page jump as the second feedback information; if the operation content is an operation name, generating operation steps corresponding to the operation name, generating a virtual human's guidance action based on the operation steps, and determining the virtual human's guidance action as the second feedback information.

[0011] Optionally, the method further includes: determining whether the target user has a voice interaction need; if the target user has a voice interaction need, obtaining a voice material library based on the voice interaction need, and training a neural network model based on the voice material library to obtain a voice conversion model; converting the voice text output to the target user through the voice conversion model to obtain the target output voice, and outputting the target output voice through a virtual human.

[0012] According to another aspect of this application, a page interaction device is provided. The device includes: a first receiving unit, configured to receive a page access request and identify device information of a login device used by a target user and user information of the target user based on the page access request, wherein the page access request is sent by the target user through a user terminal device; a first generating unit, configured to generate a display page based on the device information and user information, wherein the display page displays page content through a preset display method; a second receiving unit, configured to receive an interaction instruction and determine whether the interaction instruction is abnormal, wherein the interaction instruction is sent by the target user based on the display page; a second generating unit, configured to generate a virtual human on the display page when the interaction instruction is abnormal, and generate first feedback information based on the interaction instruction, and output second feedback information through the virtual human when a new instruction is received, wherein the first feedback information is used to instruct the target user to input a new instruction via voice; and a third generating unit, configured to generate third feedback information on the display page based on the interaction instruction when the interaction instruction is not abnormal.

[0013] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements a page interaction method provided in the foregoing embodiments of the present application.

[0014] According to another aspect of the present invention, an electronic device is also provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is configured to execute the computer-readable instructions, wherein the computer-readable instructions, when executed, perform a page interaction method provided in the foregoing embodiments.

[0015] This application employs the following steps: receiving a page access request and identifying the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device; generating a display page based on the device information and user information, wherein the display page displays page content according to a preset display method; receiving an interaction command and determining whether the interaction command is abnormal, wherein the interaction command is sent by the target user based on the display page; if the interaction command is abnormal, generating a virtual person on the display page and generating first feedback information based on the interaction command, and outputting second feedback information through the virtual person upon receiving a new command, wherein the first feedback information is used to instruct the target user to input a new command via voice; if the interaction command is not abnormal, generating third feedback information on the display page based on the interaction command. This solves the problem in related technologies where obstacles exist in the interface interaction process, resulting in low efficiency in handling business through the interactive interface. By recognizing user and device information, the content and display method on the display page are matched with the user. At the same time, when abnormal interaction commands are detected due to the user's inability to use the display page normally, a virtual human is generated to assist the user in performing the interaction operation. This achieves the technical effect of reducing the complexity of the user's use of the display page and improving the efficiency of the user's interaction with the page. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 This is a flowchart of a page interaction method provided according to an embodiment of this application;

[0018] Figure 2 This is a schematic diagram of an optional virtual human management platform provided according to an embodiment of this application;

[0019] Figure 3 This is a schematic diagram of an optional virtual human generation process provided according to an embodiment of this application;

[0020] Figure 4 This is a schematic diagram of a page interaction device provided according to an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] It should be noted that the page interaction methods, devices, and electronic devices defined in this disclosure can be used in the field of artificial intelligence, or in any field other than artificial intelligence. The application fields of the page interaction methods, devices, and electronic devices defined in this disclosure are not limited.

[0026] It should be noted that all information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) used in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse use. If the user chooses to refuse, the process proceeds to the expert decision-making process. For example, this system has interfaces with relevant users or institutions. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or institution through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or institution.

[0027] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0028] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0029] APP: Application, is a type of computer software designed to perform a specific task or provide a service. It can run on various devices, including computers, smartphones, and tablets.

[0030] API: Application Programming Interface, is a set of definitions and protocols that allow different software applications to communicate with each other.

[0031] Hive Tables: Hive is a data warehouse infrastructure used for querying and analyzing data on Hadoop. A Hive table is a data structure within Hive used to organize and store data.

[0032] According to an embodiment of this application, a page interaction method is provided.

[0033] Figure 1 This is a flowchart of a page interaction method provided according to an embodiment of this application. For example... Figure 1 As shown, the method includes the following steps:

[0034] Step S101: Receive a page access request, and identify the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device.

