Page interaction method and device and electronic equipment

Abstract

The invention discloses a page interaction method and device and electronic equipment. The method comprises the following steps: receiving a page access request, and identifying equipment information of login equipment used by a target user and user information of the target user according to the page access request; generating a display page according to the equipment information and the user information; receiving an interaction instruction, and judging whether the interaction instruction is abnormal or not; generating a virtual human in the display page under the condition that the interaction instruction is abnormal, generating first feedback information according to the interaction instruction, and outputting second feedback information through the virtual human under the condition that a newly-added instruction is received; and under the condition that the interaction instruction is not abnormal, generating third feedback information on the display page according to the interaction instruction. Through the method and the device, the problem that the efficiency of handling business through an interactive interface is relatively low due to obstacles in an interface interaction process in related technologies is solved.

Description

Technical Field

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

[0002] As the number of passengers on flights continues to increase, the interactive interfaces of airlines' apps and websites usually have many business processing modules, allowing passengers to handle most of the business. However, as the number of business processing modules continues to increase, it will make it very inconvenient for elderly passengers to use. The existing processing method is to directly adjust the interface to auxiliary mode when the user is identified as an elderly person. However, if the user's information is incomplete or the user is a special user, the system will not be able to adjust to the auxiliary mode in time, thereby increasing the difficulty of customers in handling business and reducing business processing efficiency.

[0003] There are obstacles in the interface interaction process in related technologies, which leads to low efficiency in handling business through the interactive interface. Currently, no effective solution has been proposed. Summary of the Invention

[0004] The present application provides a page interaction method, device 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 the present 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 terminal device; generating a display page based on the device information and user information, wherein the display page displays page content in a preset display mode; 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, and generating first feedback information based on the interaction instruction, and if a new instruction is received, outputting second feedback information through the virtual person, wherein the first feedback information is used to instruct the target user to input the new instruction by voice; if the interaction instruction is normal, 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 displayed in 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 the page elements and the page size.

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

[0008] Optionally, in the case where the interaction instruction is a click instruction, determining whether there is an abnormality in the interaction instruction includes: determining the click position of the click instruction, and determining whether there is a page element in the preset area where the click position is located; in the case where there is no page element, obtaining the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain a target number; in the case where the target number is less than a number threshold, determining that there is no abnormality in the interaction instruction; in the case where the target number is greater than or equal to the number threshold, determining that there is an abnormality in the interaction instruction.

[0009] Optionally, when the interaction instruction is a text instruction, determining whether there is an abnormality in the interaction instruction includes: inputting the text instruction into a large language model to obtain a recognition result of the large language model; when the recognition result represents that the content of the text instruction is question information, determining that there is an abnormality in the interaction instruction; when the recognition result represents that the content of the text instruction is operation information, determining that there is no abnormality in the interaction instruction.

[0010] Optionally, when a new instruction is received, outputting the second feedback information through the virtual person includes: extracting keywords in the new instruction, and determining the operation content indicated by the new instruction based on the keywords; when the operation content is a jump page, displaying the jump page on the display page, and determining the jump page as the second feedback information; when the operation content is an operation name, generating operation steps corresponding to the operation name, and generating the virtual person's guidance actions according to the operation steps, and determining the virtual person's guidance actions as the second feedback information.

[0011] Optionally, the method also includes: determining whether the target user has a voice interaction demand; if the target user has a voice interaction demand, obtaining a voice material library according to the voice interaction demand, 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 a target output voice, and outputting the target output voice through a virtual person.

[0012] According to another aspect of the present application, a page interaction device is provided. The device includes: a first receiving unit for 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 terminal device; a first generating unit for generating a display page based on the device information and user information, wherein the display page displays page content in a preset display mode; a second receiving unit for 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; a second generating unit for generating a virtual person on the display page if an interaction instruction is abnormal, generating first feedback information based on the interaction instruction, and outputting second feedback information through the virtual person if a new instruction is received, wherein the first feedback information is used to indicate that the target user inputs the new instruction by voice; and a third generating unit for generating third feedback information on the display page based on the interaction instruction if no abnormality occurs in the interaction instruction.

