Hot Search Term Interaction Method and Its Device, Equipment, Medium

Abstract

The present application discloses a method for interacting with hot search terms and its apparatus, device, and medium. The method includes: responding to a face presence event acting on a camera view frame, identifying eye features in the camera view frame, and locating the gaze point where the eye features act on a current graphical user interface; responding to a gaze event where the gaze point acts on a hot search term control in a hot search ranking window, displaying the term-specific animation effects corresponding to the hot search term control in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface; responding to a sustained gaze event where the gaze point acts on the hot search term control, displaying the term interaction window corresponding to the hot search term control in the current graphical user interface. The present application tracks the gaze point of a user when browsing a hot search page to interact with controls, so as to display relevant content of the hot search, enhance the interactivity of the hot search page, and improve the effectiveness of user browsing and reading information.

Description

Technical Field

[0001] The present application relates to the field of web pages, and in particular to a method for interacting with hot search terms, and also to corresponding devices, equipment and non-volatile storage media for the method. Background Art

[0002] Existing major content service Internet platforms usually provide platform users with hot search ranking online services, so that platform users can browse the current popular content on the platform through the hot search ranking online services. For example, when the platform is a live broadcast platform, platform users can browse the popular anchors and popular live broadcast rooms on the platform through the hot search ranking online services it provides, or query the popular videos on the platform for viewing.

[0003] However, the hot search ranking page corresponding to the hot search ranking online service of the existing platform usually displays the hot search terms in abbreviated text to save display space on the page, and then displays as many hot search terms as possible for users to browse in the limited display space. This requires users to click on the hot search terms to enter the corresponding page before they can browse the related hot search content, and the user's browsing experience on the hot search ranking page is poor.

[0004] In view of the problems existing in the existing hot search ranking online services, the applicant has made corresponding explorations in order to solve the problems. Summary of the Invention

[0005] The purpose of this application is to provide a hot search term interaction method to meet user needs. In addition, it also relates to corresponding devices, equipment, non-volatile storage media and computer program products of this method.

[0006] In order to achieve the purpose of this application, the following technical solutions are adopted:

[0007] A method for interacting with hot search terms proposed for the purpose of this application includes the following steps:

[0008] In response to a face presence event acting on a camera view frame, identifying eye features in the camera view frame to locate a gaze point of the eye features acting on a current graphical user interface;

[0009] In response to a gaze event in which the gaze point acts on a hot search term control in the hot search ranking window, displaying a term-specific animation effect corresponding to the hot search term control in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface;

[0010] In response to a continuous gaze event in which the gaze point acts on the hot search term control, a term interaction window corresponding to the hot search term control is displayed in the current graphical user interface.

[0011] In a further embodiment, responding to a face presence event acting on a camera view frame, identifying eye features in the camera view frame to locate the eye features acting on a representation of a gaze point in a current graphical user interface, comprises the following steps:

[0012] Obtaining a camera view frame captured by a camera, calling a face recognition model trained to convergence, and identifying whether there is a face image in the camera view frame;

[0013] When a face image exists in the camera view frame, calling a human eye recognition model trained to convergence to recognize the human eye features in the face image, wherein the human eye features include the human eye image and human eye position information;

[0014] The gaze point localization model trained to convergence is called to obtain a two-dimensional coordinate position output after fusing the features of the human eye image and the human eye position information, so as to locate the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

[0015] In a further embodiment, the step of responding to a sustained gaze event of the gaze point acting on the hot search term control includes the following steps:

[0016] Monitor the overlapping time between the continuously located gaze point and the hot search term control, determine whether the overlapping time exceeds a preset gaze time, and if so, trigger a sustained gaze event in response to the current gaze point acting on the hot search term control;

[0017] Monitor the display duration of the currently displayed entry's concrete animation effect, and determine whether the display duration exceeds the preset continuous display duration. If so, trigger a continuous gaze event in response to the currently positioned gaze point acting on the hot search entry control.

[0018] In a further embodiment, in response to the sustained gaze event of the gaze point acting on the hot search term control, the step of displaying a term interaction window corresponding to the hot search term control in the current graphical user interface includes the following steps:

[0019] In response to a continuous gaze event of a hot search term control associated with a host object, monitoring the live broadcast status of a live broadcast room associated with the host object;

[0020] When it is detected that the live broadcast status of the live broadcast room is not currently live broadcasting, the anchor feature information of the anchor object is obtained, and the entry interaction window is displayed in the current graphical user interface to output the anchor feature information to the entry interaction window for display;

[0021] When it is monitored that the live broadcast status of the live broadcast room is live broadcasting, the live broadcast stream and live broadcast room feature information of the live broadcast room are obtained, and the entry interaction window is displayed in the current graphical user interface to output the live broadcast stream and live broadcast room feature information to the entry interaction window for display.

[0022] In a preferred embodiment, after the step of outputting the live stream and live room feature information to the entry interaction window for display, the following steps are included:

[0023] Monitor the display duration of the entry interaction window that is playing the live stream, and when the display duration exceeds a preset duration, display a countdown window on the current graphical user interface, wherein the countdown window displays a countdown to enter the live broadcast room;

[0024] Obtaining a video stream captured by a camera, calling a head posture recognition model trained to convergence, and identifying current head posture features in the video stream;

[0025] When the head posture feature is characterized as a nodding posture and the countdown has not yet been reached, a live broadcast room page associated with the live stream played in the entry interaction window will be displayed in the current graphical user interface;

[0026] When the head posture characteristic is a head shaking posture and the countdown has not been reached, the countdown window will be canceled from being displayed in the current graphical user interface;

[0027] When the countdown is reached, the live broadcast room page associated with the live broadcast stream played in the entry interaction window will be displayed in the current graphical user interface.

[0028] In a further embodiment, in response to the sustained gaze event of the gaze point acting on the hot search term control, the step of displaying a term interaction window corresponding to the hot search term control in the current graphical user interface includes the following steps:

[0029] In response to a continuous gaze event acting on the hot search term control, obtaining a target hot search term contained in the hot search term control, and obtaining a video stream acquisition address of a popular video associated with the target hot search term from a server;

[0030] Displaying the entry interaction window in the current graphical user interface, and outputting the video stream obtained from the video stream acquisition address to the entry interaction window for display;

[0031] In response to a window interaction event acting on the entry interaction window, an interaction result of the window interaction event is obtained and pushed to a server, so that the server updates the conversion rate information of the popular video according to the interaction result.

[0032] In a preferred embodiment, the step of displaying the entry interactive window in the current graphical user interface and outputting the video file obtained from the video acquisition connection address to the entry interactive window for display includes the following steps:

[0033] Obtaining a current video frame of the video stream played in the entry interaction window to call a person recognition model trained to convergence and identify a person object in the video frame;

[0034] Determine whether the target hot search term contains the name text of the person object, and if so, obtain the person introduction information corresponding to the name text;

[0035] A character introduction window is displayed in the current graphical user interface, and the name text and character introduction information are output to the character introduction window for display.

[0036] A hot search term interaction device proposed for the purpose of this application includes:

[0037] a gaze point positioning module, configured to respond to a face presence event acting on a camera view frame, identify eye features in the camera view frame, and locate a gaze point where the eye features act on a current graphical user interface;

[0038] a term gaze response module, configured to respond to a gaze event in which the gaze point acts on a hot search term control in the hot search ranking window, and display a term-specific animation effect corresponding to the hot search term control in the current graphical user interface, wherein the hot search ranking window is displayed in the current graphical user interface;

[0039] The continuous gaze response module is used to respond to the continuous gaze event of the gaze point acting on the hot search term control, and display the term interaction window corresponding to the hot search term control in the current graphical user interface.