[0035] It's important to note that a page access request is the behavioral signal of a user attempting to access a specific page on a website or application. The user's device is the device the target user uses to access the webpage or application. Device information can include the hardware configuration, operating system version, network status, etc., of the device used to access the page, used to determine device attributes and performance. User information can include the target user's age, gender, etc., used to identify user characteristics in order to provide personalized services.

[0036] Specifically, the execution entity in this embodiment can be a page control system. When a target user sends a page access request through a user terminal device, the system immediately receives the request, analyzes the device information contained in the request (such as obtaining it through User-Agent header information), and attempts to identify relevant information of the target user (inferred through user account data, historical behavior records, or device attributes). After identifying the device information and user information, the system can adjust the page display format of the feedback interface for this access based on the device information and user information, thereby ensuring that the user can access the page without obstacles.

[0037] Step S102: Generate a display page based on device information and user information, wherein the display page displays page content using a preset display method.

[0038] Specifically, after obtaining device and user information, the system can generate a display page to present content to the user. This page can adjust the size, layout, and functionality of page elements through preset display methods (such as responsive design, accessibility features enabled, etc.) to adapt to the display needs of different devices and improve the user experience of specific user groups, thereby optimizing the page display and ensuring that every user can obtain the best visual and operational experience.

[0039] For example, different font sizes, margins, and layouts can be defined for different screen sizes (phones, tablets, desktops). For instance, phones can use a single-column layout, tablets can use a double-column layout, and desktops can use a multi-column layout. This allows for the rapid creation of responsive layouts, ensuring a good user experience across various devices.

[0040] Similarly, you can listen for button click events and dynamically adjust the overall font size of the page. For example, when the zoom-in button is clicked, the font size is increased by 1.2 times, and when the zoom-out button is clicked, the font size is decreased by 0.8 times. You can also define high-contrast theme styles to enhance the contrast between text and icons and the background, improve readability, enhance visual effects, and use large fonts and large icons to reduce menu hierarchy.

[0041] Step S103: Receive the interaction command and determine whether the interaction command is abnormal. The interaction command is sent by the target user based on the display page.

[0042] Specifically, after the initial page is displayed, the user will perform operations on the display page. At this time, the system will receive the interaction instructions from the target user and perform anomaly judgment to determine whether the user has performed abnormal interaction operations. For example, if the user clicks on position A more than 3 times, or if the style of the interaction module near position A is too small for the user to click, then the interaction instruction is abnormal.

[0043] It should be noted that when determining whether an interactive command is abnormal, it can be identified through various preset judgment methods, such as identifying whether the click location is abnormal or whether the clicked content is valid.

[0044] For example, when an elderly user clicks the flight search button, the system receives the instruction and checks for any abnormalities. If the instruction is correct, the system will redirect to the flight search interface; if the user accidentally clicks on a blank area of ​​the screen (a non-valid operation area), the system will recognize this behavior as abnormal and will not perform any operation.

[0045] In step S104, if there is an abnormality in the interaction command, a virtual person is generated on the display page, and a first feedback message is generated according to the interaction command. If a new command is received, a second feedback message is output through the virtual person. The first feedback message is used to instruct the target user to input a new command via voice.

[0046] Specifically, when the system detects an anomaly in the interactive command, indicating difficulty for the user in interacting with the display page, a virtual avatar is generated on the display page. This virtual avatar provides initial feedback to the user (e.g., voice prompts), explaining the reason for the command anomaly and guiding the user to input new commands via voice, thus assisting the user in performing subsequent operations. Subsequently, the system outputs a second set of feedback information through the virtual avatar, providing operation guidelines or corrected operation results via voice. This voice assistance helps the user understand and correct operational errors, while the virtual avatar executes the correct interactive operations, thereby enhancing the friendliness and intelligence of human-computer interaction.

[0047] For example, suppose a user attempts to book a flight after searching for it, but the operation fails due to selecting an invalid seat type. In this situation, a system-generated virtual assistant informs the user via voice: "The seat type you selected cannot be booked. We suggest trying economy or business class." The system then guides the user to reselect the seat type using voice commands. The user says, "I want to book economy class," and the system recognizes the new voice command. The virtual assistant confirms the command and guides the user through the booking process, for example: "Okay, now let's book economy class. You need to enter passenger information…," and controls the virtual assistant to perform the corresponding actions, thus guiding and assisting the user in completing the booking operation.

[0048] Step S105: If there are no abnormalities in the interaction instructions, generate third feedback information on the display page according to the interaction instructions.

