Object Recommendation Method, Apparatus, Electronic Device, and Storage Medium

Abstract

The present disclosure provides an object recommendation method, apparatus, electronic device, and storage medium, which relate to the field of computer technologies, and particularly to fields such as the Internet of Things, big data, intelligent search, information flow, etc. The specific implementation solution is as follows: matching the host audio-video information from a live broadcast scenario with the target object audio-video information to obtain a matching result, where the target object audio-video information is the audio-video information of a target object that has opened a virtual co-hosting channel in the live broadcast scenario, and the virtual co-hosting channel is used to collect the target object audio-video information when obtaining the authorization information of the target object; and determining the object to be recommended according to the matching result.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and in particular, to the fields of Internet of Things, big data, intelligent search, information flow, etc. Specifically, it relates to an object recommendation method, apparatus, electronic device, and storage medium. Background Art

[0002] Network interactive live broadcast refers to a network live broadcast containing interactive content, which has experienced a process from early text interaction to voice interaction and then to video interaction. The implementation of network interactive live broadcast first involves the construction of network live broadcast. The general process of network live broadcast includes: on-site audio and video collection, computer publishing, uploading to the server, and client viewing. The vast majority of network interactive live broadcasts are interactions between the audience and the live broadcast site. Summary of the Invention

[0003] The present disclosure provides an object recommendation method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of the present disclosure, there is provided an object recommendation method, including: matching host audio and video information from a live broadcast scenario with target object audio and video information to obtain a matching result, where the target object audio and video information is the audio and video information of a target object that opens a virtual connection channel via the live broadcast scenario, and the virtual connection channel is used to collect the target object audio and video information when obtaining the authorization information of the target object; and determining the object to be recommended according to the matching result.

[0005] According to another aspect of the present disclosure, there is provided an object recommendation apparatus, including: a matching module configured to match host audio and video information from a live broadcast scenario with target object audio and video information to obtain a matching result, where the target object audio and video information is the audio and video information of a target object that opens a virtual connection channel via the live broadcast scenario, and the virtual connection channel is used to collect the target object audio and video information when obtaining the authorization information of the target object; and a first determination module configured to determine the object to be recommended according to the matching result.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the object recommendation method of the present disclosure.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the object recommendation method of the present disclosure.

[0008] According to another aspect of the present disclosure, there is provided a computer program product including a computer program stored on at least one of a readable storage medium and an electronic device. When the computer program is executed by a processor, it implements the object recommendation method of the present disclosure.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0011] Figure 1 Schematically shows an exemplary system architecture to which the object recommendation method and apparatus according to embodiments of the present disclosure can be applied;

[0012] Figure 2 Schematically shows a flowchart of the object recommendation method according to embodiments of the present disclosure;

[0013] Figure 3 Schematically shows a schematic diagram of a live broadcast scenario according to embodiments of the present disclosure;

[0014] Figure 4 Schematically shows a schematic diagram of obtaining object authorization information and object audio-visual information of a first object according to embodiments of the present disclosure;

[0015] Figure 5 Schematically shows a schematic diagram of implementing a real co-hosting interaction process according to embodiments of the present disclosure;

[0016] Figure 6 Schematically shows an architecture diagram of a live broadcast system for object recommendation based on virtual co-hosting according to embodiments of the present disclosure;

[0017] Figure 7 Schematically shows a block diagram of an object recommendation apparatus according to embodiments of the present disclosure; and

[0018] Figure 8 Shows a schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0020] In the technical solution of the present disclosure, the processing of the user's personal information, such as collection, storage, use, processing, transmission, provision, disclosure, and application, complies with the provisions of relevant laws and regulations, takes necessary confidentiality measures, and does not violate public order and good customs.

[0021] In the technical solution of the present disclosure, before obtaining or collecting the user's personal information, the user's authorization or consent is obtained.

[0022] The inventors found that during the interaction process in the live broadcast room, the interaction ability between the audience and the anchor is relatively low, and the activity of the live broadcast room is relatively low. For example, in a fitness / dancing live broadcast room, the offline participation of the audience is very high, but the anchor side does not have a strong perception, and the interaction ability between the anchor and the audience is not high.