[0040] In a further embodiment, the gaze point localization module includes:

[0041] A face recognition submodule is used to obtain a camera view frame captured by a camera, call a face recognition model trained to convergence, and identify whether there is a face image in the camera view frame;

[0042] A human eye feature recognition submodule is used to call a human eye recognition model trained to convergence when a human face image exists in the camera view frame, and recognize the human eye features in the human face image, wherein the human eye features include human eye image and human eye position information;

[0043] The gaze point positioning submodule is used to call the gaze point positioning model trained to convergence, obtain the two-dimensional coordinate position output after fusing the respective features of the human eye image and the human eye position information, and locate the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

[0044] In a further embodiment, the term gaze response module includes:

[0045] Monitor the overlapping time between the continuously located gaze point and the hot search term control, determine whether the overlapping time exceeds a preset gaze time, and if so, trigger a sustained gaze event in response to the current gaze point acting on the hot search term control;

[0046] Monitor the display duration of the currently displayed entry's concrete animation effect, and determine whether the display duration exceeds the preset continuous display duration. If so, trigger a continuous gaze event in response to the currently positioned gaze point acting on the hot search entry control.

[0047] In a preferred embodiment, the entry gaze response module further includes:

[0048] A live broadcast status monitoring submodule, configured to respond to a continuous gaze event of a hot search term control acting on an associated anchor object and monitor the live broadcast status of the live broadcast room associated with the anchor object;

[0049] An anchor feature display module is used to obtain anchor feature information of the anchor object when monitoring that the live broadcast status of the live broadcast room is not currently live broadcasting, and display the entry interaction window in the current graphical user interface to output the anchor feature information to the entry interaction window for display;

[0050] The live stream output submodule is used to obtain the live stream and live room feature information of the live room when it monitors that the live broadcast status of the live broadcast room is live broadcast, and display the entry interaction window in the current graphical user interface to output the live stream and live room feature information to the entry interaction window for display.

[0051] In a preferred embodiment, the entry gaze response module further includes:

[0052] A video stream address acquisition submodule is configured to respond to a continuous gaze event on the hot search term control, acquire a target hot search term contained in the hot search term control, and obtain a video stream acquisition address of a popular video associated with the target hot search term from a server;

[0053] A video stream output submodule, configured to display the entry interaction window in the current graphical user interface, and output the video stream obtained from the video stream acquisition address to the entry interaction window for display;

[0054] The interaction result recording submodule is used to respond to the window interaction event acting on the entry interaction window, obtain the interaction result of the window interaction event and push it to the server, so that the server can update the conversion rate information of the popular video according to the interaction result.

[0055] In order to solve the above technical problems, an embodiment of the present application also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned hot search term interaction method.

[0056] In order to solve the above technical problems, an embodiment of the present application further provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the above-mentioned hot search term interaction method.

[0057] In order to solve the above technical problems, an embodiment of the present application also provides a computer program product, including a computer program and computer instructions. When the computer program and computer instructions are executed by a processor, the processor executes the steps of the above-mentioned hot search term interaction method.

[0058] Compared with the prior art, the advantages of this application are as follows:

[0059] This application provides a browsing gaze simulation service for the platform so that platform users can improve their browsing experience in the hot search ranking page through the browsing gaze simulation service when browsing the hot search ranking page. When the user uses the browsing gaze simulation service, the terminal will obtain the view frame captured by the camera, first detect whether there is a face in the view by identifying the presence of a human face, to determine whether the user is currently browsing the hot search ranking page, and then identify the human eye features of the user who is browsing the page in the view frame to locate the position of the gaze point in the page, and then simulate the gaze position of the user currently browsing the hot search ranking page, and monitor the hot search term control in the page at the same position as the gaze point to determine the hot search term control that the user is currently gazing at, and then through the concretization of animation effects, the text that is omitted from the display of the hot search term control can be fully displayed on the page, so that the user can understand the full text of the hot search term he is currently gazing at, thereby improving the user experience and monitoring the gaze point. If a hot search term control is kept for a long time, it means that the user has been staring at the hot search term control for a long time. At this time, the hot search content related to the hot search term will be displayed in the form of a small window on the page, so that the user can browse the hot search content in the current page without the need for the user to search by himself, thereby improving the readability of the hot search in the hot search ranking page. For example, when the hot search content related to the hot search term control is a popular live broadcast room, the live stream and live broadcast room information of the popular live broadcast room will be displayed in the form of a small window on the hot search ranking page for the user to browse, thereby increasing the number of views of the live broadcast room; therefore, the present application simulates the hot search term that the user is staring at when browsing the hot search ranking page, so as to display the specific text and hot search content of the hot search term being stared at on the hot search ranking page for the user to browse, thereby enhancing the readability of the hot search ranking page, and providing an interesting interactive way for users to browse the hot search ranking page, thereby improving the user's page browsing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0061] Figure 1 A schematic diagram of a typical network deployment architecture for implementing the technical solution of this application;

[0062] Figure 2 A flowchart of a typical embodiment of the hot search term interaction method of the present application is shown;

[0063] Figure 3 This is a schematic diagram of the interface for locating the display position of the gaze point in the hot search ranking page in this application;

[0064] Figure 4 This is a diagram of the interface for triggering a gaze event between a gaze point and a hot search term control in this application;

[0065] Figure 5 For this application Figure 4 A schematic diagram of an entry-specific animation effect of the hot search entry control 403 in FIG. 4 , wherein the entry-specific animation effect is a display effect of text scrolling;

[0066] Figure 6 For this application Figure 4 A schematic diagram of the term-specific animation effect of the hot search term control 403 in FIG. 4 , wherein the term-specific animation effect is a display effect of a text bubble box;

[0067] Figure 7 This is a schematic diagram of the interface where the interactive window for playing video streams in this application is displayed on the hot search ranking page;

[0068] Figure 8 This is a schematic diagram of the interface where the interactive window for the entry playing the live stream in this application is displayed on the hot search ranking page;

[0069] Figure 9 This is a schematic diagram of the interface showing the display position of the entry interactive window displaying the anchor's characteristic information on the hot search ranking page in this application;

[0070] Figure 10 A schematic diagram of a flow chart for a specific implementation method of locating a gaze point in this application;

[0071] Figure 11 This is a flowchart of a specific implementation method for triggering a sustained gaze event in this application;

[0072] Figure 12 This is a flowchart of a specific implementation method of responding to a live broadcast type continuous gaze event of a hot search term control in this application;

[0073] Figure 13 This is a schematic diagram of the interface showing the display position of the countdown window in the hot search ranking page in this application;

[0074] Figure 14 This is a schematic diagram of the live broadcast room page in this application;

[0075] Figure 15 This is a flowchart of the specific implementation of the countdown window and head posture recognition in this application;

[0076] Figure 16 A flowchart of a specific implementation method of responding to a continuous gaze event of a video type in a hot search term control in this application;

[0077] Figure 17This is a schematic diagram of the interface where the interactive window for playing video streams in this application is displayed on the hot search ranking page;

[0078] Figure 18 This is a diagram of the interface showing the display location of the character introduction window in the hot search ranking page in this application;

[0079] Figure 19 This is a flowchart of a specific implementation of the character introduction window in this application;

[0080] Figure 20 This is a principle block diagram of a typical embodiment of the hot search term interaction device of the present application;

[0081] Figure 21 This is a basic structural block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0082] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limiting the present application.