[0049] Specifically, after the system determines that the interaction command is normal, it can directly generate third feedback information (such as the display of operation results, instructions for the next operation, etc.) on the display page based on the command content, so that the user can continue to perform subsequent business operations and ensure that the user can complete the required business normally. At the same time, it can also provide corresponding recommendation information based on the business handled by the user to assist the user in handling other business.

[0050] For example, if a target user successfully completes a flight search and attempts to book, the system will display the booking result in real time, such as: "Your flight booking has been completed, flight number xx, departure time xx, seat type economy class." The system may also provide follow-up instructions, such as how to check in or view e-tickets.

[0051] The page interaction method provided in this application embodiment receives a page access request and identifies the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device; generates a display page based on the device information and user information, wherein the display page displays page content in a preset display mode; receives an interaction command and determines whether the interaction command is abnormal, wherein the interaction command is sent by the target user based on the display page; if the interaction command is abnormal, a virtual person is generated on the display page, and a first feedback message is generated based on the interaction command; if a new command is received, a second feedback message is output through the virtual person, wherein the first feedback message is used to instruct the target user to input the new command by voice; if the interaction command is not abnormal, a third feedback message is generated on the display page based on the interaction command. This solves the problem in related technologies where obstacles exist in the interface interaction process, resulting in low efficiency in handling business through the interactive interface. By recognizing user and device information, the content and display method on the display page are matched with the user. At the same time, when abnormal interaction commands are detected due to the user's inability to use the display page normally, a virtual human is generated to assist the user in performing the interaction operation. This achieves the technical effect of reducing the complexity of the user's use of the display page and improving the efficiency of the user's interaction with the page.

[0052] Optionally, in the page interaction method provided in this application embodiment, generating a display page based on device information and user information includes: determining the page elements displayed on the display page and the preset display mode of the page elements based on the user information; determining the page size of the display page and the number of page elements in the display page based on the device information; and generating the display page based on the preset display mode and number of page elements and the page size.

[0053] It's important to note that page elements, or various components displayed on a page, such as buttons, text boxes, images, and dropdown menus, are the basic units that make up a website or app interface. Preset display methods are the pre-defined rules for displaying page elements based on specific user and device information, including font size, color contrast, and layout adjustments. Page size refers to the actual size of the displayed page on the user's device, which is affected by the device's screen size and resolution. The number of page elements is the number of elements that need to be displayed on the page, determined based on the device information.

[0054] Specifically, after obtaining user information, the page elements to be displayed on the display page can be determined based on the user information. In determining the page elements, the user information can be used to predict the pages that the user may visit and the controls that the user may click. These page elements are then added to the display page. Furthermore, the display method of each element, such as size, font, and voice, also needs to be determined to ensure that the page elements displayed on the page meet the user's needs.

[0055] Furthermore, after determining the relevant information of the page elements, it is also necessary to determine the overall size of the display page based on the screen size and resolution in the device information, and adjust the number of elements displayed on the page based on the screen size and performance of the device. For devices with smaller screens, the number of elements should be reduced and a simpler layout should be adopted to ensure the visibility and ease of operation of key functions.

[0056] Once the above page requirements are determined, an initial display page can be generated based on those requirements, thus completing the generation of the customized page for that user.

[0057] For example, when a user accesses an airline's website via a small tablet, the system first identifies the device's 7-inch screen with low resolution and determines that the user has poor eyesight. The system then generates a display page that uses large font sizes and high contrast to show all text, reducing the number of page elements to just a few essential function buttons such as "Flight Search," "Booking," and "Customer Service." Simultaneously, the page layout can be adjusted to a vertically stacked single-column layout, with the page size adapted to the 7-inch screen, ensuring all elements are clearly displayed and easy to operate on the small screen. In this way, even on a smaller device, the user can easily find and use the required functions, significantly reducing the learning curve and improving operational efficiency and user satisfaction.

[0058] This embodiment generates a highly customized display page based on the user's personal and device information. It not only optimizes the visuals to meet the needs of special users, but also simplifies the layout and functions to ensure compatibility with multiple devices. This reduces the complexity of business transactions for users and improves their experience using the aviation service website.

[0059] To ensure the matching degree between page elements and users, optionally, in the page interaction method provided in this application embodiment, determining the page elements displayed on the display page based on user information includes: determining the user profile of the target user based on user information and obtaining the target user's historical browsing information; selecting candidate recommendation information from multiple preset recommendation information based on historical browsing information and user profile, and determining the preset page content of the display page indicated by the page access request; determining the filling position of promotional information in the display page based on the initial element carried in the preset page content; selecting target recommendation information from candidate recommendation information based on the number of filling positions, and determining the target recommendation information and the initial element as the page elements displayed on the display page.

