CN115988228A - Method, device, equipment and storage medium for displaying hot spots of live images - Google Patents

Abstract

The application discloses a hot zone display method, device, equipment and storage medium of a live broadcast image, belonging to the technical field of live broadcast. The method includes: displaying a live screen of a live broadcast room, where at least one recommended object is displayed on the live screen; in response to a hot spot display instruction triggered for the live screen, presenting at least one visual hot spot in the live screen, so that The visual hotspots are used to represent the number of viewers watching the location area of the corresponding recommended object in the live broadcast screen. In this way, when watching the live broadcast, there is no need for the audience to take the initiative to interact, and through the displayed visual hotspot, you can more intuitively understand the audience's interest in each recommended object, obtain audience feedback in a more timely manner, and then improve the live broadcast content accuracy.

Description

Method, device, equipment and storage medium for displaying hot spots of live images

technical field

The present application relates to the field of computer technology, in particular to the field of live broadcast technology, and provides a method, device, equipment, and storage medium for displaying hot spots on a live screen.

Background technique

With the development of network technology, webcasting has been widely popularized and has gradually become a favorite entertainment application for the public. Generally speaking, the network live broadcast scene includes the anchor client and the audience client. The anchor can create a live broadcast room in the anchor client, and the audience can interact with the anchor client after entering the live broadcast room through the audience client. For example, when the anchor performs live broadcast through the anchor client, the audience can comment or like in the live broadcast room through the audience client. Correspondingly, the comments or likes initiated by the audience client can be displayed on the corresponding in the area.

However, at present, due to the limitation of physical space during the live broadcast, the anchor cannot directly view the audience watching the live broadcast at the other end, but can only judge the audience's preference for the live broadcast content through the interactive content initiated by the audience. In this way, the anchor can only passively receive feedback from the audience. Once most of the audience lacks interaction, the anchor will not be able to get feedback in time, which may cause the live broadcast content to not be adjusted in time. For example, when the anchor recommends items to the audience in the live broadcast room, if he cannot obtain feedback from the audience in time to determine which item the audience is interested in, then he will not be able to adjust the currently recommended items in time, and it is very likely that he will not be able to accurately recommend items to the audience. Recommendation, the accuracy rate of item recommendation is low, and the viewer's viewing experience is also poor.

Contents of the invention

Embodiments of the present application provide a method, device, device, and storage medium for displaying hotspots of live images, which are used to display visual hotspots of live images, improve the timeliness of obtaining audience feedback, and further improve the accuracy of live content.

In one aspect, a method for displaying a hot zone of a live image is provided, the method comprising:

Displaying the live broadcast screen of the live broadcast room, the live broadcast screen shows at least one recommended object;

Responsive to the hot zone display instruction triggered for the live screen, at least one visual hot zone is presented in the live screen, and the visual hot zone is used to represent the number of viewers watching the location area of the corresponding recommended object in the live screen .

In one aspect, a device for displaying a hot zone of a live image is provided, the device comprising:

The picture display unit is used to display the live picture of the live broadcast room, and the live picture shows at least one recommended object;

A hotspot presentation unit, configured to present at least one visual hotspot in the live broadcast in response to the hotspot display instruction triggered for the live broadcast, and the visual hotspot is used to represent watching the corresponding recommendation in the live broadcast The number of viewers in the area where the object is located.

Optionally, the live broadcast screen also displays a hot zone display control, and the hot zone display unit is also used for:

The hot zone display instruction is obtained in response to a trigger operation on the hot zone display control.

Optionally, the device also includes a hot zone generating unit, used for:

Performing object recognition on the live screen to obtain the position area of each of the at least one recommended object in the live screen; and,

Obtaining the audience account associated with each recommended object in the at least one recommended object; wherein, the association relationship between the recommended object and the audience account is based on when the terminal device uses the audience account to play the live screen, the at least one recommended object The positional relationship between the respective position areas in the live broadcast screen and the eye gaze points detected by the terminal device is established;

Mark the associated audience account in the location area of each recommended object, and generate a visual hotspot corresponding to each recommended object.

Optionally, the hot zone generating unit is specifically used for:

Receive multiple sets of association relationships issued by the background server, each set of association relationships includes a recommendation object associated with a viewer account;

Comparing the recommended objects in the multiple sets of association relationships with the at least one recommended object to determine the viewer account associated with each recommended object in the at least one recommended object.

Optionally, at least one visual hotspot is presented in the live broadcast screen by using at least one of the following methods:

In the location area of each recommended object, at least one tag information is displayed, and one tag information represents at least one viewer account associated with the corresponding recommended object;

Display the number of audience accounts associated with each recommended object, and the number of audience accounts is positively correlated with the density of tag information;

For the recommended object with the largest number of associated viewer accounts, it is displayed in a hot zone display style different from that of the rest of the recommended objects;

Recommended objects with different numbers of associated viewer accounts will be displayed in different hot zone display styles;

The recommendation objects whose number of associated viewer accounts are in different numerical intervals are displayed in different hot zone display styles.

Optionally, the live broadcast screen also displays a hot zone display control, and the hot zone display unit is also used for:

The hot zone display instruction is obtained in response to a trigger operation on the hot zone display control.

Optionally, the device also includes a gaze recognition unit, configured to:

performing object recognition on the live screen, and obtaining the respective location areas of the at least one recommended object in the live screen;

Obtain the position information of the detected eye gaze point on the live screen;

determining a target recommendation object corresponding to the location information based on the location relationship between the location information and the location area of each recommended object;

An association relationship between the currently used target audience account and the target recommendation object is established, and the association relationship is uploaded to the background server.

Optionally, the device also includes an object focusing unit for:

receiving a trigger operation performed on a target visual hotspot in the at least one visual hotspot;

Displaying the focus operation control of the target recommendation object corresponding to the target visual hotspot;

In response to a trigger operation performed on the focus operation control, the target recommendation object is enlarged and displayed.

Optionally, the object focusing unit is specifically used for:

In response to a trigger operation performed on the focus operation control, send a focus instruction to the connected imaging device, where the focus instruction is used to instruct the imaging device to focus on the target recommended object;

A screen display is performed based on the focused screen data sent by the imaging device, so as to display the enlarged target recommendation object.

Optionally, the hot zone presentation unit is also used for:

After receiving a trigger operation for a target visual hotspot in the at least one visual hotspot, displaying an information display control corresponding to the target recommended object;

In response to a trigger operation performed on the information display control, an information display page of the target recommended object is displayed, and the information display page displays the object introduction information of the target recommended object and the account identifier of the associated audience account. at least one.

Optionally, the information display page also displays a first object recommendation control corresponding to the target recommendation object;

Then the device also includes a recommending unit for:

In response to a trigger operation performed on the first object recommendation control, an object link address associated with the target recommended object is sent to a viewer account associated with the target recommended object.

Optionally, the recommendation unit is also used for:

In response to a trigger operation performed on the account identifier of the target audience account among the audience accounts displayed on the information display page, an instant messaging page with the target audience account as the communication object is displayed, and the instant messaging page displays the target recommendation A second object recommendation control corresponding to the object;

In response to a trigger operation performed on the second object recommendation control, an object link address associated with the target recommended object is sent to the target audience account.

Optionally, the hot zone presentation unit is also used for:

In response to the trigger operation performed on the account identification of the target audience account, display the gaze point track page of the target audience account, and the gaze point track page includes the gaze point of the target audience account on the corresponding terminal device. Corresponding recommended objects;

Wherein, the account ID of the target audience account is the account ID displayed on the information display page, or is the account ID displayed on the instant messaging page.

Optionally, the hot zone presentation unit is specifically used for:

According to the eye gaze point corresponding to the target audience account and the length of stay in the location area of each recommended object, sort the recommended objects, and display the gaze based on the sort order of the recommended objects point track page; or,

According to the eye gaze point corresponding to the target audience account, the trajectory order of each recommended object within the position area of each recommended object is sorted, and based on the sorted order of each recommended object, the gaze is displayed Click the track page.

Optionally, the hot zone presentation unit is also used for:

Show hot zone off controls;

In response to a trigger operation performed on the hot spot closing control, the at least one visual hot spot is hidden, and the live video is returned to display.

Optionally, the live broadcast screen also displays a display page display control of the at least one recommended object;

The hotspot rendering unit is then used to:

In response to a trigger operation performed on the display page display control, display a display page including the at least one recommended object; on the display page, display a display manipulation control for viewing viewer accounts associated with each recommended object;

In response to a trigger operation performed on the display manipulation control corresponding to the target recommendation object, the account identifier of the viewer account associated with the target recommendation object is displayed.

Optionally, the hot zone presentation unit is specifically used for:

sorting the at least one recommended object according to the number of viewer accounts associated with each of the at least one recommended object;

The display page is displayed based on the sort order of the at least one recommended object.

In one aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

In one aspect, a computer storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the steps of any one of the above methods are implemented.

In one aspect there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps of any one of the above-mentioned methods.

In the embodiment of the present application, the terminal device may present at least one visual hotspot, which is used to represent the number of viewers watching the area where the corresponding recommended object is located in the live broadcast screen, so that when watching the live broadcast screen, there is no need for the audience to actively Interactive behaviors can also more intuitively understand the audience's interest in each recommended object, and obtain audience feedback in a more timely manner. Correspondingly, the anchor can adjust the live broadcast content in time to improve the accuracy of the live broadcast content. For example, when an anchor recommends items live, he can introduce and recommend items in a targeted manner, thereby improving the accuracy of item recommendations and improving the experience of the audience.