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

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

[0015] Through this application, the following steps are adopted: 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 the page content through a preset display method; receiving an interaction instruction, and judging whether there is an abnormality in the interaction instruction, wherein the interaction instruction is sent by the target user based on the display page; if there is an abnormality in the interaction instruction, generating a virtual person in the display page, and generating first feedback information based on the interaction instruction, and outputting second feedback information through the virtual person when receiving a new instruction, wherein the first feedback information is used to instruct the target user to input the new instruction by voice; if there is no abnormality in the interaction instruction, generating third feedback information on the display page based on the interaction instruction. This solves the problem that there are obstacles in the interface interaction process in the related art, resulting in low efficiency in handling business through the interactive interface. By identifying user information and device information, the display content and display method in the display page are matched with the user. At the same time, when it is detected that the user is unable to use the display page normally and an abnormal interaction instruction occurs, a virtual person is generated to assist the user in performing the interaction operation, thereby achieving 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0017] Figure 1 is a flow chart of a page interaction method provided according to an embodiment of the present application;

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

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

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

[0021] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0023] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] It should be noted that the page interaction method, device and electronic device determined in the present disclosure can be used in the field of artificial intelligence, and can also be used in any field other than the field of artificial intelligence. The application field of the page interaction method, device and electronic device determined in the present disclosure is not limited.

[0026] It should be noted that the collected 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, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process will be entered. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0027] The embodiments or examples of the present disclosure are not exhaustive, but are merely illustrations of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.

[0028] For ease of description, some nouns or terms involved in the embodiments of the present application are explained below:

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

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

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

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

[0033] Figure 1 This is a flow chart of the page interaction method provided according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0034] Step S101: 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 according to the page access request, wherein the page access request is sent by the target user through a user terminal device.

[0035] It should be noted that a page access request is a behavioral signal indicating that a user is attempting to access a specific page on a website or application. The user-end device is the device used by the target user to access the webpage or application. Device information can include the hardware configuration, operating system version, and network status of the device used to access the page, which is used to determine device attributes and performance. User information can include the target user's age and gender, which is used to identify user characteristics and provide personalized services.

[0036] Specifically, the executing body of this embodiment can be a page control system. When the target user sends a page access request through a user-end device, the system immediately receives the request, analyzes the device information contained in the request (such as obtained through the User-Agent header information), and attempts to identify the relevant information of the target user (through user account data, historical behavior records or device attributes). After identifying the device information and user information, the page display format of the feedback interface of this visit can be adjusted according to the device information and user information, thereby ensuring that the user can access the page without obstacles.

[0037] Step S102: generating a display page according to the device information and the user information, wherein the display page displays page content in a preset display manner.

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

[0039] For example, different font sizes, margins, layout methods, etc. are defined for different screen sizes (mobile phones, tablets, desktops). For example, a single-column layout is used for mobile phones, a double-column layout is used for tablets, and a multi-column layout is used for desktops. This allows for quick building of responsive layouts to ensure a good user experience on various devices.

[0040] Similarly, you can also listen to button click events and dynamically adjust the overall font size of the page. For example, when you click the zoom in button, the font size will increase by 1.2 times, and when you click the zoom out button, the font size will decrease 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, use large fonts and large icons, and reduce menu levels.

[0041] Step S103: 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.

[0042] Specifically, after the initial page is displayed on the display page, the user will operate in the display page. At this time, the system will receive the interaction instructions from the target user and make an abnormality judgment to determine whether the user performs an abnormal interaction operation. For example, if the user clicks on position A more than 3 times, and the style of the interaction module near position A is smaller and the user cannot click it, then there is an abnormality in the interaction instruction.