[0023] Figure 1 An exemplary system architecture to which the object recommendation method and apparatus according to the embodiments of the present disclosure can be applied is schematically shown.

[0024] It should be noted that Figure 1 The example shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments, or scenarios. For example, in another embodiment, the exemplary system architecture to which the object recommendation method and apparatus can be applied may include a terminal device, but the terminal device can implement the object recommendation method and apparatus provided by the embodiments of the present disclosure without interacting with the server.

[0025] As Figure 1 shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0026] Users can interact with the server 105 via the network 104 using the first terminal device 101, the second terminal device 102, and the third terminal device 103 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (for example only).

[0027] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop portable computers, and desktop computers, etc.

[0028] The server 105 can be a server providing various services, such as a background management server that provides support for the content browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (for example only). The background management server can analyze and process data such as received user requests, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability in traditional physical hosts and VPS services (″Virtual Private Server″, or simply ″VPS″). The server can also be a server of a distributed system, or a server combined with a blockchain.

[0029] It should be noted that the object recommendation method provided by the embodiments of the present disclosure can generally be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, the object recommendation device provided by the embodiments of the present disclosure can also be set in the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0030] Alternatively, the object recommendation method provided by the embodiments of the present disclosure can generally also be executed by the server 105. Correspondingly, the object recommendation device provided by the embodiments of the present disclosure can generally be disposed in the server 105. The object recommendation method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the object recommendation device provided by the embodiments of the present disclosure can also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0031] For example, in a live broadcast scenario, the first terminal device 101, the second terminal device 102, and the third terminal device 103 can obtain the host audio-visual information and the target object audio-visual information from the live broadcast scenario. The target object audio-visual information is the audio-visual information of the target object that opens a virtual co-hosting channel in the live broadcast scenario. The virtual co-hosting channel is used to collect the audio-visual information of the target object when the authorization information of the target object is obtained. Then, the host audio-visual information and the target object audio-visual information from the live broadcast scenario are matched to obtain a matching result, and an object to be recommended is determined according to the matching result. Or a server or a server cluster capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105 analyzes the host audio-visual information and the target object audio-visual information from the live broadcast scenario and realizes the determination of the object to be recommended.

[0032] It should be understood that Figure 1 the numbers of the terminal devices, the network, and the servers in

[0033] Figure 2 are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, the network, and the servers.

[0034] As Figure 2 shown, the method includes operations S210 to S220.

[0035] In operation S210, the host audio-visual information and the target object audio-visual information from the live broadcast scenario are matched to obtain a matching result. The target object audio-visual information is the audio-visual information of the target object that opens a virtual co-hosting channel in the live broadcast scenario. The virtual co-hosting channel is used to collect the audio-visual information of the target object when the authorization information of the target object is obtained.

[0036] In operation S220, an object to be recommended is determined according to the matching result.

[0037] According to an embodiment of the present disclosure, a live broadcast scenario may include an audio or video communication scenario initiated by one or more objects and capable of being watched or interacted with in real time by one or more objects, which may be presented in the form of an online live broadcast. The host audio-visual information may include at least one of the following information of the object initiating the live broadcast in the live broadcast scenario: audio information, video information, etc. The target object authorization information may include object identification authorization information and at least one of the following: audio authorization information, video authorization information, etc., and is not limited thereto. The target object audio-visual information may include at least one of the following information of the user or other objects participating in the live broadcast scenario: audio information, video information, etc.

[0038] Figure 3 A schematic diagram of a live broadcast scenario according to an embodiment of the present disclosure is schematically shown.

[0039] As Figure 3 shown, the live broadcast scenario 300 may include a first host terminal 310 for initiating a live broadcast and a first object terminal 320 for watching the live broadcast. The first host terminal 310 may include a first host live broadcast interface 311. The first object terminal 320 may include a user viewing interface 321. The first host terminal 310 may collect the host audio-visual information of the host under the condition of obtaining the host authorization, and display the collected host audio-visual information on the first host live broadcast interface 311. The first object terminal 320 may pull the host audio-visual information of the already broadcast live broadcast and display the pulled host audio-visual information on the user viewing interface 321 for the object to watch.