[0060] It should be noted that a user profile is a user description model formed by collecting and analyzing user basic information, behavioral habits, preferences, and other characteristic data. Historical browsing information records a user's past activities on the website, including pages viewed, search results, and clicks. Pre-set recommendations are various information or service items prepared in advance by the system for personalized recommendations. Candidate recommendations are a set of recommended information that may match the user's current needs or interests, filtered based on the user profile and historical browsing information. Pre-set page content refers to the layout, elements, and information already pre-defined on the page. Promotional information placement is a reserved area on the page for displaying personalized recommendations, such as banners, sidebars, or pop-ups.

[0061] Specifically, when determining page elements, a specific target user profile is first constructed based on the user's login information, operating habits and preferences, as well as other user behavior data. At the same time, the user's browsing history over a period of time is retrieved, including frequently visited pages, search keywords, etc. Then, based on the user profile and historical browsing information, a set of potentially interesting recommendations is selected from a preset recommendation information database as candidate recommendations.

[0062] For example, user operation data can be read, such as stored in a Hive table, and user preferences and behavior patterns can be analyzed. By analyzing the user's historical operation records, we can understand the content and services that the user is interested in, thereby obtaining candidate recommendation information.

[0063] It's important to note that models can be used to determine candidate recommendations, and online learning algorithms can be used to dynamically adjust these models. Based on real-time user feedback and new behavioral data, the data is converted into an input format, and the model learns online, updating its parameters and timely recommending content. For example, user feedback on recommended content will be used to adjust the recommendation model, ensuring that the recommended content always meets the user's current needs.

[0064] Additionally, based on the type of page the user visits (such as a flight search page), the system can determine the preset layout and initial elements of the page. Furthermore, based on the preset page content, the system can determine suitable locations for embedding recommended information according to the page structure, such as the sidebar or bottom banner. This ensures that the placement of the information does not interfere with the user's normal operation while ensuring that the recommended information is noticed, thereby improving the conversion rate.

[0065] Furthermore, based on the number and characteristics of the filling positions, several candidate recommendation information that are most suitable for the current scene and filling positions can be selected from the candidate recommendation information to form a target recommendation information set. These recommendation information are then combined with the initial elements in the preset page content to generate the final display page. This combines the recommendation information with the display page, ensuring a good match between the display page, the page elements in the page, and the recommendation information.

[0066] This embodiment generates personalized display pages based on user profiles and browsing history, which not only provides recommended information that meets user needs, but also ensures the rationality of page layout and the convenience of operation.

[0067] To ensure normal interaction between the user and the page, optionally, in the page interaction method provided in this application embodiment, when the interaction instruction is a click instruction, determining whether the interaction instruction is abnormal includes: determining the click position of the click instruction, and determining whether there are page elements in the preset area where the click position is located; if there are no page elements, obtaining the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain the target number; if the target number is less than the number threshold, determining that the interaction instruction is not abnormal; if the target number is greater than or equal to the number threshold, determining that the interaction instruction is abnormal.

[0068] It should be noted that a click instruction refers to a user's click operation on a page using a mouse or touchscreen to initiate a specific function or request. The preset area can be a range centered on the click location.

[0069] Specifically, when a user clicks on a page, the system records the screen coordinates of each click command to determine the specific location of the click. After determining the click location, it checks whether there are any page elements in the area where the click occurred. If no page elements are found, the user's click is considered invalid. In this case, it is necessary to determine the number of clicks the user made within a preset time period. If the number is less than a threshold, it indicates that the user accidentally touched the location, and there is no abnormality. The system can then execute the corresponding operation based on the user's click command or keep the page unchanged. If the number is greater than or equal to the threshold, it indicates that the user intended to click, but due to reasons such as visual impairment or finger dexterity, they were unable to click on a valid interactive control. In this case, it is determined that there is an abnormality in the interactive command, and the system needs to assist the user's operation to ensure its smooth execution.

[0070] This embodiment determines whether an instruction is abnormal by analyzing the click location and frequency, thereby enabling timely detection of abnormal user operations and providing corresponding assistance to the user, thus improving the operability of the user interface interaction.