[0043] It should be noted that when determining whether an interactive instruction is abnormal, it can be identified through a variety of preset judgment methods, including identification based on whether the click position is abnormal, or identification based on whether the click content is valid.

[0044] For example, when an elderly user clicks the flight search button, the system receives the instruction and checks whether it is abnormal. If the instruction is correct, the system will jump to the flight search interface. If the user accidentally clicks a blank area on the screen (not an active operation area), the system will recognize this behavior as abnormal and will not perform any action.

[0045] Step S104: When an abnormality occurs in the interaction instruction, a virtual person is generated in the display page, and first feedback information is generated according to the interaction instruction. When a new instruction is received, second feedback information is output through the virtual person, wherein the first feedback information is used to indicate that the target user inputs the new instruction by voice.

[0046] Specifically, when the system determines that an interactive instruction is abnormal, indicating that the user is having difficulty interacting with the display page, a virtual person is generated on the display page and provides the user with first feedback (such as a voice prompt) through the virtual person, explaining the reason for the abnormal instruction and guiding the user to input new instructions through voice, thereby helping the user perform subsequent operations. Subsequently, the system outputs second feedback information through the virtual person, providing operation guidance or corrected operation results in voice form. This helps the user understand and correct operational errors through voice assistance, while allowing the virtual person to perform correct interactive operations, thereby enhancing the friendliness and intelligence of human-computer interaction.

[0047] For example, suppose a user searches for flights and attempts to book, but the process fails due to selecting an invalid seat type. In this case, the system-generated avatar informs the user via voice: "The seat type you selected is unavailable. We recommend trying Economy or Business Class." The system then guides the user through voice commands to reselect their seat type. The user says, "I want to book Economy Class." The system recognizes the new voice command, and the avatar confirms it and guides the user through the booking process, for example, "Okay, now let's book Economy Class. You need to enter your passenger information..." The avatar then performs the corresponding actions, guiding and assisting the user in completing the booking process.

[0048] Step S105 : When there is no abnormality in the interaction instruction, third feedback information is generated on the display page according to the interaction instruction.

[0049] Specifically, after the system determines that the interactive instruction 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 instruction content, so that the user can continue to perform subsequent business operations, ensuring that the user can complete the business that needs to be performed normally. At the same time, it can also further provide corresponding recommendation information based on the business handled by the user to assist the user in handling other business.

[0050] For example, if the target user successfully completes the flight query and attempts to book, the system will display the booking results in real time, such as: "Your flight booking is completed, flight number xx, departure time xx, seat type economy class." At the same time, the system may provide subsequent operation guidance, such as how to check in or view e-ticket information.

[0051] The page interaction method provided by the embodiment of the present application 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 according to the page access request, wherein the page access request is sent by the target user through the user terminal device; generates a display page according to the device information and the user information, wherein the display page displays the page content in a preset display mode; receives an interaction instruction and determines whether there is an abnormality in the interaction instruction, wherein the interaction instruction is sent by the target user based on the display page; if there is an abnormality in the interaction instruction, generates a virtual person in the display page, and generates first feedback information according to the interaction instruction, and outputs second feedback information through the virtual person when a new instruction is received, wherein the first feedback information is used to instruct the target user to input the new instruction by voice; if there is no abnormality in the interaction instruction, generates third feedback information on the display page according to the interaction instruction. This solves the problem that there are obstacles in the interface interaction process in the related art, resulting in low efficiency in handling business through the interactive interface. By identifying user information and device information, the display content and display method in the display page are matched with the user. At the same time, when it is detected that the user is unable to use the display page normally and an abnormal interaction instruction occurs, a virtual person is generated to assist the user in performing the interaction operation, thereby achieving 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 an embodiment of the present application, generating a display page based on device information and user information includes: determining the page elements displayed in 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 a display page based on the preset display mode and number of the page elements and the page size.