Description of drawings

FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of a method for displaying hot spots on a live screen provided by an embodiment of the present application;

Figures 3a to 3b are schematic diagrams of the live broadcast screen provided by the embodiment of the present application;

Figures 4a to 4c are schematic diagrams of live images presenting visual hotspots provided by the embodiment of the present application;

FIG. 5 is another schematic flowchart of a method for displaying a hot zone of a live image provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of the principle of eye tracking provided by the embodiment of the present application;

FIG. 7 is another schematic flow chart of the method for displaying the hot zone of the live screen provided by the embodiment of the present application;

Fig. 8 is another schematic flow chart of the method for displaying the hot zone of the live screen provided by the embodiment of the present application;

Figures 9a to 9g are schematic diagrams of the operation of the live screen provided by the embodiment of the present application;

Fig. 10 is a schematic diagram of the operation of displaying the display page provided by the embodiment of the present application;

FIG. 11 is a schematic structural diagram of a hot zone display device for live images provided by an embodiment of the present application;

FIG. 12 is a schematic structural diagram of a computer device provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the application clearer, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application. In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined arbitrarily with each other. Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

In order to facilitate the understanding of the technical solutions provided by the embodiments of the present application, some key terms used in the embodiments of the present application are first explained here:

Live broadcast: Live broadcast refers to the technology in which the audio or video data collected by the host end through audio or video collection equipment is compressed into a watchable and transmittable video stream through a series of processing such as video encoding, and then output to the audience end device for playback. Live broadcasting is a broadcasting method in which post-synthesis and broadcasting are carried out at the same time. In addition to the audio or video data collected by the acquisition device, other content will be synthesized and displayed in the live broadcast screen, such as screen special effects (such as special effects for beautification or face-covering effects, etc.), interactive operation controls (such as likes, comments, or follow-up controls), and recommended object (such as commodity) entrances, etc.

Recommended object: The recommended object can be the content displayed on the live screen, such as physical items placed in the main physical space, or electronic content displayed on the live screen, such as virtual items, text or link addresses, etc. For example, when the host recommends physical products displayed in the physical space, the host can introduce each product, and the audience can judge whether to purchase the product based on the introduction of the host, then the recommended objects can be these products, and for In some live broadcasts, what the anchor recommends is not physical products, but electronic content such as text displayed on the screen, so the recommended objects can also be these texts. The specific form of the recommended object is not limited in this embodiment of the present application.

Visual hotspot: The visual hotspot can measure the attention of viewers who watch the live broadcast for each recommended object. It is the result of dividing the live broadcast by recommending objects according to the attention of viewers watching the live broadcast. , for example, the higher the viewer's attention to a recommended object, the higher the attention of the visual hotspot representation, for example, when marked with a color block, the color block of the recommended object area with a higher degree of attention is darker and more dense. Among them, the degree of attention here is mainly measured by the recommended object that the audience's eyeball gazes on.

Eye gaze point: The eye gaze point refers to the viewer’s gaze point on the terminal device determined by eye tracking technology. In the embodiment of this application, it mainly refers to the viewer’s gaze point on the live broadcast screen when the audience is watching the live screen. . Eye tracking technology is a scientific technology that can predict the user's gaze in real time. When people's eyes look in different directions, there will be subtle changes in the eyes, and these changes will generate features that can be extracted. These features can be captured by images Or the way of scanning and extraction is detected by the terminal device, so as to track the changes of the eyes in real time and predict the user's gaze point.

Viewer account: In the live broadcast scene, it generally includes the anchor and the audience. The audience account is the account used by the audience. The audience can watch the live broadcast content by logging in to the audience account on the live broadcast client. It should be noted that, in actual scenarios, viewers can use tourist accounts to watch the live broadcast without account registration, therefore, the audience accounts here may also include tourist accounts.

The following briefly introduces the design idea of the embodiment of the present application.

With the continuous development of science and technology, various traffic platforms provide live broadcast functions, and the anchor can recommend objects to the audience through live broadcast. However, due to the limitation of physical space, the anchor cannot directly view the audience, and cannot directly reflect from the audience. In order to get feedback from the audience, but only passively accept the feedback from the audience, there is a certain degree of uncertainty in the selection of the live broadcast content, so that the current recommended items cannot be adjusted in time, and it is very likely that the item cannot be accurately provided to the audience. Recommendation, the recommendation accuracy rate of items is low. For example, when the anchor does not know which items the audience is looking for, if they introduce some items that the audience is not interested in, the viewing experience of the audience will be poor.

In response to these problems, the main reason is that the anchor cannot actively obtain feedback from the audience, but can only judge the audience's preference through barrage, likes, or gifts. The threshold for these judgment dimensions is relatively high, and the audience needs to have these active behaviors It can only be judged later, so to solve these problems, a new dimension of obtaining audience feedback is needed, so that the anchor device can actively present audience feedback to the anchor.

In view of this, an embodiment of the present application provides a method for displaying a hot spot on a live screen. In this method, the terminal device may present at least one visual hot spot, and the visual hot spot is used to indicate where the corresponding recommended object is located in the live screen. The number of viewers in the location area, so that when watching the live broadcast, the audience does not need to actively interact, and can also more intuitively understand the audience's interest in each recommended object, and obtain audience feedback in a more timely manner.

In some embodiments, when the terminal device uses the audience account to play the live video, the audience account is associated with the recommended object through the detected position area of the gaze point on the live screen, and then when it needs to be presented on the live screen When the visual hotspot is selected, the corresponding visual hotspot can be presented in the live broadcast screen.

In some embodiments, by collecting the viewer’s line of sight and trajectory on the viewer’s end, and displaying them in the form of hot spots on the anchor’s device, the anchor can judge which pictures are interesting to the viewer and which are not, according to the hot spots. In this way, the anchor can adjust the content of the live broadcast in time, such as adjusting the live broadcast camera or speech content, focusing on the pictures that are more interesting to the viewers, making the live broadcast more flexible, just like making a live speech, and can be adjusted in time according to the audience's feedback Speaking skills, active atmosphere, and at the same time enhance the viewing experience of the audience.

It can be seen that in the method provided by the embodiment of this application, the host device can actively present audience feedback to the host, which expands the dimension for the host to obtain audience feedback. Correspondingly, the host can adjust the live content in time, improving the accuracy of the live content. . For example, when an anchor recommends items live, he can introduce and recommend items in a targeted manner, thereby improving the accuracy of item recommendations and improving the experience of the audience.

After introducing the design idea of the embodiment of the present application, the following briefly introduces the applicable application scenarios of the technical solution of the embodiment of the present application. It should be noted that the application scenarios introduced below are only used to illustrate the embodiment of the application and not limited. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

The solutions provided by the embodiments of the present application can be applied to most video application scenarios, and are especially applicable to real-time video application scenarios such as live broadcast scenarios. As shown in FIG. 1 , it is a schematic diagram of a network architecture provided by an embodiment of the present application, and the architecture may include a first device 101 , a server 102 and a second device 103 .

The first device 101 can install and run a real-time video application capable of playing video, such as a browser or a real-time video client, and the user can perform corresponding real-time video services, such as live broadcast services, on the application. The application involved in the embodiment of the present application may be a software client, or a client such as a web page or a small program, and the server is a background server corresponding to the software, web page, or small program, etc., and the specific type of the client is not limited. The first device 101 may be a terminal used by a first type of user, and the first type of user may use the first device 101 to play real-time video.

The server 102 can be the background server corresponding to the real-time video application installed on the first device 101, for example, it can be an independent physical server, or it can be a server cluster or a distributed system composed of multiple physical servers, or it can provide cloud services , cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (Content Delivery Network, CDN), and big data and artificial intelligence platform Cloud servers for cloud computing services, but not limited thereto.

The second device 103 can also install and run a real-time video application that can play video, such as a browser or a real-time video client, and the user can perform corresponding real-time video services, such as live broadcast services, on the application. The second device 103 may be a terminal used by a second type of user, and the second type of user may initiate and play real-time video by using the first device 101 .

The first device 101 and the server 102, and the second device 103 and the server may be directly or indirectly connected through one or more networks. The network can be a wired network or a wireless network. For example, the wireless network can be a mobile cellular network, or a wireless fidelity (Wireless-Fidelity, WIFI) network, and of course other possible networks. The embodiment of the present invention There is no restriction on this.

The above-mentioned first device 101 or second device 103 may be, for example, a smart phone, a smart handheld, a tablet computer (PAD), a notebook computer, a desktop computer, a smart TV, a vehicle-mounted terminal, etc., but is not limited thereto.

Taking the live broadcast scene as an example, the first device 101 can be the host device. Correspondingly, the application program installed on the first device 101 can be the host client used by the host. The host can use the data collection equipment included in the first device 101 itself, such as Cameras and microphones collect audio data or video data, or collect audio data or video data through an external camera or recording device connected to the first device 101, and upload these audio data or video data to the server 102, so that through the collected audio Or video data to generate a live image.

The second device 103 may be a viewer device, and the application program on the terminal device 103 may be a viewer client used by the viewer. The viewer may use the viewer client to acquire live image data from the server 102 and display it through the viewer client.

In an actual scenario, a terminal device can usually serve as both the first device 101 and the second device 103 .

In actual application, after the anchor creates a live broadcast room through the first device 101 , viewers can enter the live broadcast room through the second device 103 to watch the live broadcast images. When the viewer is watching the live video, the second device 103 can detect the gaze point of the viewer's eyes in real time through the eye tracking technology. The second device 103 can realize the detection of the eyeball fixation point by means of infrared detection or image recognition, and of course, can also realize the detection of the eyeball fixation point in other possible ways. Taking infrared detection as an example, the second device 103 can include infrared ( Infrared (IR) light camera, and then can irradiate pupil by IR light, judge eyeball fixation point according to pupil reflection light. At the same time, the second device 103 can also perform real-time image recognition for the live broadcast image, identify the location area of each recommended object in the live image, and then combine the position information of the eyeball's gaze point in the live image to determine the recommended object that the audience is looking at. And upload viewer information (namely viewer account information currently logged in by the second device 103 ) and recommended objects watched by each viewer to the server 102 in real time.

In a possible implementation manner, the first device 101 can also perform real-time image recognition on the live screen in real time, identify the location area of each recommended object in the live screen, and place each recommended object on the terminal of the first device 101. The location area is uploaded to the server 102, and then the server 102 can generate the corresponding recommended object for each recommended object based on the received recommended objects sent by the second device 103 and the location area of each recommended object uploaded by the first device 101. Visual hotspots. When the first device 101 requests to display the visual hotspot, the generated visual hotspot data is sent to the first device 101 so that the visual hotspot can be presented on the first device 101 .

In another possible implementation, the server 102 sends the recommended objects watched by each viewer to the first device 101, and the first device 101 can also perform real-time image recognition on the live images in real time to identify the live images The location area of each recommended object in the image is combined with the recommended objects that each viewer has watched to generate the visual hotspot of each recommended object. When the host performs an operation to display the visual hotspot, the first device 101 may present the visual hotspot in the live broadcast screen. In this way, the generation of the visual hotspot implemented by the first device 101 can effectively reduce the delay when the visual hotspot is presented, and improve the real-time performance of the visual hotspot information acquired by the anchor.