[0071] To ensure normal interaction between the user and the page, optionally, in the page interaction method provided in this application embodiment, when the interaction instruction is a text instruction, determining whether the interaction instruction is abnormal includes: inputting the text instruction into a large language model to obtain the recognition result of the large language model; if the recognition result indicates that the content of the text instruction is question information, determining that the interaction instruction is abnormal; if the recognition result indicates that the content of the text instruction is operation information, determining that the interaction instruction is not abnormal.

[0072] Specifically, when the interaction command is a text command, the page first needs to perform content recognition on the text entered by the user in order to understand the user's intent. At this time, the text command needs to be input into the large language model first, and the content of the text command needs to be recognized by the large language model to obtain the recognition result. Then, based on the recognition result, it is determined whether the command contains specific operation information or questions.

[0073] When the instruction content is a problem message, it indicates that the user has encountered an unsolvable problem during the interaction with the page. In this case, the interaction instruction is determined to be abnormal. For example, if the recognition result of the large language model shows that the instruction is a problem message, such as "Why can't I check in online?", the system determines that this interaction instruction is abnormal because the user may have encountered a problem or lack of information and needs further help or explanation.

[0074] When the instruction content is operation information, it indicates that the user needs to perform the corresponding operation on the page. The page can then directly display the page corresponding to the operation without assisting the user. This indicates that there is no abnormality in the interaction instruction, thus ensuring timely feedback to the user's problematic instructions, reducing the difficulty of operation for the user, and enhancing the interactive experience between the user and the page.

[0075] For example, suppose an elderly user types "Why is there no response when I click 'Flight Search'?" into the customer service chat box on an airline's website. The system first inputs this text command into a pre-trained large language model for analysis. After the model recognizes the command, the returned result indicates that this is a problem message, asking why the operation did not receive the expected response. Therefore, the system determines that this interaction command is abnormal, indicating that the user may be experiencing difficulties with the operation.

[0076] This embodiment uses a large language model to identify whether the instructions contain problems, ensuring that user problems can be handled in a timely manner and guaranteeing the smoothness of the user's page usage process.

[0077] Optionally, in the page interaction method provided in this application embodiment, when a new instruction is received, outputting second feedback information through a virtual human includes: extracting keywords from the new instruction and determining the operation content indicated by the new instruction based on the keywords; if the operation content is a page jump, displaying the page jump on the display page and determining the page jump as the second feedback information; if the operation content is an operation name, generating operation steps corresponding to the operation name, generating a virtual human's guidance action based on the operation steps, and determining the virtual human's guidance action as the second feedback information.

[0078] It should be noted that new instructions are further actions or inquiries issued by the user based on previous interaction feedback. Keywords, or key information carried in new instructions, are used to quickly understand the user's intent, such as "jump" or "action name".

[0079] Specifically, when a user performs an operation using a virtual human, the system first needs to use natural language processing technology to parse the new command issued by the user, extract keywords, and quickly identify whether the user's intention is to jump to a page or to perform a specific operation.

[0080] When a new command indicates that the user needs to be redirected to a different page, the system will immediately redirect to the page specified by the user and present the redirected page as feedback information to the user.

[0081] When a user mentions a complex operation or requires specific steps, the system will generate a series of guiding actions using a virtual human to demonstrate how to complete the operation step by step. This dual visual and auditory feedback reduces the difficulty of operation, providing intuitive and easy-to-understand guidance, especially for elderly users unfamiliar with the process, thus enhancing their ability to operate independently.

[0082] It should be noted that the virtual human can also call corresponding APIs based on the user's voice commands through custom business logic processing functions. For example, if the user says "search for flights from Beijing to Shanghai," the virtual human can call the flight search API and return the relevant flight information.

[0083] This embodiment analyzes the keywords entered by the user and executes the corresponding operations based on the keywords, thereby reducing the complexity of user interaction with the display interface and improving the efficiency of user business processing.

[0084] Optionally, in the page interaction method provided in the embodiments of this application, the method further includes: determining whether the target user has a voice interaction need; if the target user has a voice interaction need, obtaining a voice material library according to the voice interaction need, and training a neural network model according to the voice material library to obtain a voice conversion model; converting the voice text output to the target user through the voice conversion model to obtain the target output voice, and outputting the target output voice through a virtual human.