[0053] It should be noted that page elements, namely the various components displayed on the page, such as buttons, text boxes, images, drop-down menus, etc., are the basic units that make up the website or app interface. The preset display mode refers to the page element display rules set in advance for specific user information and device information, including font size, color contrast, layout adjustment, etc. The page size refers to the actual size of the displayed page on the user's device, which is affected by the device screen size and resolution. The number of page elements refers to 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 displayed in the display page can be determined based on the user information. When determining the page elements, the pages that the user may visit and the controls that the user may click can be predicted based on the user information, and then these page elements can be added to the display page. It is also necessary to determine the display method of each element, such as size, font, voice, etc., to ensure that the page elements displayed on the page can 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 displayed 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, reduce the number of elements and adopt a simpler layout to ensure the visibility and ease of operation of key functions.

[0056] After the above page requirements are determined, an initial display page can be generated according to the above page requirements, thereby completing the generation operation of the customized page for the user.

[0057] For example, when a target accesses an airline website through a small tablet device, the system first recognizes that the device screen is 7 inches and has a low resolution, and also determines that the user has poor eyesight. At this point, the display page generated by the system can display all text in large font and high contrast mode, reducing the number of page elements to the most basic function buttons, such as "Flight Inquiry", "Booking" and "Customer Service". At the same time, the page layout can be adjusted to a vertically stacked single column layout, and the page size is adapted to a 7-inch screen, ensuring that all elements are clearly displayed and easy to operate on the small screen. In this way, even on devices with smaller screens, the user can easily find and use the required functions, greatly reducing the difficulty of use and improving operational efficiency and satisfaction.

[0058] This embodiment generates a highly customized display page based on the user's personal information and device information. It is not only visually optimized to meet the needs of special users, but also streamlined in layout and functionality to ensure that it can be adapted to a variety of devices, thereby reducing the complexity of users' business transactions and improving the user experience of using the aviation service website.

[0059] In order to ensure the matching degree between page elements and users, optionally, in the page interaction method provided in the embodiment of the present application, determining the page elements displayed in the display page based on user information includes: determining the user portrait of the target user based on the user information, and obtaining the historical browsing information of the target user; selecting candidate recommendation information from multiple preset recommendation information based on the historical browsing information and the user portrait, and determining the preset page content of the display page indicated by the page access request; determining the filling position of the promotional information in 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 displayed in the display page.

[0060] It should be noted that the user portrait is a user description model formed by collecting and analyzing user basic information, behavioral habits, preferences and other characteristic data. Historical browsing information records the user's past activities on the website, including browsed pages, search content, click behavior, etc. Preset recommendation information is pre-prepared by the system for various types of information or service items for personalized recommendation. Candidate recommendation information is a set of recommended information that may match the user's current needs or interests, filtered out based on user portraits and historical browsing information. The preset page content is the layout, elements and information that have been preset in the display page. The filling position of promotional information is the position reserved in the page for displaying personalized recommendation information, such as banners, sidebars, pop-ups, etc.

[0061] Specifically, when determining page elements, we first construct a specific target user portrait based on the user's login information, operating habits and preferences, and other user behavior data. At the same time, we retrieve the user's browsing history over the past period of time, including frequently visited pages, search keywords, etc., and then, based on the user portrait and historical browsing information, select a group of recommended information that may be of interest from the preset recommendation information library as candidate recommendations.

[0062] For example, reading user operation data, such as storing the data in a Hive table, analyzing user preferences and behavior patterns, and understanding the content and services that users are interested in by analyzing their historical operation records, thereby obtaining candidate recommendation information.

[0063] It should be noted that models can be used to determine candidate recommendation information, and online learning algorithms can be used to dynamically adjust the model. Based on real-time user feedback and new behavioral data, the model is converted into an input format, and online learning is performed within the model to update model parameters and timely update recommended content. For example, user feedback on recommended content can be used to adjust the recommendation model to ensure that the recommended content always meets the user's current needs.