Of course, in the above-mentioned embodiments, the first device 101 is used as an example to present the visual hotspot, but in practical applications, the second device 103 can also present the visual hotspot.

In addition, in the above-mentioned embodiments, the live broadcast scene is taken as an example, but the method of the embodiment of the present application can also be applied to other video scenes, for example, the method of the embodiment of the present application can be applied to the multi-person video conference scene, then Each terminal device in the multi-person video conferencing scenario may correspond to the above-mentioned first device 101 or second device 103, or, the method in the embodiment of the present application may also be applied to the online classroom scenario, then the teacher in the online classroom scenario The terminal device may correspond to the above-mentioned first device 101, for example, and the student-side device may correspond to the above-mentioned second device 103. Of course, it may also be applied in other video scenarios, which is not limited in this embodiment of the present application.

It should be noted that, in the embodiment of the present application, the number of the first device 101 may be one or multiple, and similarly, the number of the server 102 may also be one or multiple, that is to say, for , the number of the first device 101 or the number of the server 102 is not limited.

In a possible application scenario, the relevant data involved in the embodiment of the present application (such as recommended objects watched by each audience account, etc.) may be stored using cloud storage (cloud storage) technology. Cloud storage is a new concept extended and developed from the concept of cloud computing. Distributed cloud storage system refers to a large number of different types of storage in the network through functions such as cluster applications, grid technology, and distributed storage file systems. Devices (or storage nodes) work together through application software or application interfaces to jointly provide a storage system with data storage and service access functions.

At present, the storage method of the storage system is: create logical volumes, when creating logical volumes, allocate physical storage space for each logical volume, the physical storage space may be composed of disks of a certain storage device or several storage devices. The client stores data on a logical volume, that is, the data is stored on the file system. The file system divides the data into many parts, and each part is an object. The object contains not only data but also data identification (ID, ID entity) and other additional information, the file system writes each object to the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access data, the file system can be based on each The object's storage location information allows the client to access the data.

The process of the storage system allocating physical storage space for the logical volume, specifically: according to the capacity estimation of the objects stored in the logical volume (this estimation often has a large margin relative to the capacity of the actual object to be stored) and the independent redundant disk Array (RAID, Redundant Array of Independent Disk) group, which divides the physical storage space into stripes in advance, and a logical volume can be understood as a stripe, thus allocating physical storage space for the logical volume.

In a possible application scenario, in order to reduce the communication delay, servers 102 can be deployed in various regions, or for load balancing, different servers 102 can serve the respective first device 101 or second device 103 corresponding area. A plurality of servers 102 can realize data sharing through blockchain, and a plurality of servers 102 is equivalent to a data sharing system composed of a plurality of servers 102 . For example, the first device 101 or the second device 103 is located at location a, and communicates with the server 102 , and the first device 101 or the second device 103 is located at location b, and communicates with other servers 102 .

For each server 102 in the data sharing system, there is a node identification corresponding to the server 102, and each server 102 in the data sharing system can store node identifications of other servers 102 in the data sharing system, so that subsequent The node identification of the server 102 broadcasts the generated block to other servers 102 in the data sharing system. Each server 102 may maintain a node identification list, and the name of the server 102 and the node identification are correspondingly stored in the node identification list. Wherein, the node identifier may be an Internet Protocol (IP) address for interconnection between networks and any other information that can be used to identify the node.

Of course, the method provided in the embodiment of the present application is not limited to the application scenario shown in FIG. 1 , and can also be used in other possible application scenarios, which is not limited by the embodiment of the present application. The functions that can be realized by each device in the application scenario shown in FIG. 1 will be described together in subsequent method embodiments, and will not be repeated here.

The method flow provided in each embodiment of the present application can be executed by any one of the first device 101, the second device 103, or the server 102 in FIG. or may also be jointly executed by the first device 101, the second device 103, and the server 102. The following mainly uses the first device 101, the second device 103, and the server 102 as examples for introduction.

Referring to FIG. 2 , it is a schematic flowchart of a method for displaying hot spots on a live image provided by an embodiment of the present application.

Step 201: The terminal device displays the live broadcast screen of the live broadcast room, and the live broadcast screen displays at least one recommended object.

It should be noted that the terminal device here can be the first device 101 mentioned above, or the second device 103 mentioned above. That is to say, in practical applications, the device that displays the visual hotspot can be the host The end device may also be a viewer end device, which is not limited in this embodiment of the present application.

In the specific implementation process, the terminal device can respond to the host's live room creation operation, create a corresponding live room, and can respond to the host's start operation. , to display the live video of the live room on the terminal device.

In some implementations, the terminal device may respond to the anchor's start operation on the live broadcast application, start the live broadcast application, and based on the anchor's start-up operation in the live broadcast application, request the start of the broadcast from the server corresponding to the live broadcast application, and correspondingly, based on the server's response , to display the live video on the terminal device.

In some implementation manners, the terminal device may also start the live reference in response to the trigger of other devices. For example, when the anchor is live broadcasting, he usually connects other external devices, such as camera equipment, microphone equipment, lighting equipment, and external display screens. The terminal device is made to start the live broadcast application to perform subsequent related operations.

Correspondingly, the terminal device may also respond to the viewer's operation of entering the live broadcast room, and enter the host's live broadcast room, that is, display the live broadcast picture of the live broadcast room on the terminal device.

In some embodiments, the terminal device can respond to the viewer's start operation on the live broadcast application, start the live broadcast application, and based on the live broadcast room selected by the viewer in the live broadcast application, request the live broadcast data of the live broadcast room from the server, and then based on the server's response , to display the live video on the terminal device.

In some implementations, the content displayed by the host device and the viewer device may be the same, or there may be some differences. For example, the live broadcast screen displayed by the host device may include functions that are not included in the live screen displayed by the viewer device. button, similarly, the live screen displayed by the viewer device can also include function buttons that are not included in the live screen displayed by the anchor device.

In the above process, the terminal device starts the live broadcast application, and displays a live broadcast screen in the live broadcast application, and one or more recommended objects are displayed in the live broadcast screen.

In some implementations, the recommended objects may be physical items placed in the physical space of the live broadcast room.

Referring to FIG. 3 a , it is a schematic diagram of a live screen. When anchor A creates a live broadcast room, or starts broadcasting in the created live broadcast room, those who enter the live broadcast room of anchor A to watch can see the live broadcast screen as shown in Figure 3a. When the anchor A is live broadcasting, he can take a video picture through an image acquisition device such as a camera, and show the video picture to the audience. As shown in Figure 3a, the anchor A shoots an item display platform in a physical space through a camera, so that the live broadcast The item display stand can also be displayed on the screen, and multiple physical objects are displayed on the item display stand. As shown in Figure 3a, the item display stand in the top row consists of multiple enterprise dolls, and the item display stand in the second row displays There are toy cars, cups, rabbit dolls, etc. Through the live broadcast screen displayed by the audience device, the audience can watch the various physical objects on the item display platform, and these physical objects can be recommended objects. The item is introduced, and the audience can judge whether they need the physical item based on the introduction of the anchor.

In some implementations, the recommended objects may also be electronic content displayed on the live broadcast screen, such as virtual items, text or link addresses, and the like.

Referring to FIG. 3 b , it is a schematic diagram of another live image. In the live broadcast picture shown in Figure 3a, anchor A may not use an image acquisition device such as a camera to provide a live broadcast picture, but directly present an electronic content interface, for example, the screen pictures of other electronic devices may be connected to form a live broadcast screen, then the electronic content presented in the live broadcast screen can also be used as recommendation objects.

For example, anchor A can be a game anchor, then anchor A can connect the game screen he is currently playing to form a live broadcast screen, as shown in Figure 3b, anchor A can currently be in the game hero selection interface, and the interface shows Heroes 1 to 4 of the game, through this interface, anchor A can choose the hero to play next, or choose the hero to explain to the audience, then these heroes can be recommended objects.

Step 202: The terminal device presents at least one visual hotspot in the live broadcast in response to the hotspot display instruction triggered for the live broadcast, and each visual hotspot is used to represent the number of viewers who are watching the location area of the corresponding recommended object in the live broadcast.

In the embodiment of the present application, in order to allow the anchor or the viewer to obtain the degree of interest of the viewer currently watching the live broadcast image for each recommended object in the live broadcast image, the visual hotspot of the current live broadcast image may be displayed for it.

In some implementations, as shown in FIG. 3a and FIG. 3b , a hot zone display control is also displayed in the live broadcast picture. Yes, based on the trigger operation, the terminal device may receive a hotspot display instruction, for example, the live broadcast application client on the terminal device may receive the hotspot display instruction, and then present the corresponding visual hotspot.

In Fig. 3a and Fig. 3b, the hot zone display controls are displayed at the bottom and top of the live screen respectively, but it should be understood that the embodiment of the present application does not agree with the display position and icon style of the hot zone display controls. If there is a limit, it can be set according to the actual situation in actual application.

Optionally, the user's trigger operation on the hot zone display control includes but is not limited to: click operation, long press operation, double-click operation, slide operation, etc. The embodiment of the present application does not limit the type of trigger operation. Similarly, when referring to trigger operations later, the operation types of the operations may be the above-mentioned operations, and for trigger operations in different spaces, the types of the trigger operations may be the same or different.

In some implementations, for the cleanliness of the live broadcast screen, the hot zone display control may not be displayed in the live broadcast screen, and the user (can be the anchor or the audience) can trigger the terminal device to obtain the hot zone in other ways Show instructions. For example, by setting a shortcut button, that is, setting a button of the terminal device as a shortcut button for hot zone display, and then operating the shortcut button, the terminal device can obtain a hot zone display instruction. Alternatively, gesture operation may also be used, that is, a gesture for hot zone display is preset, and when the operator uses the gesture to operate the terminal device, the terminal device may obtain a hot zone display instruction. Of course, the hot zone display command can also be triggered in other ways, such as voice control, eye movement trigger, facial expression trigger, body movement trigger, etc. The embodiment of the present application does not discuss the hot zone display command trigger mode. No restrictions are imposed.