[0083] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0084] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0085] It will be understood by those skilled in the art that the terms "client," "terminal," and "terminal device" as used herein include both devices that are wireless signal receivers, i.e., devices that only have wireless signal receivers without transmission capabilities, and devices that have receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers and tablet computers, which have single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service), which may combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which may include a radio frequency receiver, a pager, Internet / Intranet access, a web browser, a notepad, a calendar, and / or a GPS (Global Positioning System) receiver; and conventional laptop and / or palmtop computers or other devices, which have and / or include a radio frequency receiver. As used herein, the terms "client," "terminal," or "terminal device" may be portable, transportable, or installed in a vehicle (air, sea, and / or land), or may be adapted and / or configured to operate locally and / or in a distributed manner at any other location on Earth and / or in space. As used herein, the terms "client," "terminal," or "terminal device" may also refer to a communication terminal, an Internet terminal, or a music / video playback terminal, such as a PDA, an MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or may include a smart TV, a set-top box, or other device.

[0086] The hardware referred to by names such as "server", "client", and "work node" in this application is essentially an electronic device with capabilities equivalent to those of a personal computer. It is a hardware device that has the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. Computer programs are stored in its memory, and the central processing unit calls the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0087] It should be noted that the concept of "server" referred to in this application can also be extended to server clusters. Based on the network deployment principles understood by those skilled in the art, the servers described should be logically divided. In physical space, these servers can be independent of each other but callable through interfaces, or integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method of this application.

[0088] See also Figure 1 , the hardware foundation required for the implementation of the relevant technical solutions of this application can be deployed according to the architecture shown in the figure. The server 80 referred to in this application is deployed in the cloud. As an online server, it can be responsible for further connecting relevant data servers and other servers that provide relevant support, etc., to form a logically related service cluster to provide services for relevant terminal devices such as the smartphone 81 and personal computer 82 shown in the figure or a third-party server (not shown). The smartphone and personal computer can both access the Internet through a well-known network access method and establish a data communication link with the server 80 in the cloud to run terminal applications related to the services provided by the server.

[0089] For the server, the application is usually constructed as a service process, opening the corresponding program interface for remote calls by applications running on various terminal devices. The relevant technical solutions in this application that are suitable for running on the server can be implemented in the server in this way.

[0090] The application mentioned above refers to an application running on a server or terminal device. This application implements the relevant technical solutions of the present application in a programming manner. Its program code can be stored in a non-volatile storage medium that can be recognized by the computer in the form of computer-executable instructions, and can be loaded into the memory by the central processing unit for execution. The relevant device of the present application is constructed by the operation of this application on the computer.

[0091] For the server, the application is usually constructed as a service process, opening the corresponding program interface for remote calls by applications running on various terminal devices. The relevant technical solutions in this application that are suitable for running on the server can be implemented in the server in this way.

[0092] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus exhibit commonality, unless otherwise specified, these methods can be independently executed. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept. Therefore, concepts with the same expression, as well as concepts that are appropriately transformed for convenience despite different expression, should be understood as equivalent.

[0093] See also Figure 2 In a typical embodiment of the present application, a method for interacting with hot search terms includes the following steps:

[0094] Step S11: In response to a face presence event acting on a camera view frame, identifying eye features in the camera view frame to locate a gaze point where the eye features act on a current graphical user interface.

[0095] The camera view frame is generally collected by a camera or other camera device. For example, when the current terminal is a mobile phone device, the camera video frame is generally collected by the front camera of the mobile phone device. When the current terminal is a computer device, the camera video frame is generally collected by the external camera of the computer device.

[0096] The camera video frame refers to a current frame of video or camera photo in a video image captured by a camera or other camera equipment.

[0097] After the current terminal obtains the camera video frame, it will perform face recognition on the camera video frame to identify whether there is a face in the camera video frame. Specifically, after the current terminal obtains the camera video frame, it will call the face recognition model trained to gift giving to perform feature extraction on the camera video frame, obtain the image feature vector of the camera video frame, and then judge whether there is a face image in the camera video frame based on the image feature vector. If so, the face existence event is triggered; the face recognition model is generally constructed based on a convolutional neural network. Of course, those skilled in the art can also use other neural network ideas to construct it, and this step will not be repeated.

[0098] Of course, the party responsible for performing face recognition on the camera video frame can also be the corresponding business server. After the current terminal obtains the camera video frame, the camera video frame is pushed to the business server to drive the business server to call the face recognition model to perform face recognition on the camera video frame, and then feed back the recognition result to the current terminal.

[0099] When the current terminal determines that there is a face image in the camera video frame, that is, in response to the face existence event acting on the camera video frame, the current terminal will identify the human eye features in the camera view frame. Specifically, the current terminal first calls the human eye recognition model trained to convergence to identify the human eye features in the face image existing in the first video frame. The human eye features only include the human eye image and human eye position information, wherein the human eye image generally includes a left eye image and a right eye image; after obtaining the human eye features, the current terminal will call the gaze point positioning model trained to convergence to drive the gaze point positioning model to extract the respective image feature vectors of the left eye image and the right eye image contained in the human eye image, and extract the position feature vector of the human eye position, and then locate the left eye The respective image feature vectors of the image and the right eye image and the position feature vector are feature fused through a fully connected layer, and the corresponding two-dimensional coordinate position is output, so that the current terminal uses the two-dimensional coordinate position as the position of the gaze point in the current graphical user interface, that is, locates the position of the gaze point in the current graphical user interface; accordingly, the gaze point positioning model also extracts and fuses features by extracting other data other than the human eye features. For example, the left eye image, right eye image, face image and face position are input into the gaze point positioning model to extract the feature vectors of the left eye image, right eye image, face image and face position respectively, and then perform feature fusion, and then output the corresponding two-dimensional coordinate position to determine the position of the gaze point in the current graphical user interface.

[0100] It can be understood that the implementation method of the human eye recognition and gaze point positioning can be performed by the corresponding server. The business server calls the human eye recognition model and the gaze point positioning model to obtain the two-dimensional coordinate position corresponding to the photographic video frame containing the face image and pushes it to the current terminal, so that the current terminal constructs the two-dimensional coordinate position to determine the position of the gaze point in the current graphical user interface.

[0101] Please refer to Figure 3 The gaze point refers to the position where the eyes of the user using the current terminal are gazing at the current graphical user interface, such as Figure 3 As shown in the gaze point 301 in FIG. Figure 3 The display position of the hot search ranking page shown in the figure is to simulate and indicate the position where the user's eyes are looking when browsing the hot search page. For example, when the user is browsing Figure 3 When the gaze position is at position 302 on the hot search ranking page shown, the current terminal will move the gaze point 301 shown to position 302 by performing gaze point positioning on the video frame currently captured by the camera.

[0102] In addition, the display style of the gaze point in the current graphical user interface is generally a semi-transparent display style, or is displayed in a special display style such as a transparent bubble to play an auxiliary role. Of course, the gaze point can also be displayed in a fully transparent display style to prevent the gaze point from blocking the hot search term control and affecting the user's browsing experience. Those skilled in the art can flexibly design the display style of the gaze point, and this step will not be repeated.

[0103] In order to associate with the hot search rankings online service provided by the platform and save the computing resources of the current terminal, the current terminal displays Figure 3 After the hot search ranking page is viewed, the camera video frame is obtained to implement the positioning of the gaze point, that is, the embodiment of this step is generally only performed in the hot search ranking page.

[0104] Step S12: In response to a gaze event in which the gaze point acts on a hot search term control in the hot search ranking window, a term-specific animation effect corresponding to the hot search term control is displayed in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface:

[0105] The current terminal tracks the gaze point in the current graphical user interface in real time. When the gaze point is located at a hot search term control in the hot search ranking window displayed in the current graphical user interface, the gaze event acting on the hot search term control will be triggered.