[0064] At the same time, the preset layout and initial elements of the page can be determined based on the type of page the user visits (such as the flight inquiry page). Further, based on the preset page content, the appropriate location for embedding recommended information can be determined according to the page structure, such as the page sidebar, bottom banner, etc., to ensure that the filling position does not affect the user's normal operation, and can ensure that the recommended information can be 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, and these recommendation information can be combined with the initial elements in the preset page content to generate the final display page, thereby combining the recommendation information with the display page to ensure a good match between the display page and the page elements and recommendation information in the page.

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

[0067] In order to ensure normal interaction between the user and the page, optionally, in the page interaction method provided in the embodiment of the present application, when the interaction instruction is a click instruction, judging whether there is an abnormality in the interaction instruction includes: determining the click position of the click instruction, and judging whether there is a page element in the preset area where the click position is located; when there is no page element, obtaining the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain a target number; when the target number is less than a number threshold, determining that there is no abnormality in the interaction instruction; when the target number is greater than or equal to the number threshold, determining that there is an abnormality in the interaction instruction.

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

[0069] Specifically, when the user clicks on the page, the system records the screen coordinates of each click instruction to determine the specific location of the user's click, and after determining the click location, determines whether there is a page element in the area of ​​the click location. If there is no page element, it indicates that the user's click is an invalid click. At this time, it is necessary to determine the number of clicks of the user within the preset time period. If the number is less than the number threshold, it indicates that the user accidentally touched the location, and then it is determined that there is no abnormality. The corresponding operation can be performed according to the user's click instruction or the page remains unchanged. If the number is greater than or equal to the number threshold, it indicates that the user wants to click, but due to some reasons, such as vision factors, finger flexibility, etc., he has not been able to click on the effective interactive control. At this time, it can be determined that there is an abnormality in the interactive instruction, and the user's operation needs to be assisted to ensure the smooth execution of the operation.

[0070] This embodiment determines whether there is an abnormality in the instruction through the click position and click frequency of the instruction, thereby achieving the effect of timely discovering the user's abnormal operation and performing corresponding auxiliary operations on the user, thereby improving the operability of the user's interaction with the interface.

[0071] In order to ensure normal interaction between the user and the page, optionally, in the page interaction method provided in the embodiment of the present application, when the interaction instruction is a text instruction, determining whether there is an abnormality in the interaction instruction includes: inputting the text instruction into a large language model to obtain a recognition result of the large language model; when the recognition result represents that the content of the text instruction is question information, determining that there is an abnormality in the interaction instruction; when the recognition result represents that the content of the text instruction is operation information, determining that there is no abnormality in the interaction instruction.

[0072] Specifically, when the interactive instructions are text instructions, the page first needs to recognize the content of the text entered by the user in order to understand the user's intention. At this time, the text instructions need to be input into the large language model first, and the content of the text instructions needs to be recognized by the large language model to obtain the recognition results, and then judge whether the instructions contain specific operation information or questions based on the recognition results.

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

[0074] When the instruction content is operation information, it indicates that the user needs to perform a corresponding operation on the page at this time. The page corresponding to the operation can be directly displayed on the page without assisting the user, which indicates that there is no abnormality in the interactive instruction, thereby ensuring that the user's problem instructions can be fed back in time, reducing the user's operation difficulty and enhancing the interactive experience between the user and the page.

[0075] For example, suppose an elderly user enters the text in the customer service chat box on an airline website: "Why is there no response when I click 'Flight Search'?" The system first feeds this text command into a trained large language model for analysis. After the model recognizes it, it returns a result indicating that this is a question, asking why the action didn't produce the expected response. The system then determines that this interaction is abnormal, indicating that the user may be experiencing difficulty with the operation.

[0076] This embodiment uses a large language model to identify whether an instruction carries a problem, thereby ensuring that usage problems encountered by users can be handled in a timely manner and ensuring the smoothness of the user's page usage process.

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

[0078] It should be noted that new commands are further operations or inquiries issued by users based on previous interaction feedback. Keywords are key information carried in new commands, such as "jump" and "operation name", which are used to quickly understand user intent.