In some implementations, the terminal device can also detect whether the triggering condition for hot zone display is currently satisfied, and if so, automatically trigger the hot zone display command. Correspondingly, the terminal device displays visual thermal district. For example, the frequency of hot zone display can be set in advance, such as once every 2 minutes or once every 5 minutes, then when the time arrives, the terminal device determines that the trigger condition for hot zone display is met, and automatically triggers the hot zone display command; or, the terminal device It is also possible to detect the live image. When a specific content appears in the live image, the terminal device determines that the triggering condition of the hot zone display is met, and automatically triggers the hot zone display command; or, the terminal device can base on the attention of each viewer to the recommended object. For example, when a product has a particularly high degree of attention, but the product currently introduced by the anchor has a low degree of attention, the terminal device determines that the trigger condition for hot zone display is met, and automatically triggers the hot zone display command. Of course, the hotspot display instruction may also be triggered by a trigger condition, and the embodiment of the present application does not limit the triggering manner of the hotspot display instruction.

In the embodiment of this application, when using the live broadcast application, the user can selectively select the trigger mode of the hot zone display command, that is, the desired trigger mode can be set in advance, and then in the process of displaying the anchor screen, it will use The corresponding trigger mode triggers the hot zone display command.

Optionally, the user may also choose to turn off the hotspot display function, which means that the user does not want to display the visual hotspot. Therefore, the display of the visual hotspot will not be triggered during the display of the live broadcast.

In the embodiment of the present application, the visual hotspot is used to represent the number of viewers watching the location area of the corresponding recommended object in the live broadcast screen. In practical applications, one viewer usually uses one viewer account to watch live content, so each visual hotspot represents the number of viewer accounts associated with the corresponding recommended object. The association between the recommended object and the viewer account is based on the When the viewer account is used to play the live broadcast, at least one recommended object’s location area in the live broadcast is established based on the positional relationship between the eye gaze point detected by the terminal device, in other words, it can also reflect the viewer’s eye on the live broadcast The regional distribution of fixation points, when the audience's eye gaze points are more densely distributed in the location area of a certain recommended object, it indicates that more viewers are more interested in the recommended object.

In some implementations, the association between the viewer account and the recommended object indicates the recommended object that the viewer account is watching. That is to say, when a viewer watches the live broadcast through its corresponding If the recommended object is selected, the audience account of the viewer is associated with the recommended object. It should be noted that when the viewer is watching the live broadcast, the gaze point of the eyeballs is constantly changing. For example, if they focus on product A in the last second, they may shift their eyes to product B in the next second. Therefore, this relationship Relationships change in real time, not fixed associations.

In the embodiment of this application, at least one of the following methods can be used to present at least one visual hotspot in the live broadcast screen, and combined with Figures 4a to 4c, Figures 4a and 4b are live broadcasts that present visual hotspots A schematic diagram of the screen.

(1) In the position area corresponding to each recommended object, at least one tag information is displayed, and one tag information represents at least one viewer account associated with the corresponding recommended object.

In this embodiment of the present application, the number of viewer accounts can be displayed by marking each viewer account associated with each recommendation object.

In some implementations, one tag information may correspond to one viewer account. That is, when the recommended object associated with the viewer account 1 is the recommended object A, a mark is added in the position area of the recommended object A, so that the number of the viewer accounts associated with the recommended object A is reflected by the number of marks.

In some implementations, color blocks can be used as marking information, and the color blocks of each viewer account are the same. Then, when the viewer account 1 is associated with the recommended object A, a color block is added in the location area of the recommended object A, so that the color block of the viewer account associated with the recommended object A is superimposed in its location area, so that through the color block The intensity of the color block and the depth of the color can intuitively reflect the attention of the recommended object A. The denser the color block and the darker the color, the higher the attention of the recommended object A. As shown in Figure 4a, a corresponding number of color blocks are superimposed and displayed in the location area corresponding to each displayed product, such as the audience in the first row of item display stands, whose eyeballs fall on the first penguin doll area from the left Quantity, less than the number of viewers whose eyeballs fall in the area of the second penguin doll from the left, so in the presented visual hotspot, it can be seen that the number of color blocks in the area of the first penguin doll is significantly less than that of the second penguin The number of color blocks in the doll's area. However, it should be noted that the number of color blocks shown in FIG. 4a may not directly correspond to the number of viewers due to possible superposition of color blocks.

In some implementations, one tag information may correspond to multiple viewer accounts. That is, one tag information can represent multiple viewer accounts watching a certain recommended object, for example, when there are 10,000 viewers watching a certain recommended object, then a tag information is added in the location area of the recommended object.

In the embodiment of the present application, the intensity of tag information is positively correlated with the number of associated viewer accounts, that is, the more viewers watch a certain recommended object, the more tag information in the location area of the recommended object.

Optionally, in the specific implementation process, the specific style of the color block is not limited in this embodiment of the application. For example, different recommended objects may use the same color block color, such as red or green, or different recommended objects may use different color block colors, such as each recommended object corresponds to a color number. In addition, different recommended objects can use the same color block shape, such as the circle shown in Figure 4a, or different recommended objects can also use different color block shapes, such as the shape of the color block corresponding to recommended object A is a circle shape, and the shape of the color block corresponding to the recommended object is a star shape. Moreover, the marking style of the visual hotspot is not limited to the color block style, and may be any visual style that can serve the purpose of marking.

In some implementations, the visual hotspot can also be presented in the form of a heat map, then when a viewer account is associated with the recommended object A, the color of the location area of the recommended object A will be darkened by one unit, so that the recommended object The number of viewer accounts associated with A determines the degree of color in its location area, so the degree of attention of recommended object A can be intuitively reflected through the degree of color in the heat map. As shown in Figure 4b, by superimposing the colors in the corresponding position area of each game hero, it reflects the audience's attention to each game hero. For example, the color of game hero 1 is obviously lighter than that of game hero 2, which shows that The audience paid more attention to Game Hero 2 than Game Hero 1.

(2) Displaying the number of viewer accounts associated with each recommended object.

In order to more intuitively reflect the degree of concern of each recommended object, the number of viewer accounts associated with each recommended object may also be directly displayed.

Referring to Fig. 4a and Fig. 4b, each recommended object also displays the number of corresponding viewers. The viewing audience of a recommended object refers to the audience whose line of sight (that is, the detected eye gaze point) falls within the area of the recommended object.

In some implementations, the number of viewers who are watching can be displayed in the corresponding area of the recommended object. As shown in Figure 4a, in the first row of item display stands, the area near the first penguin doll from the left shows "about 20,000 people are watching", which means that the gaze point of the eye falls within the area of the penguin doll The number of viewers is about 20,000. For another example, as shown in Figure 4b, "approximately 20,000 people are watching" is displayed in the location area of the game hero 1, which means that the number of viewers whose eyes are fixed on the game hero 1 is about 20,000.

In some implementations, the number of viewers watching each recommended object may also be displayed in a sorted manner. As shown in Figure 4c, in order to make it easier for the anchor to obtain the order of attention of each game hero, the number of viewers who are watching each game hero can be directly displayed in a sorted manner. 90,000, ranking first, Game Hero 3 is watching about 60,000 viewers, ranking second, and so on.

It should be noted that there is no limitation on the display manner and display style of the number of viewers who are watching. For example, other possible bubble styles may also be used, or the number of viewers watching may also be displayed at other positions. In addition, the data that appears in the visual hotspot is not limited to the number of people, but can be all data related to user portraits, such as geographical location, age, etc.

(3) For the recommendation object with the largest number of associated viewer accounts, it is displayed in a hot zone display style different from that of the rest of the recommendation objects.

In this embodiment of the application, the first recommendation object is used to represent the recommendation object with the largest number of associated viewer accounts, that is, the recommendation object with the most viewers watching, and the second recommendation object is the rest of the recommendation objects except the first recommendation object. object. In order for the anchor to know more intuitively which recommended object has the highest attention, the visual hotspot of the recommended object may be displayed in a different manner from other recommended objects.

In an implementation manner, the visual hotspot of the first recommended object may be highlighted for display. Wherein, the highlighted content may be the location area of the recommended object, or the number of viewers who are watching. As shown in Figure 4a, the number of viewers watching the penguin doll in the middle of the first row is about 70,000, and it ranks first among all items, so this penguin doll is the first recommendation object, and other items are the second For the recommended object, when presenting the visual hotspot, the bubbles of the number of viewers watching the penguin doll can be highlighted. In Figure 4a, bubbles with darker colors are used to display the number of viewers watching the penguin doll, so that the The number of viewers watching the penguin doll is even more striking. As shown in Figure 4b, the number of viewers of Game Hero 2 is about 90,000, ranking first among all game heroes, so Game Hero 2 is the first recommendation object, and other game heroes are the second recommendation Object, when presenting the visual hotspot, the number of viewers watching Game Hero 2 can be highlighted. In Figure 4b, the number of viewers watching Game Hero 2 is specifically shown in bold, so that the Look at the number of viewers is more eye-catching.

(4) Based on the number of associated audience accounts, formulate the display styles of different visual hot spots.

In the embodiment of this application, the recommended objects with different numbers of associated audience accounts are displayed in different hot zone display styles; or, the recommended objects with different numbers of associated audience accounts located in different numerical intervals are displayed in different hot zone display styles show.

In some implementations, the first type of recommended objects refers to the recommended objects whose number of associated viewer accounts is greater than the object number threshold, and the second type of recommended objects refers to the recommended objects whose associated number of viewer accounts is not greater than the object number threshold. That is to say, the number threshold can be set in advance to highlight the recommended objects with high audience attention. For example, the object number threshold can be set to 30% of the total audience in the live broadcast room, then the number of viewers greater than The visual hotspots of 30% of the recommended objects are highlighted for display. Of course, the object quantity threshold here is only an example, and in actual application, a corresponding value can be set according to actual requirements, which is not limited in this embodiment of the present application.

It should be noted that the live images showing visual hotspots shown in Figures 4a to 4c are only examples, and any other possible ways can be used to present visual hotspots in actual applications. This is not limiting.

It should be noted that since the association relationship between the recommended object and the viewer account changes in real time, correspondingly, the visual hotspot will also change with the real-time change of the association relationship. For example, the number of viewers who recommended object A was 80,000 at the last moment, but the number of viewers who are watching recommended object A at the current moment is only 20,000, so the visual hotspot of recommended object A needs to be adjusted accordingly. Such as adjusting the number and color of the displayed color blocks, and the value of the number of viewers. In addition, when the anchor is live broadcasting, he may also adjust the shooting area of the camera equipment, or adjust the content of the live broadcast, and the live broadcast screen will change accordingly, so that the visual hotspot will also change accordingly. For example, if item A was included in the area photographed at the last moment, and item A was moved out of the live broadcast screen after the lens of the camera equipment was adjusted, then the visual hotspot of item A would no longer be presented, and if a new item A Item B will also display the visual hotspot of item B based on the new data.