[0106] Please refer to Figure 3 The hot search ranking window contains multiple hot search term controls associated with its hot search type, and the hot search ranking window is generally displayed as follows: Figure 3 In the hot search ranking page shown, Figure 3 The hot search ranking window 303 includes two of the hot search ranking windows, wherein the hot search type of the hot search ranking window 303 is the hot search video type, and the types of the hot search term controls contained therein are also the hot search video type; the hot search type of the hot search ranking window 304 is the hot search live broadcast type, and the types of the hot search term controls contained therein are also the hot search live broadcast type; of course, those skilled in the art can design the type of the hot search ranking window according to the online services provided by the platform, and this step will not be repeated here.

[0107] The hot search term control refers to a control that can trigger an event corresponding to the gaze point, and the hot search term control displays the corresponding hot search term, such as Figure 4 As shown, Figure 4The hot search terms included in the hot search term control 403 shown in the figure are Guangzhou food recommendation videos, but considering the need to display as many hot search term controls as possible in the hot search ranking window 402, the hot search terms displayed in the hot search term control 403 and other hot search term controls shown will be omitted after exceeding the preset word limit. For example, the hot search term "Guangzhou food recommendation video" is omitted and displayed as "Guangzhou food..." in the hot search term control 403 shown. Of course, considering the user's browsing experience, this method will respond to the gaze event acting on the hot search term control to fully display the corresponding hot search term by displaying the term-specific animation effects associated with the hot search term control.

[0108] Please refer to Figure 4 The gaze event acting on the hot search term control means that when the display position of the gaze point in the current graphical user interface is located at the hot search term control, the gaze event acting on the hot search term control will be triggered. Specifically, Figure 4 As shown, when the display position of the gaze point 401 in the hot search ranking page is located at the hot search term control 403 in the hot search ranking window 402, that is, the gaze point 401 overlaps with the hot search term control 403, then the gaze event acting on the hot search term control 403 will be triggered, and the term-specific animation effect associated with the hot search term control 403 will be displayed in the current graphical user interface.

[0109] Also, please refer to Figure 4 In addition to triggering the gaze event, the hot search term control can also trigger a corresponding touch event. For example, when Figure 4 When the hot search term control 403 shown is touched and the touch event is triggered, the current terminal will respond to the trigger event to input the hot search term "Guangzhou Food Recommendation Video" in the hot search term control 403 shown into the hot search control 404, or display the related hot search page after searching for the hot search term "Guangzhou Food Recommendation Video" in the current graphical user interface.

[0110] Please refer to Figure 4 and Figure 5 The term specific animation effect is used to specifically display the hot search terms of the hot search term control associated with it. The term specific animation effect displays the hot search terms. Generally, the display effect of the hot search terms is to display the full text of the hot search terms with a text scrolling display effect. For details, please refer to Figure 5 , Figure 5 The entry specific animation effect 501 shown in the figure is displayed with the text scrolling display effect Figure 4 The hot search terms in the hot search terms control 403, and the term specific animation effects 501 shown will be Figure 4The hot search term control 403 is displayed in the display position shown in .

[0111] In one embodiment, please refer to Figure 6 The entry specific animation effect can also be a display effect of a text bubble box. Figure 6 As shown, Figure 6 The term specific animation effect 601 displayed in the hot search term control 602 uses the display effect of a text bubble box to display the hot search terms. Of course, those skilled in the art can flexibly design the display effect of the term specific animation effect to specifically display the hot search terms that are omitted from the hot search term control. This step will not be repeated here.

[0112] Step S13: In response to a continuous gaze event in which the gaze point acts on the hot search term control, a term interaction window corresponding to the hot search term control is displayed in the current graphical user interface:

[0113] When the current terminal responds to the gaze event of the target hot search term control, it will monitor the overlapping duration of the display position of the gaze point in the current graphical user interface and the display position of the target hot search term control. When the overlapping duration exceeds the preset gaze duration, it will trigger the continuous gaze event of the gaze point acting on the target hot search term control; the gaze duration is generally set within the range of 3-4 seconds. Of course, those skilled in the art can flexibly design the gaze duration.

[0114] In one embodiment, the current terminal can also monitor the display duration of the entry-specific animation effect of the target hot search entry control, and then trigger the continuous gaze event of the gaze point acting on the target hot search entry control when the display duration exceeds the preset continuous display duration; the continuous display duration is generally set within the time range of 3-4 seconds. Of course, those skilled in the art can flexibly design the continuous display duration.

[0115] When the current terminal responds to the sustained gaze event acting on the target hot search term control, the term interaction window corresponding to the target hot search term control will be displayed in the current graphical user interface. The term interaction window is used to display specific data information associated with the target hot search term control. For example, when the hot search term of the target hot search term control is "Guangzhou Food Recommendation Video", the video stream of the type "Guangzhou Food Recommendation Video" will be played in the term interaction window. For details, please refer to Figure 7 , Figure 7 The interactive window 703 for playing video stream is shown in FIG. Figure 7 As shown, Figure 7The current terminal responds to the continuous gaze event of the hot search term control 702, and the current terminal obtains the video stream acquisition address associated with the hot search term displayed in the hot search term control 702, which is "Guangzhou Food Recommendation Video", from the business server, so that the current terminal obtains the corresponding video stream through the video stream acquisition address and outputs it to the term interaction window 703 shown for playback, such as the video stream of "YY Bear Eats All Over Guangzhou" played in the term interaction window 703 shown. Furthermore, the video stream corresponding to the video stream acquisition address generally pushed to the current terminal by the business server is the video stream with the highest playback volume or the highest conversion rate among the video streams associated with the hot search term. Of course, those skilled in the art can flexibly design the relevant parameters for reference by the business server to select the video stream acquisition address, and this step will not be repeated here.

[0116] In one embodiment, please refer to Figure 8 and Figure 9 When the hot search type of the target hot search item control pointed to by the sustained gaze event responded by the current terminal is a live hot search type, the live stream or anchor feature information associated with the target hot search item control will be displayed in the item interaction window displayed in the current graphical user interface. For details, please refer to Figure 8 , the target hot search term control corresponding to the continuous gaze event responded by the current terminal is Figure 8 The hot search term control 802 shown in the figure has a hot search type of live broadcast hot search type, and the hot search term contained in the hot search term control is "YY Music Bear Singing Live Broadcast Room". At this time, the current terminal will obtain the live broadcast status of the live broadcast room pointed to by the hot search term control 802. When the live broadcast status of the live broadcast room is live broadcasting, the term interaction window displayed in the current graphical user interface is as follows: Figure 8 The entry interaction window 803 shown in the figure will play the live stream of the live broadcast room corresponding to the hot search entry control 802; when the live broadcast status of the live broadcast room is not currently live, the entry interaction window displayed in the current graphical user interface is as follows: Figure 9 The entry interaction window 903 shown in FIG. 9 shows Figure 9 The anchor special effect information of the anchor user corresponding to the hot search term control 902 shown.

[0117] In one embodiment, please refer to Figure 7 ,when Figure 7When the video stream is played in the entry interaction window 703 shown, the character displayed in the video stream can be identified by calling the character recognition model that has been trained to convergence, so that the character feature information of the character can be output to the current graphical user interface in the form of a window. For example, if the character "YY Bear" in the entry interaction window 703 shown in the identification is identified, the character feature information of "YY Bear" will be output to the current graphical user interface for display.

[0118] In another embodiment, the current terminal responds to the open video instruction acting on the entry interaction window of the video stream being played, and after displaying the video page playing the video stream in the current graphical user interface, it can also identify the character feature information of the characters in the video stream through the character recognition model, and output the character feature information in the form of a window to the video page for display for the user to browse.