[0079] Specifically, when a user uses a virtual person to perform an operation, it is first necessary to use natural language processing technology to parse the new instructions issued by the user, extract the keywords, and quickly identify whether the user's intention is to jump to a page or execute a specific operation.

[0080] When the newly added instruction indicates that the user needs to jump to a page, the system will immediately jump to the jump page indicated by the user and present the jump page to the user as feedback information.

[0081] When the user mentions a complex operation or requires specific step-by-step guidance, the system uses a virtual human to generate a series of guided actions, demonstrating how to complete the operation step by step. This dual visual and audio feedback reduces the difficulty of operation, especially for elderly users who are unfamiliar with the operation, providing intuitive and easy-to-understand guidance and improving their ability to operate independently.

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

[0083] This embodiment analyzes the keywords input by the user and performs corresponding operations according to the keywords, thereby reducing the complexity of the user's interaction with the display interface and improving the user's business processing efficiency.

[0084] Optionally, in the page interaction method provided in the embodiment of the present application, the method also includes: determining whether the target user has a voice interaction demand; if the target user has a voice interaction demand, obtaining a voice material library according to the voice interaction demand, 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 a target output voice, and outputting the target output voice through a virtual person.

[0085] Specifically, when user input requires voice interaction, a voice conversion model needs to be trained. At this time, a suitable data set needs to be extracted from the voice material library to train the neural network model so that it can generate sounds that meet user needs, and the information that needs 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 sound required by the user, thereby providing voice services to the user, allowing the user to receive business information without additional operation, which greatly facilitates elderly users, especially those who rely on voice assistance and specified voice sounds, thereby achieving the technical effect of improving the efficiency of user business interaction.

[0086] It's important to note that you can use Hugging Face's Transformers library and pre-trained models for natural language processing. For example, you can use a pre-trained dialogue generation model to implement intelligent conversational features, allowing virtual humans to understand and respond to user commands.

[0087] It should be noted that voice-to-text tools can be used to perform voice recognition and convert it into text so that the virtual person can understand the voice information input by the user 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 users with feedback on operation results in the form of voice and text. For example, a virtual human can generate voice feedback through speech synthesis technology and display text information on the interface to ensure that users can clearly understand the operation results.

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

[0090] It should be noted that when creating a virtual person, you can create and manage it through the virtual person management platform. Figure 2 is a schematic diagram of an optional virtual human management platform provided according to an embodiment of the present application, such as Figure 2As shown, the platform includes: Virtual human profile 21: Use the polygonal modeling technology of 3D modeling software to create the basic shape of the virtual human, use the subdivision surface modifier to increase model details, and use sculpting tools to shape facial expressions and body details. Voice generation module 22: Can use timbre cloning technology, only a small number of sample audio samples are needed to pre-process the samples, including noise reduction, framing, etc. The pre-processed audio data is input into the trained timbre cloning model. The model generates a voice similar to the target timbre by learning the characteristics of the sample, achieving high-quality voice cloning. This technology supports multiple languages ​​to meet the needs of different users. Associated material library 23: Use the content management system to store and manage the material library, including product manuals, technical documents, etc., so that the virtual human can call the required information at any time according to user needs. Character generation module 24: Combined with plug-ins, the virtual human model is driven by the scene to generate corresponding animations.

[0091] Further, Figure 3 is a schematic diagram of an optional virtual human generation process provided in an embodiment of the present application, such as Figure 3 As shown, first, the initial character image of the virtual person is 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 sequence. According to the information fed back to the user obtained from the material library, the corresponding voice is generated, and the virtual person's movements and lip shapes are generated synchronously according to the voice, so as to combine the virtual person image and the information output by the virtual person to be displayed to the user.

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

[0093] The embodiment of the present application further provides a page interaction device. It should be noted that the page interaction device of the embodiment of the present application can be used to execute the page interaction method provided in the embodiment of the present application. The page interaction device provided in the embodiment of the present application is introduced below.