In the embodiment of the present application, as shown in Figures 4a to 4c, after the terminal device responds to the hot zone display command, it will also change the state of some controls on the live broadcast interface, for example, it will change the hot zone display control to the hot zone off control, As shown in the figure, it has been changed to the "Close Hot Zone" button, then the user can trigger the hot zone off control. Correspondingly, the terminal device will hide at least one visual hot zone displayed in response to the trigger operation. Return to display the previous live screen.

The solution of the embodiment of the present application will be introduced below by taking the second device (viewer device) to collect the gaze point of the audience and display the visual hotspot on the first device (anchor device) as an example. Referring to FIG. 5 , it is another schematic flow chart of the method for displaying the hotspot of the live video provided by the embodiment of the present application.

Step 501a: The first device performs object recognition on the live screen, and obtains the location area of each recommended object in the live screen.

Step 501b: The second device performs object recognition on the live screen, and obtains the location area of each recommended object in the live screen.

In the embodiment of this application, generally speaking, both the anchor terminal and the audience terminal will display the live screen, but due to the difference in equipment used by the live broadcast terminal and the audience terminal, the position of each recommended object on the device screen may be different. Therefore, each terminal device (including the first device and the second device) can recognize the live screen in real time (including people and items in the screen), and record each recommended object (including people and items in the screen) in real time The location area on the live screen.

In some implementations, the location area may refer to the location area of the recommended object on the screen of the terminal device when the terminal device is displaying the live broadcast screen. By identifying the location area of each recommended object in real time, it is convenient for subsequent implementation with the audience. The landing point is compared, or it is convenient for the display of the subsequent visual hotspot.

In this embodiment of the present application, object recognition refers to identifying live images by using image recognition, that is, identifying recommended objects and corresponding location areas included in the live images. Since the live broadcast picture usually includes other function buttons or icons in addition to the video stream picture (referring to the video picture taken by the camera equipment), the object recognition can only refer to the recognition of the video stream picture, that is Each frame image of the video stream picture can be used as the image to be recognized, so that the video frame image can be recognized frame by frame, and the recommended object and corresponding location area included in each frame can be stored; or, the object recognition can also be the current The entire live broadcast screen can be identified. For example, the screen capture of the display screen of the terminal device can be used to obtain the image to be identified, and then the intercepted image to be identified can be identified, and the recommended object and corresponding location area included in each frame can be stored.

It should be noted that the processes of step 501a and step 501b above have no substantial sequence relationship, and the execution of step 501a by the first device and the execution of step 501b by the second device can be performed continuously in real time, so the execution of steps 501a and 501b by the first device The second device may execute step 501b at the same time, or there may be a certain sequence.

Step 502: The second device obtains the detected location information of the gaze point of the eyes on the live screen.

The second device here may be a terminal device corresponding to any viewer account entering the live broadcast room. In a specific implementation process, due to hardware limitations of some terminal devices, eye tracking may not be supported, so the second device here may not include it.

The second device may detect the eye gaze point of the current viewer in real time based on the eye tracking technology.

In some embodiments, eye tracking may be performed using an eye tracker included in the second device. Referring to FIG. 6 , it is a schematic diagram of the principle of eye tracking. Wherein, the eye control device may include a built-in infrared light source, an optical sensor, an image processor, and a viewpoint calculation core and other components.

When the second device is playing the live image, the audience watches the live image, and at this time, the eye control device included in the second device executes step S1 in Figure 6, that is, the eye control device projects the created setting image to the human eyes Above, the image may be projected, for example, by an infrared light source, which is generally not perceived by the human eye. After the image is projected, the eye control device executes step S2, that is, captures the face image through the optical sensor included in it, so as to obtain the image information of the eyes from the face image. Next, the eye control device executes step S3 based on the captured eye image information, that is, extracts eye image features through its included image processor. Furthermore, the eye control device executes the S4 step based on the eye image features, that is, calculates the eye gaze point position information through its included viewpoint calculation core, such as the coordinates on the screen of the second device (the screen coordinates can be mapped to the position on the live screen ).

In some embodiments, the camera of the second device can also capture the face image of the audience, and then use the deep learning model to analyze the face image to obtain the gaze point of the audience corresponding to the second device.

In the embodiment of the present application, as long as the adopted eye tracking technology can detect the gaze point of the viewer's eyes, its specific implementation and required physical conditions are not limited. Moreover, it should be understood that the detection of eye gaze point using eye tracking technology may be performed with the permission of the viewer. For example, when the detection is performed for the first time, the live broadcast application needs to request the viewer to authorize the eye detection function.

Step 503: the second device determines the target recommendation object corresponding to the location area where the location information is located.

In the embodiment of the present application, the location information of the eye gaze point is compared with the location area of each recommended object to obtain the location area of which recommended object the eye gaze point is located in, and the recommended object is the target recommended object.

In some implementations, the position information can be represented by coordinates, and the coordinates of the eye gaze point can be used to traverse the position area included in each recommended object to obtain the target recommended object corresponding to the matching coordinates.

Step 504: The second device establishes an association relationship between the target audience account and the target recommendation object, and uploads the association relationship to the background server.

In this embodiment of the application, the target audience account refers to an account registered in the live broadcast application on the second device. In some scenarios, the second device can use the live broadcast application as a tourist, so the tourist identity can also be considered as the target audience account.

In some implementations, when the viewer uses the target viewer account to watch the live broadcast, and their eye gaze falls within the position area of the target recommended object, then there is an association between the target audience account and the target recommended object, and the association is uploaded to the live broadcast The application's background server.

It should be noted that the detection of the gaze point of the eyeball is continuously performed in real time, and the association relationship can also be uploaded in real time, that is, whenever the second device determines that the gaze point of the audience falls within the location area of the recommended object That is, after the second device determines the recommended object that the current viewer is looking at, it uploads the target audience account used by the viewer and the recommended object viewed to the background server.

Optionally, the uploaded target viewer account information may be information that can uniquely identify a viewer account, such as an account identifier (identity, ID), and the uploaded recommended object information may also be object ID or object connection address, etc. that can be uniquely identified Information about a referral object.

In this embodiment of the present application, generating a visual hotspot may include the following two methods.

(1) The first way

In this manner, the first device generates visual hotspots, that is, the manner shown in FIG. 5 .

Step 505: The first device receives multiple sets of association relationships sent by the background server, each set of association relationships includes a recommendation object associated with a viewer account.

In the embodiment of this application, in order to generate visual hotspots, the first device needs to obtain the corresponding supporting data, that is, obtain the viewer account associated with each recommended object in the live broadcast screen, and the background server receives the association uploaded by each second device in real time. relationship, the background server may send the received association relationship to the first device, so that the first device learns the viewer account associated with each recommended object based on the association relationship.

In some implementation manners, the background server may continuously receive the association relationship, and send the received association relationship to the first device in sequence. That is to say, whenever the background server receives an association relationship sent by the second device, the background server will synchronize it to the first device.

In some implementation manners, the background server may continue to receive the association relationship until it is determined that a certain trigger condition is met, and then send the association relationship to the first device once. The trigger condition may be, for example, that the time difference from the last transmission reaches the time difference threshold, or that all the association relationships of the second device have been received, or that the number of received association relationships reaches a certain number threshold, of course, it may also be Other possible trigger conditions are not limited in this embodiment of the present application.

In the embodiment of the present application, after receiving the association relationship, the first device may compare the recommended objects in multiple sets of association relationships with at least one recommended object, so as to determine the viewer account associated with each recommended object in the at least one recommended object.

For example, items A, B, C, and D are displayed on the live screen, and the association relationship received by the first device is shown in Table 1 below, where the item associated with the viewer account 1001 is item A, and the item associated with the viewer account 1001 is is item A, audience account 1002 is associated with item C, audience account 1003 is associated with item B, audience account 1004 is associated with item A, audience account 1005 is associated with item C, audience account 1006, the associated item is item D, and the viewer account 1007, the associated item is item A.

Table 1

After comparison, it can be obtained that the audience accounts associated with item A are 1001, 1004, and 1007, the audience accounts associated with item B are 1003, the audience accounts associated with item C are 1002 and 1005, and the audience accounts associated with item D are 1006.

Step 506: The first device marks the associated viewer account in the location area of each recommended object, and generates a visual hotspot corresponding to each recommended object.

In the embodiment of the present application, according to the location area of each recommended object recognized in real time, the corresponding location area is marked to form a visual hotspot of each recommended object. For example, when a color block is used as the marking information, a color block can be marked in the corresponding location area for each viewer account ID associated with the recommended object. After marking all the viewer account IDs associated with the recommended object, the recommended object can be obtained Corresponding visual hotspots.

It should be noted that the visual hotspots generated by the first device are not directly displayed. The first device can receive the association relationship data sent by the background server in real time, that is, the viewer account ID and the recommended object data it has viewed, and The background of the first device forms the visual hotspot, but does not display it, and only presents it on the live screen based on the formed visual hotspot when the display is triggered.

Step 507: The first device presents a visual hotspot on the live broadcast screen in response to the hotspot display instruction triggered for the live broadcast screen.

For this step, reference may be made to the introduction of the above-mentioned step 202, and details are not repeated here.

(2) The second way

In this method, the background server integrates the association relationship of each recommended object, and the first device generates a visual hotspot. Refer to the method shown in FIG. 7, wherein steps 501a, 501b and steps 502-504 in FIG. The embodiment shown in FIG. 5 is completely the same, so details are not repeated here.

Step 508: The first device uploads the identified recommended objects to the background server.

Step 509: Receive the viewer account associated with each recommended object in the live broadcast screen sent by the background server.

In the embodiment of the present application, the first device may upload the identified recommended object to the background server in real time after identifying the live broadcast screen, and at the same time, the background server will also receive the association relationship from the second device, Then the backend server can integrate the recommended object uploaded by the first device and the association relationship uploaded by the second device, to obtain the statistics of the viewer account associated with each recommended object uploaded by the first device, and feed back to the first device.

It should be noted that, when the background server performs data integration, the method it adopts may be the same as when the first device performs the integration, so please refer to the introduction of the above-mentioned step 505 .

Step 510: The first device marks the associated viewer account in the location area of each recommended object, and generates a visual hotspot corresponding to each recommended object.