[0119] In one embodiment, please refer to Figure 8 , the current terminal monitors Figure 8 The display duration of the entry interaction window 803 shown, when the display duration exceeds the preset duration, the current terminal displays a countdown to automatically enter the live broadcast room in the current graphical user interface, so as to display the live broadcast room page of the live broadcast room in the current graphical user interface after the countdown ends; and during the countdown process, the current terminal collects the camera video stream with the face of the user operating the current terminal through the camera, so as to identify the current head posture feature in the camera video stream through the head posture recognition model trained to convergence, when the head posture feature is characterized by a nodding gesture and the countdown has not been reached, the live broadcast room page associated with the live stream played in the entry interaction window will be displayed in the current graphical user interface, and when the head posture feature is characterized by a shaking head gesture and the countdown has not been reached, the countdown window will be cancelled from being displayed in the current graphical user interface.

[0120] Through the typical implementation of this method, it can be known that this method provides a browsing gaze simulation service for the platform, so that platform users can improve their browsing experience in the hot search ranking page through the browsing gaze simulation service when browsing the hot search ranking page. When the user uses the browsing gaze simulation service, the terminal will obtain the view frame captured by the camera, first detect whether there is a face by identifying the view to determine whether the user is currently browsing the hot search ranking page, and then identify the human eye features of the user who is browsing the page in the view frame to locate the position of the gaze point in the page, and then simulate the gaze position of the user currently browsing the hot search ranking page, and monitor the hot search term control in the page at the same position as the gaze point to determine the hot search term control that the user is currently gazing at, and then through the concrete animation effects, the text that is omitted from the hot search term control can be fully displayed on the page, so that the user can understand the full text of the hot search term he is currently gazing at, thereby improving the user experience. And if it is detected that the gaze point is on a hot search term control for a long time, it indicates that the user has been gazing at the hot search term control for a long time. At this time, the hot search content related to the hot search term will be displayed in the page in the form of a small window, so that the user can browse the hot search content in the current page without the need for the user to search by himself, thereby improving the readability of the hot search in the hot search ranking page. For example, when the hot search content related to the hot search term control is a popular live broadcast room, the live stream and live broadcast room information of the popular live broadcast room will be displayed in the form of a small window on the hot search ranking page for the user to browse, thereby increasing the number of views of the live broadcast room; therefore, this method simulates the hot search term that the user is gazing at when browsing the hot search ranking page, so as to display the specific text and hot search content of the hot search term being gazed at on the hot search ranking page for the user to browse, thereby enhancing the readability of the hot search ranking page, and providing an interesting interactive way for the user to browse the hot search ranking page, thereby improving the user's page browsing experience.

[0121] The above exemplary embodiments and their variations fully disclose the implementation scheme of the hot search term interaction method of the present application. However, various variations of the method can be derived by changing and expanding some technical means. Other embodiments are briefly described below:

[0122] In one embodiment, please refer to Figure 10 The step of responding to a face presence event acting on a camera view frame and identifying eye features in the camera view frame to locate a representation of a gaze point in a current graphical user interface by the eye features comprises the following steps:

[0123] Step S111: Obtain a camera view frame captured by a camera, call a face recognition model trained to convergence, and identify whether there is a face image in the camera view frame:

[0124] The current terminal obtains the video view frame captured by the camera. The video view frame generally refers to a frame of image in the video stream captured by the camera.

[0125] After the current terminal obtains the camera view frame, it will call the face recognition model that has been trained to convergence to identify whether there is a face image in the camera view frame. The face recognition model is constructed based on the idea of neural network. The face recognition model extracts the image feature vector of the camera view frame and inputs the image feature vector into the fully connected layer to output the corresponding recognition result. When the recognition result indicates that there is a face image in the camera view frame, the current terminal will perform human eye recognition on the camera view frame.

[0126] Step S112: When a face image exists in the camera view frame, the trained eye recognition model is called to identify the eye features in the face image, where the eye features include the eye image and eye position information.

[0127] The human eye recognition model is a neural network model trained to a convergent state. After obtaining the camera view frame, the human eye recognition model extracts the image feature vector of the camera view frame and inputs the image feature vector into the fully connected layer to thereby identify the human eye features in the camera view frame. The human eye features include a human eye image and human eye position information. The human eye image includes a left eye image and a right eye image, and the human eye position information includes the coordinate information of the four corners of the eye in the camera view frame.

[0128] Step S113: Calling the gaze point localization model trained to convergence, obtaining the two-dimensional coordinate position output after fusing the features of the human eye image and the human eye position information, and locating the gaze point in the current graphical user interface according to the two-dimensional coordinate position:

[0129] The gaze point localization model is a neural network model trained to a convergent state. After obtaining the human eye image and human eye position information, the gaze point localization model will respectively extract the image feature vectors of the left eye image and the right eye image contained in the human eye image through a convolutional neural network, and extract the corresponding position feature vector through a landmark algorithm for the human eye. Then, the image feature vector of the left eye image, the image feature vectors of the right eye image, and the position feature vector are fused through a fully connected neural network to output a two-dimensional coordinate position so as to locate the display position of the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

[0130] In this embodiment, a face recognition model is used to identify whether there is a face in the view frame captured by the camera. If there is a face, it indicates that the user of the operating terminal is browsing the hot search ranking page. At this time, the human eye features in the view frame are extracted by the human eye recognition model, and then the gaze point positioning model is called to process the human eye features to locate the display position of the gaze point in the page, so as to simulate the position where the user is gazing when browsing the page.

[0131] In one embodiment, please refer to Figure 6 and Figure 11 The step of responding to the continuous gaze event of the gaze point acting on the hot search term control includes the following steps:

[0132] Step S131: monitor the overlapping time between the continuously located gaze point and the hot search term control, and determine whether the overlapping time exceeds the preset gaze time. If so, trigger a continuous gaze event in response to the current gaze point acting on the hot search term control:

[0133] Please refer to Figure 6 ,like Figure 6 As shown, Figure 6 The hot search term control 602 shown has triggered a gaze event, so that the current terminal responds to the annotation event and displays the term-specific animation effect 601 of the hot search term control 602 shown in the current graphical user interface. At this time, the current terminal will monitor the overlapping duration of the gaze point 603 shown and the hot search term control 602 shown, that is, the overlapping duration of the positions of the gaze point 603 and the hot search term control 602 shown. When the overlapping duration exceeds the preset gaze duration, the continuous gaze event acting on the hot search term control 602 will be triggered.

[0134] Step S132: monitor the display duration of the currently displayed entry specific animation effect, and determine whether the display duration exceeds the preset continuous display duration. If so, trigger a continuous gaze event in response to the currently located gaze point acting on the hot search entry control:

[0135] Please refer to Figure 6 In another triggering action on a hot search term control, such as the sustained gaze event Figure 6 As shown, the current terminal will monitor the display duration of the entry specific animation effect 601. When the display duration exceeds the preset continuous display duration, the continuous gaze event acting on the hot search entry control 602 will be triggered.

[0136] In this embodiment, the current terminal determines the continuous gaze event acting on any hot search term control that has triggered the gaze event in two ways or one of the two ways, and subsequently responds to the event and displays the term interaction window corresponding to the hot search term control in the current graphical user interface.