[0085] Specifically, when user input requires voice interaction, a voice conversion model needs to be trained. At this time, a suitable dataset needs to be extracted from the voice material library to train the neural network model, enabling it to generate sounds that meet the user's needs. The information to be conveyed to the user is input into the voice conversion model in text form. The model converts the text into a voice file that simulates the user's voice, thereby providing voice services to the user. This allows the user to receive business information without additional operation, greatly facilitating elderly users, especially those who rely on voice assistance and specify voice voices, thereby achieving the technical effect of improving the efficiency of users' business interactions.

[0086] It's worth noting that Hugging Face's Transformers library and pre-trained models can be used for natural language processing. For example, pre-trained dialogue generation models can be used to implement intelligent dialogue functionality, enabling virtual humans to understand and respond to user commands.

[0087] It should be noted that a voice-to-text tool can be used to perform speech recognition and convert it into text so that the virtual human can understand the user's voice input and perform subsequent operations based on the voice information.

[0088] It should be noted that speech synthesis technology and text feedback can be used to provide the user with feedback on the operation results in both voice and text form. For example, a virtual human can generate voice feedback through speech synthesis technology and display text information on the interface to ensure that the user can clearly understand the operation results.

[0089] This embodiment uses a neural network model to generate the voice files required by the user and provides voice services to the user, thereby improving the convenience of user interaction.

[0090] It should be noted that virtual avatars can be created and managed through a virtual avatar management platform. Figure 2 This is a schematic diagram of an optional virtual human management platform provided according to an embodiment of this application, such as... Figure 2As shown, the platform includes: Virtual Human Profile 21: The basic shape of the virtual human is created using polygonal modeling technology in 3D modeling software. Details are added through a subdivision surface modifier, and facial expressions and body details are sculpted using sculpting tools. Voice Generation Module 22: Voice cloning technology allows for preprocessing of samples (including noise reduction and frame segmentation) with only a small number of audio samples. The preprocessed audio data is input into a trained voice cloning model, which learns the features of the samples to generate voices similar to the target voice, achieving high-quality voice cloning. This technology supports multiple languages ​​to meet the needs of different users. Related Material Library 23: A content management system is used to store and manage the material library, including product manuals, technical documents, etc., allowing the virtual human to easily access the information needed by the user. Character Generation Module 24: Combined with plugins, this module drives the virtual human model to generate corresponding animations based on the scene.

[0091] Furthermore, Figure 3 This is a schematic diagram of an optional virtual human generation process provided according to an embodiment of this application, such as... Figure 3 As shown, the initial character image of the virtual human is first generated, and different output voices are generated according to user needs. When there are many user needs, the needs need to be placed in a queue and generated in order. Based on the information obtained from the material library to provide feedback to the user, the corresponding voice is generated, and the virtual human's movements and lip movements are generated synchronously based on the voice, so as to combine the virtual human image and the information output by the virtual human to be displayed to the user.

[0092] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0093] This application also provides a page interaction device. It should be noted that the page interaction device of this application can be used to execute the page interaction method provided in this application. The page interaction device provided in this application is described below.

[0094] Figure 4 This is a schematic diagram of a page interaction device provided according to an embodiment of this application. For example... Figure 4 As shown, the device includes: a first receiving unit 41, a first generating unit 42, a second receiving unit 43, a second generating unit 44, and a third generating unit 45.

[0095] The first receiving unit 41 is used to receive a page access request and identify the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device.

[0096] The first generation unit 42 is used to generate a display page based on device information and user information, wherein the display page displays page content through a preset display method.

[0097] The second receiving unit 43 is used to receive interactive instructions and determine whether there is any abnormality in the interactive instructions, wherein the interactive instructions are sent by the target user based on the display page.

[0098] The second generation unit 44 is used to generate a virtual human on the display page when there is an abnormality in the interaction command, generate first feedback information according to the interaction command, and output second feedback information through the virtual human when a new command is received. The first feedback information is used to instruct the target user to input a new command by voice.

[0099] The third generation unit 45 is used to generate third feedback information on the display page according to the interaction instructions if there are no abnormalities in the interaction instructions.