Step 511: The first device responds to the hotspot display instruction triggered for the live broadcast, and presents the visual hotspot on the live broadcast.

For step 510 and step 511, reference may be made to the introduction of step 506 and step 507 above, and details are not repeated here.

(3) The third way

In this method, the background server generates visual hotspots, and the first device displays the hotspots. Refer to the method shown in FIG. 8, wherein steps 501a, 501b and steps 502-504 in FIG. are exactly the same, so they will not be repeated here.

Step 512: The first device uploads the identified recommended objects and corresponding location area information to the background server.

Step 513: The first device sends a hotspot request to the background server in response to the hotspot display instruction triggered for the live image.

In the embodiment of the present application, the first device may upload the identified recommended object to the background server in real time after identifying the live broadcast screen, and at the same time, the background server will also receive the association relationship from the second device, Then the background server can integrate the recommended object uploaded by the first device and the association relationship uploaded by the second device to obtain the statistics of the viewer account associated with each recommended object uploaded by the first device, and combine the location of each recommended object Region information, which is marked within the corresponding location region to form a visual hotspot for each recommended object.

When the first device needs to present a visual hotspot, if the anchor clicks the "Show hotspot" button, the first device responds to the hotspot display instruction triggered by the click operation, and sends a hotspot request to the background server to request the displayed hotspot. Visual hotspot data.

Step 514: The first device presents the visual hotspot in the live broadcast screen based on the visual hotspot data returned by the background server.

In the embodiment of the present application, after presenting the visual hotspots in the live broadcast screen, the anchor can more conveniently know the recommended objects that the audience is interested in, so as to introduce the recommended objects in a targeted manner. Referring to FIG. 9a to FIG. 9c , they are schematic diagrams of the operation flow of focusing on recommending objects.

As shown in Figure 9a, after the visual hotspot is presented in the live broadcast screen, it is easy to see that the penguin doll in the middle of the first row is currently the most concerned recommended object, and then the anchor can adjust the live broadcast content to introduce the penguin doll . Then, the target visual hotspot can be selected from the visual hotspots presented in the live broadcast screen. Here, the selected target visual hotspot is the visual hotspot corresponding to the most concerned penguin doll as an example, and the target visual hotspot Perform a trigger operation to jump to the interface shown in Figure 9b.

Optionally, the trigger operation on the target visual hotspot may be, including but not limited to: click operation, long press operation, double-tap operation, slide operation, etc. The embodiment of the present application does not limit the type of trigger operation.

As shown in Figure 9b, after the trigger operation is performed on the target visual hotspot, the operable controls for the target recommendation object corresponding to the target visual hotspot are displayed on the live broadcast screen, including the focus operation control as shown in Figure 9b and information display controls, but it should be understood that within a reasonable range, when other operations need to be performed on the target recommendation object, corresponding operation controls may also be displayed, which is not limited in this embodiment of the present application.

Optionally, in order to display the cleanliness of the interface, after operating the target visual hotspot, part of the content of the interface shown in Figure 9a can be hidden and displayed, such as the hidden display of the number of viewers in Figure 9b, to avoid interface confusion The bad viewing experience brought by clutter to users. Of course, other content can also be hidden and displayed, such as the color block mark can also be hidden and displayed.

Among them, the focus operation control is used to focus and display the target recommendation object to display the details of the target recommendation object. If the target recommendation object needs to be focused and displayed, the focus operation control can be triggered, and the terminal device responds with the focus operation The trigger operation performed by the control jumps to the interface shown in FIG. 9c, and the target recommendation object is enlarged and displayed.

In some implementation manners, the terminal device may zoom in on the area where the target recommended object is located in the current live broadcast screen, so as to obtain the effect of enlarged display of the target recommended object. If the terminal device is a viewer device, and the viewer device cannot adjust the camera equipment of the live broadcast, then the viewer device can zoom in on the area where the target object is located to focus on displaying the target recommendation object.

In some embodiments, if the terminal device is the host device, the host device may adjust the lens of the camera device to focus on the target recommendation object. Wherein, the camera device here may be a camera included in the host device itself or an external camera device.

Specifically, the host device can respond to the trigger operation on the focus operation control, and send a focus command to the connected camera device (including the camera of its own device), the focus command is used to instruct the camera device to focus on the target recommended object, and then the camera Shebi can adjust the focal length and transmit the adjusted picture data back, so that the anchor device can display the picture based on the focused picture data sent by the camera equipment to display the enlarged target recommendation object. At the same time, after the camera equipment is adjusted, the live broadcast screen displayed by the audience device will also be adjusted synchronously, that is, the enlarged target recommendation object will also be displayed. Due to the adjustment method of the camera equipment, the loss of image quality can be reduced as much as possible, thereby bringing a better viewing experience to the user.

Specifically, after listening to the user clicking the "Zoom in" button, the system sends an instruction to zoom in on the visual hotspot, and the front end displays the zoomed-in effect, as shown in Figure 9c, then zooms in on the selected penguin doll, and the audience can view it more clearly. Watch the details of the penguin doll clearly to judge whether you need to buy the product.

It should be understood that after performing the focusing operation, the live broadcast interface can be switched to a normal interface, that is, an interface that does not display the visual hotspot, and correspondingly, the state of certain spaces displayed in the live broadcast screen of the visual hotspot A corresponding switch is required. For example, as shown in FIG. 9 c , if the "Close Hot Zone" button is displayed on the live broadcast interface presenting the visual hot zone, it will be switched to the "Display Hot Zone" button for display.

Continuing to refer to FIG. 9b, there is also displayed an information display control, that is, "detailed information" shown in FIG. 9b, and the information display control is used to display the detailed information of the target recommendation object. Referring to FIG. 9 d , it is a schematic diagram of a page for displaying information of a target recommendation object.

Specifically, the terminal device may display an information display page of the target recommended object in response to a trigger operation performed on the information display control.

In some implementations, as shown in FIG. 9d, the information display page may be presented on the live screen in the form of a pop-up window. Wherein, the pop-up window shown in FIG. 9d is only a possible example, and the style and position of the pop-up window are adjusted reasonably in practical applications, which is not limited in this embodiment of the present application.

In some embodiments, the information display page can also be displayed as a complete page, that is, the information display page can be jumped from the live broadcast screen.

Wherein, the information display page displays at least one of the following information.

(1) Object introduction information of the target recommendation object.

As shown in Figure 9d, the information display page displays the information of the most concerned penguin doll, such as its name, price, and item introduction. It is conceivable that after the information display page is presented on the anchor device, the anchor can Make a better product introduction based on the information on this page.

In the embodiment of this application, in order to be able to display the object introduction information of each recommended object, it is necessary to create an object information database in advance and record the object introduction information of each recommended object that may be involved. In this way, during the live broadcast, click the detailed information Only then can there be data as a support to present the corresponding information display page. For example, the operation establishes an information database of all items in advance. When the anchor clicks on the item, he can view the detailed information of the item and assist the anchor to introduce the item in more detail.

In the embodiment of this application, the created object information database may be stored in the background server. For example, after the anchor clicks the "detailed information" button shown in Figure 9b, the terminal device sends information about the target recommended object to the background server. The request is obtained, and based on the object introduction information of the target recommendation object returned by the background server, an information display page as shown in FIG. 9d is displayed.

(2) The account ID of the audience account associated with the target recommendation object

As shown in Figure 9d, the information display page can also display the account ID of the viewer account associated with the target recommendation object, which is specifically shown as the account avatar in Figure 9d, but it should be noted that in the actual implementation process, there are still Other content may be used as the account identifier for display, which is not limited in this embodiment of the present application.

(3) Relevant recommended objects (not shown in Figure 9d)

In the embodiment of the present application, the information display interface may also display other recommended objects related to the target recommended object, and the other recommended objects are not limited to existing recommended objects in the live broadcast room.

(4) The first object recommendation control

As shown in FIG. 9d , the button "send product links in groups" displayed on the information display page is the first object recommendation control, and its function is to send object link addresses of target recommendation objects in groups.

Specifically, when the anchor is live broadcasting, viewers who have watched the target recommended object usually have a certain interest in it, so the object link address of the target recommended object can be sent to the audience accounts of these viewers. Then, the anchor may perform a trigger operation on the first object recommendation control, and then the terminal device, in response to the trigger operation, sends the object link address associated with the target recommendation object to the viewer account associated with the target recommendation object.

In some implementations, after the terminal device receives the trigger operation, it can know that the group is sent to the default viewer account, such as the viewer account of the viewer who has viewed the target recommended object.

In some implementation manners, after receiving the trigger operation, the terminal device may display a display page as shown in FIG. 9e to provide the host with selectable group sending objects.

In the embodiment of this application, the anchor can choose to send the object link address of the target recommended object to all viewer accounts in the live broadcast room; or, can also choose to send the object link address of the target recommended object to the target in the live broadcast room All audience accounts of the recommended object; or, you can also choose to send the object link address of the target recommended object to the specified audience account. After the selection is completed, the object link address of the target recommendation object is sent to the selected audience account.

It should be noted that the above descriptions are all made with the host device as an example, but the operations performed by the above host device can also be applied to the viewer device.

In the embodiment of the present application, a function of separately sending the target recommendation object link may also be provided. Referring to Fig. 9f, after the information display page of the target recommendation object is displayed, the account identification on the page can also be operated. As shown in Figure 9f, the first viewer account is used as the target viewer account, and after a trigger operation is performed on its avatar, the terminal device responds to the trigger operation performed on the target viewer account, and displays an instant messaging page with the target viewer account as the communication object.

As shown in the right figure in Figure 9f, on the instant messaging page, the account ID corresponding to the target recommendation object is displayed, as well as interactive controls for instant communication interaction with the target recommendation object, such as voice control, emoticon control, etc. In addition, A second object recommendation control is also displayed on the instant messaging page, and the second object recommendation control is used to send the object link address associated with the target recommended object to the target audience account. When a trigger operation is performed on the second object recommendation control, in response to the trigger operation, the terminal device can send the object link address associated with the target recommended object to the target audience account. In this way, the anchor can send a private message to Viewers send product links.

It should be noted that the connection address sent by the terminal device mentioned in the embodiment of the present application may be sent through the background server to send the link, that is, the terminal device sends a request to the background server, requesting the background server to send the object connection address to the corresponding viewer account.