[0094] Figure 4 Schematic diagram of a page interaction device according to an embodiment of the present application. 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 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 according to the page access request, wherein the page access request is sent by the target user via a user terminal device.

[0096] The first generating unit 42 is configured to generate a display page according to the device information and the user information, wherein the display page displays page content in a preset display manner.

[0097] The second receiving unit 43 is configured to receive an interaction instruction and determine whether the interaction instruction is abnormal, wherein the interaction instruction is sent by a target user based on a display page.

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

[0099] The third generating unit 45 is configured to generate third feedback information on the display page according to the interaction instruction when there is no abnormality in the interaction instruction.

[0100] The page interaction device provided in the embodiment of the present application 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, wherein the page access request is sent by the target user through the user terminal device; a first generating unit 42 generates a display page based on the device information and the user information, wherein the display page displays the page content in a preset display mode; a second receiving unit 43 receives an interaction instruction and determines whether the interaction instruction is abnormal, wherein the interaction instruction is sent by the target user based on the display page; the second generating unit 44 generates a virtual person on the display page if there is an abnormality in the interaction instruction, and generates first feedback information based on the interaction instruction, and outputs second feedback information through the virtual person if a new instruction is received, wherein the first feedback information is used to indicate that the target user has input the new instruction by voice; and a third generating unit 45 generates third feedback information on the display page based on the interaction instruction if there is no abnormality in the interaction instruction. The present invention solves the problem in the related art that the interface interaction process has obstacles, resulting in low efficiency in handling business through the interactive interface. By identifying user information and device information, the display content and display method in the display page are matched with the user. At the same time, when it is detected that the user is unable to use the display page normally and an abnormal interaction instruction occurs, a virtual person is generated to assist the user in performing the interaction operation, thereby achieving 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 embodiment of the present application, the first generation unit 42 includes: a first determination module, used to determine the page elements displayed in the display page and the preset display mode of the page elements based on user information; a second determination module, used to determine the page size of the display page and the number of page elements in the display page based on device information; and a first generation module, used to generate a display page based on the preset display mode and number of page elements and the page size.

[0102] Optionally, in the page interaction device provided in the embodiment of the present application, the first determination module includes: a first determination sub-module, used to determine the user portrait of the target user based on the user information, and obtain the historical browsing information of the target user; a first selection sub-module, used to select candidate recommendation information from multiple preset recommendation information based on the historical browsing information and the user portrait, and determine the preset page content of the display page indicated by the page access request; a second determination sub-module, used to determine the filling position of the promotional information in the display page based on the initial element carried in the preset page content; the second selection sub-module, used to select target recommendation information from the 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 the embodiment of the present application, when the interaction instruction is a click instruction, the second receiving unit 43 includes: a first judgment module, used to determine the click position of the click instruction, and to determine whether there is a page element in the preset area where the click position is located; a second judgment 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 determination module, used to determine that there is no abnormality in the interaction instruction when the target number is less than the number threshold; and a fourth determination module, used to determine that there is an abnormality in the interaction instruction when the target number is greater than or equal to the number threshold.

[0104] Optionally, in the page interaction device provided in the embodiment of the present 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 the large language model to obtain the recognition result of the large language model; a fifth determination module, used to determine that there is an abnormality in the interaction instruction when the recognition result represents that the content of the text instruction is question information; and a sixth determination module, used to determine that there is no abnormality in the interaction instruction when the recognition result represents that the content of the text instruction is operation information.

[0105] Optionally, in the page interaction device provided in the embodiment of the present application, the second generation unit 44 includes: an extraction module, used to extract keywords in the newly added instructions, and determine the operation content indicated by the newly added instructions 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; a second generation module, used to generate operation steps corresponding to the operation name when the operation content is an operation name, and generate a virtual person's guidance action based on the operation steps, and determine the virtual person's guidance action as the second feedback information.