[0137] In one embodiment, please refer to Figure 8 、 Figure 9 and Figure 12 In the step of responding to the continuous gaze event of the gaze point acting on the hot search term control and displaying the term interaction window corresponding to the hot search term control in the current graphical user interface, the steps include:

[0138] Step S131′: In response to a continuous gaze event of a hot search term control associated with a host object, monitor the live broadcast status of the live broadcast room associated with the host object:

[0139] Please refer to Figure 8 , Figure 8 The hot search term control 802 shown in the figure is a hot search term control associated with the anchor object. When the current terminal responds to the continuous gaze event of the hot search term control 802 shown, it will monitor the live broadcast status of the live broadcast room where the anchor object associated with the hot search term control 802 is located; the anchor object generally refers to the anchor user in the platform, such as the anchor object associated with the hot search term control 802 is "YY Music Bear".

[0140] Step S132': when it is detected that the live broadcast status of the live broadcast room is not currently live broadcasting, the anchor feature information of the anchor object is obtained, and the entry interaction window is displayed in the current graphical user interface to output the anchor feature information to the entry interaction window for display:

[0141] Please refer to Figure 9 When the terminal monitors that the live broadcast status of the live broadcast room of the anchor object "YY Music Bear" associated with the hot search term control 902 is not currently broadcasting, the current terminal will push a request to the business server to obtain the anchor feature information of the anchor object. The anchor feature information includes anchor information such as the anchor name, anchor avatar, and number of anchor fans, so that the current terminal can output the anchor feature information to the term interaction window 903 shown for display.

[0142] Step S133': when it is detected that the live broadcast status of the live broadcast room is live broadcasting, the live broadcast stream and live broadcast room feature information of the live broadcast room are obtained, and the entry interaction window is displayed in the current graphical user interface to output the live broadcast stream and live broadcast room feature information to the entry interaction window for display:

[0143] Please refer to Figure 8When the terminal monitors that the live broadcast status of the live broadcast room of the anchor object "YY Music Bear" associated with the hot search term control 802 is currently broadcasting, the current terminal will push a request to the business server to obtain the live broadcast stream and live broadcast room feature information of the live broadcast room of the anchor object. The live broadcast room feature information includes information such as the number of live broadcast room viewers and the live broadcast room name, so that the current terminal can output the live broadcast stream and live broadcast room feature information to the term interaction window 803 shown for playback and display.

[0144] In this embodiment, when a hot search entry control has an associated anchor or its type is a live broadcast type, the anchor's characteristic information will be output to the entry interaction window for display when the live broadcast is not in progress, and the live broadcast stream and live broadcast room information will be output to the entry interaction window for display when the live broadcast is in progress, so as to provide users with corresponding hot search information for browsing.

[0145] In one embodiment, please refer to Figure 13 、 Figure 14 and Figure 15 After the step of outputting the live stream and live room feature information to the entry interaction window for display, the following steps are included:

[0146] Step S134', monitoring the display duration of the entry interactive window that is playing the live stream, and when the display duration exceeds the preset duration, displaying a countdown window on the current graphical user interface, the countdown window displays the countdown to enter the live broadcast room:

[0147] Please refer to Figure 13 and Figure 14 , the current terminal will monitor Figure 13 The display duration of the interactive window 1301 of the live stream being played is shown. When the display duration exceeds the preset duration, the current terminal will display the following in the current graphical user interface: Figure 13 The countdown window 1302 shown in the countdown window 1302 is displayed. When the countdown displayed in the countdown window 1302 is 0, the live broadcast room page to which the live broadcast stream played in the entry interaction window 1301 belongs will be displayed. The live broadcast room page is as shown in FIG. Figure 14 shown.

[0148] Step S135': obtain the video stream captured by the camera, call the head posture recognition model trained to convergence, and identify the current head posture features in the video stream:

[0149] When the countdown window is displayed in the current graphical user interface, the current terminal will obtain the camera video stream captured by the camera to call the head posture recognition model trained to convergence to identify the head posture features of the user operating the current terminal in the camera video stream.

[0150] After obtaining the photographic video stream, the head posture recognition model will capture the six facial key points of the operating user in the current video frame of the photographic video stream. The six key points correspond to the left corner of the eye, the right corner of the eye, the tip of the nose, the left corner of the mouth, the right corner of the mouth and the chin in the face, and then capture the six facial key points of the next video frame. The head state characteristics of the operating user are identified through the coordinate changes between the six key points of two or more video frames.

[0151] Step S136': when the head posture feature is a nodding gesture and the countdown has not yet arrived, the live broadcast room page associated with the live stream played in the entry interaction window will be displayed in the current graphical user interface:

[0152] Please refer to Figure 13 and Figure 14 , when the countdown in the countdown window is not 0 and the head posture feature identified by the head posture recognition model is a nodding posture, the current terminal will display the following in the current graphical user interface: Figure 14 The live broadcast room page shown is the same as Figure 13 The entry interaction window 1301 shown is associated with the live stream being played.

[0153] Step S137': when the head posture characteristic is a head shaking posture and the countdown has not yet arrived, the countdown window will be canceled from being displayed in the current graphical user interface.

[0154] Please refer to Figure 13 When the countdown in the countdown window is not 0 and the head posture feature identified by the head posture recognition model is a head shaking posture, the current terminal cancels Figure 13 The countdown window 1302 is shown in Figure 13 The display in the graphical user interface is shown.

[0155] Step S138': When the countdown is reached, the live broadcast room page associated with the live stream played in the entry interaction window will be displayed in the current graphical user interface:

[0156] Please refer to Figure 14 When the countdown in the countdown window is 0 and the head posture recognition model does not recognize the head posture feature in the camera video stream or the head posture feature is not a nodding gesture or a shaking gesture, the current terminal will display the following in the current graphical user interface: Figure 14 The live broadcast room page shown.

[0157] In this embodiment, after the interactive window of the entry playing the live stream is displayed for a period of time, the corresponding live broadcast room will be actively displayed to the user after the countdown. During the countdown, the user's head posture will be recognized so that the user can indicate whether he or she wants to enter the live broadcast room by nodding or shaking his or her head, without the need for manual operation by the user, thereby improving the user experience.

[0158] In one embodiment, please refer to Figure 6 、 Figure 7 and Figure 16 In the step of responding to the continuous gaze event of the gaze point acting on the hot search term control and displaying the term interaction window corresponding to the hot search term control in the current graphical user interface, the steps include:

[0159] In step S131, in response to a continuous gaze event on the hot search term control, a target hot search term contained in the hot search term control is obtained, so as to obtain a video stream acquisition address of a popular video associated with the target hot search term from a server:

[0160] Please refer to Figure 6 , the current terminal response acts on Figure 6 The continuous gaze event of the hot search term control 602 shown is used to obtain the target hot search term changed by the hot search term control 602 shown, which is "Guangzhou Food Recommendation Video", to obtain the video stream acquisition address of the popular video associated with the target hot search term from the server.

[0161] After the server obtains the target hot search term, it will query one or more video streams with the target hot search term from the video library, and query the video stream with the highest conversion rate among these video streams. This video stream is the popular video, and the video stream acquisition address of the popular video is pushed to the current terminal, so that the video stream output and played by the current terminal is the most popular video stream on the platform, thereby improving the video viewing experience of the user operating the current terminal.

[0162] In step S132, the entry interaction window is displayed in the current graphical user interface, and the video stream obtained from the video stream acquisition address is output to the entry interaction window for display:

[0163] Please refer to Figure 7 After the current terminal obtains the video stream acquisition address, it will be displayed in the current graphical user interface Figure 7 The entry interactive window 703 shown is output with the video stream named "YY Bear Eats All Over Guangzhou" obtained through the video stream acquisition address and played and displayed in the entry interactive window 703 shown.