Referring to FIG. 9g, it is a schematic diagram of displaying the gaze point track page. Wherein, the user can also perform a trigger operation on the account identification of the target audience account. Correspondingly, the terminal device responds to the trigger operation and displays the gaze point track page of the target audience account. The gaze point track page includes the target audience account on the corresponding terminal device. Each recommendation object corresponding to the eye gaze point of , that is, the viewer’s gaze stay trajectory corresponding to the target audience account, as shown in the right figure in Figure 9g, the items seen by account A include penguin dolls, drinking cups, and rabbit dolls, etc. .

Optionally, the account ID is the account ID displayed on the information display page, or the account ID displayed on the instant messaging page, that is, the gaze point track page can be displayed by triggering the account ID displayed on the instant messaging page, That is, the method (1) shown in FIG. 9g; or, the gaze point track page can also be displayed by triggering the account identifier displayed on the information display page, that is, the method (2) shown in FIG. 9g.

In some implementations, the recommended objects can be sorted according to the eye gaze point of the target audience account and the length of stay in the location area of each recommended object, and the gaze point track page can be displayed based on the sort order of each recommended object, That is, the display method shown in the right diagram of Figure 9g, according to the length of stay realized by account A, the display order is the penguin doll, the drinking cup, the rabbit doll, and the toy car.

In some implementations, it is also possible to sort the recommended objects according to the eye gaze points of the target viewer account, and the track order in the position area of each recommended object, and display the gaze point track page based on the sort order of each recommended object , that is, to display in sequence according to the detection timeline of eye gaze points.

Please continue to refer to FIG. 3 a , a display page display control may also be displayed on the live broadcast screen, and the display page display control is used to display recommended objects in the live broadcast room. Wherein, besides at least one recommended object displayed on the current live broadcast screen, the recommended objects in the live broadcast room may also include recommended objects not displayed on the current live broadcast screen. Wherein, by performing a trigger operation on the display control of the display page, the terminal device displays the display page in response to the trigger operation.

Refer to Figure 10, which is a schematic diagram of the interface of the display page. Among them, multiple commodities are displayed on the display page, such as penguin dolls, drinking cups, rabbit dolls and toy cars as shown in FIG. 10 .

In some implementations, the terminal device can regularly count the data of each recommended object, for example, it can count the number of viewer accounts associated with each recommended object in history, and then can calculate the number of viewer accounts associated with at least one recommended object. Quantity, sort at least one recommended object, and display it in the sort order of these recommended objects on the display page. As shown in Figure 10, the display page can be used as a product ranking list, sorted according to the number of people who have viewed each product. For example, the penguin doll was viewed by 2345 people and ranked first, and the drinking cup was viewed by 2341 people. , ranked second.

As shown in Figure 10, the display page also displays a display manipulation control for viewing the viewer account associated with each recommendation object, then by operating the display manipulation control corresponding to the target recommendation object, you can jump to the right picture in Figure 10 In the shown interface, the account identifier of the viewer account associated with the target recommendation object is displayed on the interface. As shown in the right figure of Figure 10, when the penguin doll is used as the target recommendation object, after the punishment operation is performed on the display operation control corresponding to the penguin doll, that is, the "People who have seen" button shown in Figure 10, the terminal device can display the The account identification corresponding to the viewer who has passed the penguin doll, such as avatar, account ID, etc.

Optionally, the account identifiers of the viewer accounts associated with the target recommendation object can also be sorted and displayed according to the number of times they have been viewed, which is specifically shown in Figure 10 as an example, or they can also be displayed in the order of the actual gaze time To sort and display, so as to assist the anchor to perform a better live broadcast.

It should be noted that the display page can be presented on the live screen in the form of a pop-up window. Wherein, the pop-up window shown in FIG. 10 is only a possible example, and the style and position of the pop-up window are adjusted reasonably in practical applications, which is not limited in this embodiment of the present application. Alternatively, it can also be displayed as a complete page, that is, you can jump from the live broadcast screen to the display page. Similarly, the display page of the account ID of the associated viewer account is also the same.

To sum up, the embodiment of this application uses the image of the front-end system of the audience device to identify objects and people in the live broadcast screen, and marks the coordinates in real time, uses eye tracking technology to record the coordinates of the audience's line of sight, and obtains the viewer's view through comparison Items and people are uploaded to the background server in real time, and then the background server sends them to the front-end system of the host device in real time. The front-end system analyzes the data for visual display, so that the host can watch the items and people viewed by the audience on the other end in real time, and understand the viewers Which ones are more interested in, so that the anchor can adjust the camera or speech in time, making the live broadcast more flexible, just like making a live speech, it can adjust the speech skills in time according to the audience's feedback, enliven the atmosphere, and improve the audience's viewing experience at the same time . For example, when selling live broadcasts, the anchor can know which products the audience is more interested in. In this way, the anchor will focus on introducing the product during the oral broadcast, improving the accuracy of product recommendation, thereby increasing the success rate of product transactions.

Please refer to FIG. 11 , based on the same inventive concept, the embodiment of the present application also provides a hot zone display device 110 of live images, which includes:

The screen display unit 1101 is used to display the live screen of the live broadcast room, and the live screen shows at least one recommendation object;

The hotspot presentation unit 1102 is configured to present at least one visual hotspot in the live broadcast in response to the hotspot display instruction triggered for the live broadcast, and the visual hotspot is used to represent the number of viewers who are watching the area where the corresponding recommended object is located in the live broadcast .

Optionally, if the live broadcast screen also displays a hot zone display control, the hot zone presentation unit 1102 is also used for:

A hot zone display instruction is obtained in response to a trigger operation on the hot zone display control.

Optionally, the device also includes a hot zone generation unit 1103, configured to:

Object recognition is performed on the live screen to obtain the position area of at least one recommended object in the live screen; and,

Obtain the audience account associated with each recommended object in at least one recommended object; wherein, the association relationship between the recommended object and the audience account is based on when the terminal device uses the audience account to play the live broadcast screen, at least one of the recommended objects respectively in the live screen The location area is established based on the location relationship between the eye gaze point detected by the terminal device;

Mark the associated audience account in the location area of each recommended object, and generate a visual hotspot corresponding to each recommended object.

Optionally, the hot zone generating unit 1103 is specifically used for:

Receive multiple sets of association relationships issued by the background server, each set of association relationships includes a recommendation object associated with a viewer account;

The recommended objects in the multiple groups of association relationships are compared with the at least one recommended object to determine the viewer account associated with each recommended object in the at least one recommended object.

Optionally, use at least one of the following methods to present at least one visual hotspot in the live broadcast screen:

Displaying at least one mark information in the location area of each recommended object, one mark information representing at least one viewer account associated with the corresponding recommended object;

Display the number of viewer accounts associated with each recommended object;

For the recommended object with the largest number of associated viewer accounts, it is displayed in a hot zone display style different from that of the rest of the recommended objects;

The density of tagged information is positively correlated with the number of associated viewer accounts;

Recommended objects with different numbers of associated viewer accounts will be displayed in different hot zone display styles;

The recommendation objects whose number of associated viewer accounts are in different numerical intervals are displayed in different hot zone display styles.

Optionally, if the live broadcast screen also displays a hot zone display control, the hot zone presentation unit 1102 is also used for:

A hot zone display instruction is obtained in response to a trigger operation on the hot zone display control.

Optionally, the device further includes a gaze point recognition unit 1104, configured to:

Object recognition is performed on the live screen to obtain the position area of at least one recommended object in the live screen; and,

Obtain the position information of the detected eye gaze point on the live screen;

determining a target recommendation object corresponding to the target location area where the location information is located;

An association relationship between the currently used target audience account and the target recommendation object is established, and the association relationship is uploaded to the background server.

Optionally, the device further includes an object focusing unit 1105, configured to:

receiving a trigger operation performed on a target visual hotspot in at least one visual hotspot;

Display the focus operation control of the target recommendation object corresponding to the target visual hotspot;

In response to a trigger operation performed on the focus operation control, the target recommendation object is enlarged and displayed.

Optionally, the object focusing unit 1105 is specifically used for:

In response to a trigger operation performed on the focus operation control, a focus instruction is sent to the connected camera device, where the focus instruction is used to instruct the camera device to focus on the target recommended object;

The screen display is performed based on the focused screen data sent by the imaging device, so as to display the enlarged target recommendation object.

Optionally, the hot zone presentation unit 1102 is also used to:

After receiving a trigger operation for a target visual hotspot in at least one visual hotspot, displaying an information display control corresponding to the target recommended object;

In response to a trigger operation on the information display control, an information display page of the target recommended object is displayed, and the information display page displays at least one of the object introduction information of the target recommended object and the account identifier of the associated viewer account.

Optionally, the information display page also displays a first object recommendation control corresponding to the target recommendation object;

Then the device further includes a recommendation unit 1106, configured to:

In response to the trigger operation performed on the first object recommendation control, the object link address associated with the target recommended object is sent to the viewer account associated with the target recommended object.

Optionally, the recommendation unit 1106 is also used for:

In response to the trigger operation performed on the account identifier of the target audience account in the audience account displayed on the information display page, an instant messaging page with the target audience account as the communication object is displayed, and the instant messaging page displays a second object recommendation control corresponding to the target recommendation object ;

In response to a trigger operation performed on the second object recommendation control, the object link address associated with the target recommended object is sent to the target audience account.

Optionally, the hot zone presentation unit 1102 is also used to:

In response to the trigger operation performed on the account identification of the target audience account, display the gaze point track page of the target audience account, and the gaze point track page includes each recommended object corresponding to the eye gaze point of the target audience account on the corresponding terminal device;

Wherein, the account ID of the target audience account is the account ID displayed on the information display page, or the account ID displayed on the instant messaging page.

Optionally, the hot zone presentation unit 1102 is specifically used for:

According to the eye gaze point corresponding to the target audience account and the length of stay in the location area of each recommended object, sort each recommended object, and display the gaze point track page based on the sort order of each recommended object; or,

According to the eye gaze point corresponding to the target audience account, the track order of each recommended object within the location area of each recommended object is sorted, and based on the sort order of each recommended object, the gaze point track page is displayed.

Optionally, the hot zone presentation unit 1102 is also used to:

Show hot zone off controls;

In response to a trigger operation performed on the hot zone closing control, at least one visual hot zone is hidden, and the live broadcast image is returned to display.