[0100] The page interaction device provided in this application embodiment receives a page access request through a first receiving unit 41, and identifies the device information of the login device used by the target user and the user information of the target user based on the page access request. The page access request is sent by the target user through a user terminal device. A first generating unit 42 generates a display page based on the device information and user information, and the display page displays page content using a preset display method. A second receiving unit 43 receives an interaction command and determines whether the interaction command is abnormal. The interaction command is sent by the target user based on the display page. If the interaction command is abnormal, the second generating unit 44 generates a virtual person on the display page, generates first feedback information based on the interaction command, and outputs second feedback information through the virtual person when a new command is received. The first feedback information is used to instruct the target user to input a new command via voice. If the interaction command is not abnormal, the third generating unit 45 generates third feedback information on the display page based on the interaction command. This solves the problem in related technologies where obstacles exist in the interface interaction process, leading to low efficiency in handling business through the interactive interface. By recognizing user and device information, the content and display method on the display page are matched with the user. At the same time, when abnormal interaction commands are detected due to the user's inability to use the display page normally, a virtual human is generated to assist the user in performing the interaction operation. This achieves the technical effect of reducing the complexity of the user's use of the display page and improving the efficiency of the user's interaction with the page.

[0101] Optionally, in the page interaction device provided in the embodiments of this application, the first generation unit 42 includes: a first determining module, used to determine the page elements displayed in the display page and the preset display mode of the page elements according to user information; a second determining module, used to determine the page size of the display page and the number of page elements in the display page according to device information; and a first generation module, used to generate the display page according to the preset display mode and number of page elements and the page size.

[0102] Optionally, in the page interaction device provided in this application embodiment, the first determining module includes: a first determining submodule, used to determine the user profile of the target user based on user information and obtain the target user's historical browsing information; a first selecting submodule, used to select candidate recommendation information from multiple preset recommendation information based on historical browsing information and user profile, and determine the preset page content of the display page indicated by the page access request; a second determining submodule, used to determine the filling position of promotional information in the display page based on the initial element carried in the preset page content; and a second selecting submodule, used to select target recommendation information from candidate recommendation information based on the number of filling positions, and determine the target recommendation information and the initial element as the page elements displayed in the display page.

[0103] Optionally, in the page interaction device provided in this application embodiment, when the interaction instruction is a click instruction, the second receiving unit 43 includes: a first judging module, used to determine the click position of the click instruction and determine whether there is a page element in the preset area where the click position is located; a second judging module, used to obtain the number of times the target user repeatedly executes the interaction instruction within a preset time period when there is no page element, and obtain the target number; a third determining module, used to determine that the interaction instruction is not abnormal when the target number is less than the number threshold; and a fourth determining module, used to determine that the interaction instruction is abnormal when the target number is greater than or equal to the number threshold.

[0104] Optionally, in the page interaction device provided in the embodiments of this application, when the interaction instruction is a text instruction, the second receiving unit 43 includes: an input module, used to input the text instruction into a large language model to obtain the recognition result of the large language model; a fifth determining module, used to determine that the interaction instruction is abnormal when the recognition result indicates that the content of the text instruction is question information; and a sixth determining module, used to determine that the interaction instruction is not abnormal when the recognition result indicates that the content of the text instruction is operation information.

[0105] Optionally, in the page interaction device provided in this application embodiment, the second generation unit 44 includes: an extraction module, used to extract keywords from the new instruction and determine the operation content indicated by the new instruction based on the keywords; a display module, used to display the jump page on the display page when the operation content is a jump page, and determine the jump page as the second feedback information; and a second generation module, used to generate operation steps corresponding to the operation name when the operation content is an operation name, generate the virtual human's guidance action based on the operation steps, and determine the virtual human's guidance action as the second feedback information.

[0106] Optionally, in the page interaction device provided in the embodiments of this application, the device further includes: a judgment unit, used to judge whether the target user has a voice interaction need; a training unit, used to obtain a voice material library according to the voice interaction need when the target user has a voice interaction need, and to train the neural network model according to the voice material library to obtain a voice conversion model; and an output unit, used to convert the voice text output to the target user through the voice conversion model to obtain the target output voice, and to output the target output voice through a virtual human.

[0107] The aforementioned page interaction device includes a processor and a memory. The first receiving unit 41, the first generating unit 42, the second receiving unit 43, the second generating unit 44, the third generating unit 45, etc., are all stored in the memory as program units. The processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0108] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured; by adjusting kernel parameters, the problem of low efficiency in handling business through an interactive interface, stemming from obstacles in the user interface process, can be addressed.

[0109] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0110] This invention provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the page interaction method.

[0111] This invention provides a processor for running a program, wherein the program executes the page interaction method during runtime.