[0164] In step S133, in response to the window interaction event acting on the entry interaction window, the interaction result of the window interaction event is obtained and pushed to the server, so that the server updates the conversion rate information of the popular video according to the interaction result:

[0165] Please refer to Figure 7 , the current terminal will respond to the following Figure 7 The window interaction event of the entry interaction window 703 shown, for example, when the operating user touches the close window control 704 in the entry interaction window 703 shown, it will trigger a window interaction event with the interaction result of closing the video, and when touching the enter video page control 705 in the entry interaction window 703 shown, it will trigger a window interaction event with the interaction result of entering the video, and then the current terminal responds to the window interaction event, and promotes the interaction result corresponding to the event to the server, so that the server updates the conversion rate information of the video stream played in the entry interaction window 703 shown according to the interaction result. Generally, when the interaction result is to close the video, the conversion rate in the conversion rate information will be reduced, and when the interaction result is to enter the video, the conversion rate of the conversion rate information will be increased.

[0166] In this embodiment, the popular videos corresponding to the hot search terms are output to the term interaction window for display, so that users can browse the corresponding popular videos without having to search for the corresponding videos themselves, and the interaction results representing whether the user likes the popular videos are collected, thereby updating the conversion rate of the popular videos.

[0167] In one embodiment, please refer to Figures 17 to 19 The step of displaying the entry interactive window in the current graphical user interface and outputting the video file obtained from the video acquisition connection address to the entry interactive window for display includes the following steps:

[0168] Step S1331, obtain the current video frame of the video stream played in the entry interaction window, call the character recognition model trained to convergence, and recognize the character object in the video frame:

[0169] Please refer to Figure 17 , the current terminal is displayed in the current graphical user interface as follows Figure 17 When the entry interaction window 1701 of the video stream is played, the current video frame in the video stream will be intercepted to call the character recognition model shown to identify the character object operated in the video frame; the character recognition model is a neural network model, which extracts the image feature vector of the video frame and identifies the character image in the video frame through the image feature vector, and then identifies the character object of the character displayed in the character image, and the character object contains character text representing the character name.

[0170] Step S1332, determine whether the target hot search term contains the name text of the character object. If so, obtain the character introduction information corresponding to the name text:

[0171] Please refer to Figure 18 After the current terminal obtains the character object, it will determine whether the target hot search term in the hot search term control 1702 contains the name text of the character object. For example, when the name text is "YY Bear", correspondingly, the target hot search term contained in the hot search term control 1702 is "YY Bear Guangzhou VLOG", then the target hot search term exists in the target hot search term. The current terminal obtains the character introduction information from the platform's anchor user library, or obtains the character introduction information from the Internet; the character introduction information includes information such as the character picture, character name and character introduction text.

[0172] In step S1333, a character introduction window is displayed in the current graphical user interface, and the name text and character introduction information are output to the character introduction window for display:

[0173] Please refer to Figure 18 After the current terminal obtains the character introduction information, it will be displayed in the current graphical user interface as follows Figure 18 The character introduction window 1801 is shown, so that the character introduction information is output to the character introduction window 1801 for display.

[0174] In this embodiment, by identifying the character in the video stream played in the entry interaction window and determining that the character's name is the hot search character of the hot search entry corresponding to the video stream, the character introduction information of the hot search character is output in the current graphical user interface, making it easier for users to understand the hot search character.

[0175] Furthermore, by functionalizing each step in the method disclosed in the above embodiments, a hot search term interaction device of the present application can be constructed. According to this idea, please refer to Figure 20In a typical embodiment, the device includes: a gaze point positioning module 11, which is used to respond to a face presence event acting on a camera view frame, identify human eye features in the camera view frame, and locate the gaze point where the human eye features act on the current graphical user interface; a term gaze response module 12, which is used to respond to a gaze event in which the gaze point acts on a hot search term control in a hot search ranking window, and display the term-specific animation effects corresponding to the hot search term control in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface; a continuous gaze response module 13, which is used to respond to a continuous gaze event in which the gaze point acts on the hot search term control, and display the term interaction window corresponding to the hot search term control in the current graphical user interface.

[0176] In one embodiment, the gaze point positioning module 11 includes: a face recognition submodule, which is used to obtain a camera view frame captured by a camera, call a face recognition model trained to convergence, and identify whether there is a face image in the camera view frame; a human eye feature recognition submodule, which is used to call a human eye recognition model trained to convergence when there is a face image in the camera view frame, and identify the human eye features in the face image, wherein the human eye features include the human eye image and the human eye position information; a gaze point positioning submodule, which is used to call the gaze point positioning model trained to convergence, and obtain the two-dimensional coordinate position output after fusing the respective features of the human eye image and the human eye position information, so as to locate the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

[0177] In one embodiment, the entry gaze response module 13 includes: monitoring the overlapping time of the continuously positioned gaze point and the hot search entry control, judging whether the overlapping time exceeds the preset gaze time, and if so, triggering a response to the continuous gaze event of the current gaze point acting on the hot search entry control; monitoring the display time of the currently displayed entry concrete animation effect, judging whether the display time exceeds the preset continuous display time, and if so, triggering a response to the continuous gaze event of the currently positioned gaze point acting on the hot search entry control.

[0178] In another embodiment, the entry gaze response module 13 also includes: a live broadcast status monitoring submodule, which is used to respond to the continuous gaze event of the hot search entry control acting on the associated anchor object, and monitor the live broadcast status of the live broadcast room associated with the anchor object; an anchor feature display module, which is used to obtain the anchor feature information of the anchor object when it monitors that the live broadcast status of the live broadcast room is not currently broadcasting, and display the entry interaction window in the current graphical user interface to output the anchor feature information to the entry interaction window for display; a live broadcast stream output submodule, which is used to obtain the live broadcast stream and live broadcast room feature information of the live broadcast room when it monitors that the live broadcast status of the live broadcast room is being broadcasting, and display the entry interaction window in the current graphical user interface to output the live broadcast stream and live broadcast room feature information to the entry interaction window for display.

[0179] In another embodiment, the term gaze response module 13 also includes: a video stream address acquisition submodule, which is used to respond to a continuous gaze event acting on the hot search term control, obtain the target hot search term contained in the hot search term control, and obtain the video stream acquisition address of the popular video associated with the target hot search term from the server; a video stream output submodule, which is used to display the term interaction window in the current graphical user interface, and output the video stream obtained from the video stream acquisition address to the term interaction window for display; an interaction result recording submodule, which is used to respond to a window interaction event acting on the term interaction window, obtain the interaction result of the window interaction event and push it to the server, so that the server can update the conversion rate information of the popular video according to the interaction result.

[0180] To solve the above technical problems, the present application also provides a computer device for running a computer program implemented according to the hot search term interaction method. Figure 21 , Figure 21 This is a basic structural block diagram of the computer device in this embodiment.

[0181] like Figure 21As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory and a network interface connected via a system bus. Among them, the non-volatile storage medium of the computer device stores an operating system, a database and computer-readable instructions, and the database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement a hot search term interaction method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute a hot search term interaction method. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art can understand that Figure 21 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0182] In this embodiment, the processor is used to execute the specific functions of each module / submodule in the hot search term interaction device of this application, and the memory stores the program code and various data required to execute the above modules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the hot search term interaction device, and the server can call the server's program code and data to execute the functions of all submodules.

[0183] The present application also provides a non-volatile storage medium, in which the hot search term interaction method is written into a computer program and stored in the storage medium in the form of computer-readable instructions. When the computer-readable instructions are executed by one or more processors, it means that the program is running in the computer, thereby enabling one or more processors to execute the steps of the hot search term interaction method of any of the above embodiments.