Optionally, the live broadcast screen also displays a display page display control with at least one recommended object;

Then the hot zone presentation unit 1102 is further configured to:

In response to a trigger operation performed on the display control of the display page, display a display page including at least one recommended object; on the display page, display a display manipulation control for viewing viewer accounts associated with each recommended object;

In response to a trigger operation performed on the display manipulation control corresponding to the target recommendation object, the account identifier of the viewer account associated with the target recommendation object is displayed.

Optionally, the hot zone presentation unit 1102 is specifically used for:

sorting the at least one recommended object according to the number of viewer accounts associated with each of the at least one recommended object;

Displaying a display page based on the sort order of at least one recommended object.

The device can be used to execute the methods shown in the various embodiments of the present application. Therefore, for the functions that can be realized by the functional modules of the device, etc., reference can be made to the descriptions of the foregoing embodiments, and details will not be repeated here.

The device provided in the embodiment of the present application can associate the viewer account with the recommended object through the detected position area of the gaze point of the eye on the live screen when the viewer account is used to play the live screen, and then when the live screen needs to be When the visual hotspot is presented on the live broadcast screen, the corresponding visual hotspot can be presented in the live broadcast screen. The visual hotspot is used to represent the number of viewer accounts associated with each recommended object, so that when watching the live broadcast screen, the audience does not need to actively interact Behavior, you can also more intuitively understand the audience's interest in each recommended object, and obtain audience feedback in a more timely manner.

Please refer to FIG. 12 , based on the same technical concept, this embodiment of the present application also provides a computer device 120, which may be the terminal device or server shown in FIG. 1, and the computer device 120 may include a memory 1201 and a processor 1202.

The memory 1201 is used for storing computer programs executed by the processor 1202 . The memory 1201 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function, etc.; the data storage area may store data created according to the use of the computer device, etc. The processor 1202 may be a central processing unit (central processing unit, CPU), or a digital processing unit or the like. The specific connection medium between the memory 1201 and the processor 1202 is not limited in this embodiment of the present application. In the embodiment of the present application, in FIG. 12, the memory 1201 and the processor 1202 are connected through the bus 1203. The bus 1203 is represented by a thick line in FIG. As far as possible. The bus 1203 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 12 , but it does not mean that there is only one bus or one type of bus.

The memory 1201 can be a volatile memory (volatile memory), such as a random-access memory (random-access memory, RAM); the memory 1201 can also be a non-volatile memory (non-volatile memory), such as a read-only memory, a flash memory (flash memory), hard disk (hard disk drive, HDD) or solid-state drive (solid-state drive, SSD), or memory 1201 can be used to carry or store the desired program code with instruction or data structure form and can be used by computer Any other medium accessed, but not limited to. The memory 1201 may be a combination of the above-mentioned memories.

The processor 1202 is configured to execute the methods executed in the foregoing embodiments when invoking the computer program stored in the memory 1201 .

In some possible implementations, various aspects of the method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product is run on a computer device, the program code is used to The computer device is made to execute the steps in the methods described above in this specification according to various exemplary implementations of the present application, for example, the computer device may execute the methods executed in the foregoing embodiments.

The program product may reside on any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

While preferred embodiments of the present application have been described, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, the appended claims are intended to be construed to cover the preferred embodiment and all changes and modifications which fall within the scope of the application.

Obviously, those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims (20)

1. A hot zone display method of a live broadcast picture, the method comprising:

displaying a live broadcast picture of a live broadcast room, wherein at least one recommended object is displayed on the live broadcast picture;

and responding to a hotspot display instruction triggered by the live broadcast picture, presenting at least one visual hotspot in the live broadcast picture, wherein the visual hotspot is used for representing the number of audiences watching the position area of the corresponding recommended object in the live broadcast picture.

2. The method of claim 1, wherein the live view further displays a hotspot display control, the method further comprising, prior to presenting at least one visual hotspot in the live view in response to the hotspot display instruction triggered for the live view:

and responding to the trigger operation aiming at the hot zone display control, and obtaining the hot zone display instruction.

3. The method of claim 1, wherein the method further comprises:

carrying out object identification on the live broadcast picture to obtain a position area of each recommended object in the live broadcast picture;

obtaining a viewer account associated with each of the at least one recommendation object; the association relationship between the recommendation objects and the audience account is established according to the position relationship between the position area of each recommendation object in the live broadcast picture and the eyeball fixation point detected by the terminal equipment when the terminal equipment plays the live broadcast picture by using the audience account;

and marking the related audience accounts in the position area of each recommended object to generate a visual hotspot corresponding to each recommended object.

4. The method of claim 3, wherein obtaining the viewer account associated with each of the at least one recommendation object comprises:

receiving a plurality of groups of incidence relations issued by a background server, wherein each group of incidence relations comprises a recommendation object associated with an audience account;

comparing the recommended object in the multiple groups of incidence relations with the at least one recommended object to determine a viewer account associated with each recommended object in the at least one recommended object.

5. A method as defined in claim 3, wherein at least one visual hotspot is presented in the live view in at least one of:

displaying at least one piece of mark information in the position area of each recommended object, wherein one piece of mark information represents at least one audience account related to the corresponding recommended object;

displaying the number of the audience accounts associated with each recommendation object, wherein the number of the audience accounts is positively correlated with the density of the marking information;

displaying the recommended object with the largest number of the associated audience accounts in a hotspot display style different from that of the rest recommended objects;

the recommendation objects with different associated audience account numbers are displayed in different hotspot display styles;

and the recommended objects with the number of the related audience accounts in different numerical value intervals are displayed in different hotspot display styles.

6. The method of claim 1, wherein the method further comprises:

carrying out object identification on the live broadcast picture to obtain a position area of each recommended object in the live broadcast picture;

acquiring position information of the detected eyeball fixation point on the live broadcast picture;

determining a target recommendation object corresponding to the position information based on the position relation between the position information and the position area of each recommendation object;

and establishing an association relation between the currently used target audience account and the target recommendation object, and uploading the association relation to a background server.

7. The method of any of claims 1-6, wherein after presenting at least one visual hotspot in the live view in response to a hotspot display instruction triggered for the live view, the method further comprises:

receiving a trigger operation for a target visual hotspot of the at least one visual hotspot;

displaying a focusing operation control of a target recommendation object corresponding to the target visual hotspot;

and responding to the trigger operation of the focusing operation control, and amplifying and displaying the target recommendation object.

8. The method of claim 7, wherein in response to a triggering operation on the focus operation control, zooming in on the target recommendation object comprises:

responding to the trigger operation of the focusing operation control, and sending a focusing instruction to connected camera equipment, wherein the focusing instruction is used for indicating the camera equipment to focus on the target recommendation object;

and performing screen display based on the focused screen data transmitted by the image pickup apparatus to display the enlarged target recommendation object.

9. The method of claim 7, wherein after receiving a triggering operation for a target visual hotspot of the at least one visual hotspot, the method further comprises:

displaying an information display control corresponding to the target recommendation object;

and responding to the triggering operation of the information display control, and displaying an information display page of the target recommended object, wherein the information display page displays at least one of object introduction information of the target recommended object and an account identifier of an associated audience account.

10. The method of claim 9, wherein the information display page further displays a first object recommendation control corresponding to the target recommendation object;

the method further comprises:

and responding to the triggering operation performed on the first object recommendation control, and sending the object link address associated with the target recommendation object to the audience account associated with the target recommendation object.

11. The method of claim 9, wherein after displaying an information display page of the target recommendation object in response to a triggering operation performed on the information display control, the method further comprises:

responding to a triggering operation performed on an account identifier of a target audience account in the audience accounts displayed on the information display page, and displaying an instant messaging page which takes the target audience account as a messaging object, wherein the instant messaging page displays a second object recommendation control corresponding to the target recommendation object;

and responding to the triggering operation performed on the second object recommendation control, and sending an object link address associated with the target recommendation object to the target audience account.

12. The method of claim 11, wherein the method further comprises:

responding to a trigger operation performed aiming at the account identifier of the target audience account, and displaying a gaze point track page of the target audience account, wherein the gaze point track page comprises each recommended object corresponding to an eyeball gaze point of the target audience account on corresponding terminal equipment;

and the account identifier of the target audience account is the account identifier displayed on the information display page, or the account identifier displayed on the instant messaging page.

13. The method of claim 12, wherein displaying a point of regard track page for the target viewer account comprises:

sequencing each recommended object according to the eyeball fixation point corresponding to the target audience account and the stay time of each recommended object in the position area, and displaying the fixation point track page based on the sequencing sequence of each recommended object; or,

and sequencing the recommended objects according to the eyeball gaze points corresponding to the target audience accounts and the track sequence in the position areas of the recommended objects, and displaying the gaze point track page based on the sequencing sequence of the recommended objects.

14. The method of any of claims 1 to 6, wherein in response to a hotspot display instruction triggered for the live view, further comprising:

displaying a hot zone closing control;

and hiding the at least one visual hot zone in response to the triggering operation of the hot zone closing control, and returning to display the live broadcast picture.

15. The method according to any one of claims 1 to 6, wherein the live view further displays a showcase page display control of the at least one recommended object;

the method further comprises:

displaying a display page comprising the at least one recommended object in response to a triggering operation performed on the display page display control; a display control for viewing the audience account associated with each recommendation object is displayed in the display page;

and responding to a trigger operation performed on a display control corresponding to the target recommendation object, and displaying an account identifier of a viewer account associated with the target recommendation object.

16. The method of claim 15, wherein displaying an showcase page including the at least one recommended object comprises:

sequencing the at least one recommended object according to the number of the audience accounts respectively associated with the at least one recommended object;

displaying the display page based on the sorted order of the at least one recommended object.

17. A hot zone display device for live video, the device comprising:

the system comprises a picture display unit, a selection unit and a selection unit, wherein the picture display unit is used for displaying a live broadcast picture of a live broadcast room, and the live broadcast picture displays at least one recommended object;

and the hot zone presenting unit is used for responding to a hot zone display instruction triggered by the live broadcast picture, presenting at least one visual hot zone in the live broadcast picture, wherein the visual hot zone is used for representing the number of audiences watching the position area where the corresponding recommended object in the live broadcast picture is located.

18. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor,

the processor when executing the computer program realizes the steps of the method of any of claims 1 to 16.

19. A computer storage medium having computer program instructions stored thereon, wherein,

the computer program instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 16.

20. A computer program product comprising computer program instructions that, when executed,

the computer program instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 16.

Images