[0112] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of this application, such as... Figure 5As shown, this embodiment of the invention provides an electronic device 50, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of the above-described page interaction method. The device in this document can be a server, PC, PAD, mobile phone, etc.

[0113] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of initializing the above-described page interaction method.

[0114] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0119] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0120] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0122] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A page interaction method, characterized in that, include: Receive a page access request, and identify the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device; A display page is generated based on the device information and the user information, wherein the display page displays page content through a preset display method; Receive an interaction instruction and determine whether the interaction instruction is abnormal, wherein the interaction instruction is sent by the target user based on the display page; In the event of an anomaly in the interaction command, a virtual human is generated on the display page, and a first feedback message is generated based on the interaction command. Upon receiving a new command, a second feedback message is output through the virtual human, wherein the first feedback message is used to instruct the target user to voice input the new command. If there are no abnormalities in the interaction instructions, a third feedback message is generated on the display page according to the interaction instructions.

2. The method according to claim 1, characterized in that, Generating a display page based on the device information and the user information includes: The page elements displayed on the display page and the preset display mode of the page elements are determined based on the user information. The page size of the display page and the number of page elements in the display page are determined based on the device information; The display page is generated based on the preset display method and quantity of the page elements and the page size.

3. The method according to claim 2, characterized in that, The page elements displayed on the display page are determined based on the user information, including: Based on the user information, determine the user profile of the target user and obtain the target user's historical browsing information; Based on the historical browsing information and the user profile, candidate recommendation information is selected from multiple preset recommendation information, and the preset page content of the display page indicated by the page access request is determined. The position of the promotional information in the display page is determined based on the initial elements carried in the preset page content; Based on the number of filling positions, target recommendation information is selected from the candidate recommendation information, and the target recommendation information and the initial element are determined as the page elements displayed on the display page.

4. The method according to claim 1, characterized in that, When the interaction instruction is a click instruction, determining whether the interaction instruction is abnormal includes: Determine the click location of the click instruction, and determine whether there are page elements in the preset area where the click location is located; In the absence of the page element, obtain the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain the target number; If the target number of times is less than the number of times threshold, it is determined that the interaction instruction is not abnormal; If the target number of times is greater than or equal to the number of times threshold, it is determined that the interaction instruction is abnormal.

5. The method according to claim 1, characterized in that, When the interaction command is a text command, determining whether the interaction command is abnormal includes: The text command is input into the large language model to obtain the recognition result of the large language model; If the recognition result indicates that the content of the text instruction is a problem message, it is determined that the interaction instruction is abnormal; If the recognition result indicates that the content of the text instruction is operation information, it is determined that the interaction instruction is not abnormal.

6. The method according to claim 1, characterized in that, Upon receiving a new instruction, the virtual human outputs the following second feedback information: Extract keywords from the newly added instructions, and determine the operation content indicated by the newly added instructions based on the keywords; When the operation involves redirecting to a page, the redirected page is displayed on the display page, and the redirected page is identified as the second feedback information. When the operation content is an operation name, the operation steps corresponding to the operation name are generated, and the virtual human's guidance action is generated according to the operation steps, and the virtual human's guidance action is determined as the second feedback information.

7. The method according to claim 1, characterized in that, The method further includes: Determine whether the target user has a need for voice interaction; When the target user has the voice interaction requirement, a voice material library is obtained according to the voice interaction requirement, and a neural network model is trained according to the voice material library to obtain a voice conversion model. The voice text output to the target user is converted through the voice conversion model to obtain the target output voice, and the target output voice is output through the virtual human.

8. A page interaction device, characterized in that, include: The first receiving unit is configured to receive a page access request and identify the device information of the login device used by the target user and the user information of the target user based on the page access request, wherein the page access request is sent by the target user through the user terminal device; The first generation unit is configured to generate a display page based on the device information and the user information, wherein the display page displays page content through a preset display method; The second receiving unit is used to receive the interaction instruction and determine whether the interaction instruction is abnormal, wherein the interaction instruction is sent by the target user based on the display page; The second generation unit is configured to generate a virtual human on the display page when the interaction instruction is abnormal, generate first feedback information according to the interaction instruction, and output second feedback information through the virtual human when a new instruction is received, wherein the first feedback information is used to instruct the target user to voice input the new instruction; The third generation unit is used to generate third feedback information on the display page according to the interaction instruction if there is no abnormality in the interaction instruction.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the page interaction method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program executes the page interaction method according to any one of claims 1 to 7 when it runs.

Images