[0184] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0185] To sum up, this application tracks the user's gaze point when browsing the hot search page to perform control interaction to display relevant content of the hot search, enhance the interactivity of the hot search page, and improve the effectiveness of user browsing information reading.

[0186] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0187] Those skilled in the art will appreciate that the steps, measures, and schemes in the various operations, methods, and processes discussed in this application may be interchanged, modified, combined, or deleted. Furthermore, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be interchanged, modified, rearranged, decomposed, combined, or deleted.

[0188] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for interacting with hot search terms, characterized in that: The steps include: In response to a face presence event acting on a camera view frame, identifying eye features in the camera view frame to locate a gaze point of the eye features acting on a current graphical user interface; In response to a gaze event in which the gaze point acts on a hot search term control in the hot search ranking window, displaying a term-specific animation effect corresponding to the hot search term control in the current graphical user interface, and the hot search ranking window is displayed in the current graphical user interface; In response to a sustained gaze event of the gaze point acting on the hot search term control, displaying a term interaction window corresponding to the hot search term control in the current graphical user interface, including: in response to the sustained gaze event of the hot search term control acting on an associated anchor object, monitoring the live broadcast status of a live broadcast room associated with the anchor object; when monitoring that the live broadcast status of the live broadcast room is live broadcasting, obtaining the live broadcast stream and live broadcast room feature information of the live broadcast room, and displaying the term interaction window in the current graphical user interface, so as to output the live broadcast stream and live broadcast room feature information to the term interaction window for display; Monitor the display duration of the entry interaction window that is playing the live stream, and when the display duration exceeds a preset duration, display a countdown window on the current graphical user interface, wherein the countdown window displays a countdown to enter the live broadcast room; Obtaining a video stream captured by a camera, and identifying current head posture features in the video stream; When the head posture feature is characterized as a nodding posture and the countdown has not yet been reached, displaying a live broadcast room page associated with the live stream played in the entry interaction window in the current graphical user interface; When the head posture characteristic is a head shaking posture and the countdown has not yet arrived, canceling the display of the countdown window in the current graphical user interface; When the countdown is reached, the live broadcast room page associated with the live broadcast stream played in the entry interaction window is displayed in the current graphical user interface.

2. The method according to claim 1, characterized in that The step of responding to a face presence event acting on a camera view frame and identifying eye features in the camera view frame to locate a representation of a gaze point in a current graphical user interface caused by the eye features comprises the following steps: Obtaining a camera view frame captured by a camera, calling a face recognition model trained to convergence, and identifying whether there is a face image in the camera view frame; When a face image exists in the camera view frame, calling a human eye recognition model trained to convergence to recognize the human eye features in the face image, wherein the human eye features include the human eye image and human eye position information; The gaze point localization model trained to convergence is called to obtain a two-dimensional coordinate position output after fusing the features of the human eye image and the human eye position information, so as to locate the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

3. The method according to claim 1, characterized in that The step of responding to the continuous gaze event of the gaze point acting on the hot search term control includes the following steps: Monitor the overlapping time between the continuously located gaze point and the hot search term control, determine whether the overlapping time exceeds a preset gaze time, and if so, trigger a sustained gaze event in response to the current gaze point acting on the hot search term control; Monitor the display duration of the currently displayed entry's concrete animation effect, and determine whether the display duration exceeds the preset continuous display duration. If so, trigger a continuous gaze event in response to the currently positioned gaze point acting on the hot search entry control.

4. The method according to claim 1, wherein The step of responding to the sustained gaze event of the gaze point acting on the hot search term control and displaying the term interaction window corresponding to the hot search term control in the current graphical user interface further includes the following steps: When it is monitored that the live broadcast status of the live broadcast room is not currently broadcasting, the anchor feature information of the anchor object is obtained, and the entry interaction window is displayed in the current graphical user interface to output the anchor feature information to the entry interaction window for display.

5. The method according to claim 1, wherein The step of responding to the sustained gaze event of the gaze point acting on the hot search term control and displaying a term interaction window corresponding to the hot search term control in the current graphical user interface includes the following steps: In response to a continuous gaze event acting on the hot search term control, obtaining a target hot search term contained in the hot search term control, and obtaining a video stream acquisition address of a popular video associated with the target hot search term from a server; Displaying the entry interaction window in the current graphical user interface, and outputting the video stream obtained from the video stream acquisition address to the entry interaction window for display; In response to a window interaction event acting on the entry interaction window, an interaction result of the window interaction event is obtained and pushed to a server, so that the server updates the conversion rate information of the popular video according to the interaction result.

6. The method according to claim 5, characterized in that The step of displaying the entry interactive window in the current graphical user interface and outputting the video file obtained from the video acquisition connection address to the entry interactive window for display includes the following steps: Obtaining a current video frame of the video stream played in the entry interaction window to call a person recognition model trained to convergence and identify a person object in the video frame; Determine whether the target hot search term contains the name text of the person object, and if so, obtain the person introduction information corresponding to the name text; A character introduction window is displayed in the current graphical user interface, and the name text and character introduction information are output to the character introduction window for display.

7. A hot search term interactive device, characterized in that: include: a gaze point positioning module, configured to respond to a face presence event acting on a camera view frame, identify eye features in the camera view frame, and locate a gaze point where the eye features act on a current graphical user interface; a term gaze response module, configured to respond to a gaze event in which the gaze point acts on a hot search term control in the hot search ranking window, and display a term-specific animation effect corresponding to the hot search term control in the current graphical user interface, wherein the hot search ranking window is displayed in the current graphical user interface; A continuous gaze response module is used to respond to the continuous gaze event of the gaze point acting on the hot search term control, and display the term interaction window corresponding to the hot search term control in the current graphical user interface, including: responding to the continuous gaze event of the hot search term control acting on the associated anchor object, monitoring the live broadcast status of the live broadcast room associated with the anchor object; when monitoring that the live broadcast status of the live broadcast room is live broadcasting, obtaining the live broadcast stream and live broadcast room feature information of the live broadcast room, and displaying the term interaction window in the current graphical user interface to output the live broadcast stream and live broadcast room feature information to the term interaction window for display; monitoring the display time of the term interaction window that is playing the live stream, and when the display When the duration exceeds the preset time, a countdown window is displayed in the current graphical user interface, and the countdown to entering the live broadcast room is displayed in the countdown window; the video stream captured by the camera is obtained, and the current head posture feature in the video stream is identified; when the head posture feature is characterized by a nodding gesture and the countdown has not been reached, the live broadcast room page associated with the live stream played in the entry interaction window is displayed in the current graphical user interface; when the head posture feature is characterized by a shaking head gesture and the countdown has not been reached, the display of the countdown window in the current graphical user interface is canceled; when the countdown is reached, the live broadcast room page associated with the live stream played in the entry interaction window is displayed in the current graphical user interface.

8. The device according to claim 7, characterized in that The gaze point positioning module includes: A face recognition submodule is used to obtain a camera view frame captured by a camera, call a face recognition model trained to convergence, and identify whether there is a face image in the camera view frame; A human eye feature recognition submodule is used to call a human eye recognition model trained to convergence when a human face image exists in the camera view frame, and recognize the human eye features in the human face image, wherein the human eye features include human eye image and human eye position information; The gaze point positioning submodule is used to call the gaze point positioning model trained to convergence, obtain the two-dimensional coordinate position output after fusing the respective features of the human eye image and the human eye position information, and locate the gaze point in the current graphical user interface according to the two-dimensional coordinate position.

9. An electronic device comprising a central processing unit and a memory, characterized in that: The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 6.

10. A non-volatile storage medium, characterized in that: It stores a computer program implemented according to the method described in any one of claims 1 to 6 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the method are executed.

Images