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

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

[0108] The processor includes a core, which retrieves the corresponding program unit from memory. One or more cores can be configured, and adjusting the core parameters solves the problem of interface interaction barriers in related technologies, resulting in low efficiency in handling business through the interactive interface.

[0109] The memory may include non-permanent memory in a computer-readable medium, 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] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the page interaction method is implemented.

[0111] An embodiment of the present invention provides a processor, which is used to run a program, wherein the page interaction method is executed when the program is running.

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

[0113] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the steps of the above-mentioned page interaction method.

[0114] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

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

[0119] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0120] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0122] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A page interaction method, characterized in that: include: 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 according to the page access request, wherein the page access request is sent by the target user through a user terminal device; Generate a display page according to the device information and the user information, wherein the display page displays page content in a preset display mode; 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 an abnormality occurs in the interaction instruction, a virtual person is generated in the display page, and first feedback information is generated according to the interaction instruction. If a new instruction is received, second feedback information is output through the virtual person, wherein the first feedback information is used to instruct the target user to input the new instruction by voice; When there is no abnormality in the interaction instruction, third feedback information is generated on the display page according to the interaction instruction.

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

3. The method according to claim 2, characterized in that Determining the page elements displayed on the display page according to the user information includes: Determine a user profile of the target user based on the user information, and obtain historical browsing information of the target user; Selecting candidate recommendation information from a plurality of preset recommendation information according to the historical browsing information and the user portrait, and determining the preset page content of the display page indicated by the page access request; Determining a filling position of the promotion information in the displayed page according to the initial element carried in the preset page content; Target recommendation information is selected from the candidate recommendation information according to the number of the filling positions, and the target recommendation information and the initial element are determined as page elements displayed in the display page.

4. The method according to claim 1, wherein When the interaction instruction is a click instruction, determining whether the interaction instruction is abnormal includes: Determining a click position of the click instruction, and judging whether there is a page element in a preset area where the click position is located; In the absence of the page element, obtaining the number of times the target user repeatedly executes the interaction instruction within a preset time period to obtain a target number of times; When the target number of times is less than the number threshold, determining that the interaction instruction is normal; When the target number of times is greater than or equal to the number threshold, it is determined that an abnormality exists in the interaction instruction.

5. The method according to claim 1, wherein 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 a recognition result of the large language model; If the recognition result indicates that the content of the text instruction is question information, determining that there is an abnormality in the interactive instruction; When the recognition result indicates that the content of the text instruction is operation information, it is determined that there is no abnormality in the interaction instruction.

6. The method according to claim 1, characterized in that When the new instruction is received, the second feedback information outputted by the virtual person includes: Extracting keywords from the newly added instruction, and determining the operation content indicated by the newly added instruction based on the keywords; In a case where 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; In the case where the operation content is an operation name, operation steps corresponding to the operation name are generated, and guiding actions of the virtual person are generated according to the operation steps, and the guiding actions of the virtual person are determined as the second feedback information.

7. The method according to claim 1, characterized in that The method further comprises: Determine whether the target user has a voice interaction requirement; 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 speech text output to the target user is converted through the speech conversion model to obtain a target output speech, and the target output speech is output through the virtual person.

8. A page interaction device, characterized in that: include: 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 according to the page access request, wherein the page access request is sent by the target user through a user terminal device; A first generating unit is configured to generate a display page according to the device information and the user information, wherein the display page displays page content in a preset display mode; 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 person on the display page if an abnormality exists in the interaction instruction, generate first feedback information according to the interaction instruction, and output second feedback information through the virtual person if a new instruction is received, wherein the first feedback information is used to instruct the target user to input the new instruction by voice; The third generating unit is configured to generate third feedback information on the display page according to the interaction instruction when 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 running, the device where the computer-readable storage medium is located is controlled to execute the page interaction method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor is used to run the program, wherein the program executes the page interaction method described in any one of claims 1 to 7 when running.

Images