[0040] It should be understood that Figure 3 the numbers of the host terminals and object terminals in are merely illustrative. According to the implementation requirements, there may be any number of host terminals and object terminals. Both the host terminal and the object terminal may be implemented using mobile phones, tablet computers, laptop computers, desktop computers, and other electronic devices, etc.

[0041] According to an embodiment of the present disclosure, a virtual co-hosting channel may establish a live broadcast interaction in the live broadcast scenario that is imperceptible to the host side and perceptible to the object side for the objects participating in the live broadcast interaction. The object that enables the virtual co-hosting channel may view the host audio-visual information and the target object audio-visual information on the user viewing interface of the live broadcast scenario, realizing perceptibility on the object side. Only the host audio-visual information may be displayed on the host live broadcast interface of the live broadcast scenario, without displaying the target object audio-visual information, realizing imperceptibility on the host side. Under the condition of obtaining the target object authorization information based on the virtual co-hosting channel, the target object audio-visual information in the live broadcast scenario may be collected during the live broadcast interaction.

[0042] It should be noted that objects that have not enabled the virtual co-hosting channel can also view the audio and video information of the host in the live broadcast scenario, but cannot participate in the live broadcast interaction process and will not generate collectible audio and video information in the live broadcast scenario.

[0043] According to an embodiment of the present disclosure, the matching result may include a result representing the similarity degree between the host's audio and video information and the target object's audio and video information, or may include a result representing the matching degree between the host's audio and video information and the target object's audio and video information when the host's audio and video information is different from the target object's audio and video information.

[0044] According to an embodiment of the present disclosure, based on the matching result, an object corresponding to the target object's audio and video information whose similarity degree or matching degree with the host's audio and video information meets a preset range can be determined as the object to be recommended. The preset range may include at least one of the following: less than a first threshold, greater than a second threshold, and between a third threshold and a fourth threshold. The first threshold is less than the second threshold.

[0045] Through the above embodiments of the present disclosure, by matching the host's audio and video information and the target object's audio and video information in the live broadcast scenario, the potential information exchange between the host and the user in the live broadcast scenario can be increased. By determining the object to be recommended according to the matching result, the potential interaction ability between the host and the target object in the live broadcast scenario can be improved, and the user activity in the live broadcast scenario can be enhanced from the underlying implementation.

[0046] The following further describes the Figure 2 method shown with specific embodiments.

[0047] According to an embodiment of the present disclosure, before performing operation S210, the target object's audio and video information may be obtained first. The method for obtaining the audio and video information of the object participating in the live broadcast scenario may include: when it is detected that a first object enters the live broadcast scenario, in response to receiving an instruction indicating that the host enables the imitation function, a first virtual co-hosting instruction for enabling the virtual co-hosting channel is generated on the viewing interface of the first object in the live broadcast scenario. In response to determining that the first object executes the first virtual co-hosting instruction, the object authorization information and the object's audio and video information of the first object are obtained.

[0048] According to an embodiment of the present disclosure, the first object may include any user or other object having the need and ability to watch the live broadcast. The imitation function can be enabled by the host in the host terminal in the live broadcast scenario and can be used to support users to imitate the host in the live broadcast scenario and output the imitation result. The viewing interface of the first object may represent the user viewing interface of the object terminal used by the first object. The first virtual co-hosting instruction can be transmitted to the viewing interface of the first object, and the first object can select to execute or not execute the first virtual co-hosting instruction on the viewing interface of the first object.

[0049] According to an embodiment of the present disclosure, after the host starts a live broadcast, a host live broadcast interface capable of real-time displaying the host's audio and video information can be generated at the host side, and the host's audio and video information can be broadcast in the live broadcast scenario in the form of a live stream. When it is detected that the first object pulls the live stream, the first object viewing interface of the object side used by the first object can display the host's audio and video information in real time, and it can be determined that the first object enters the live broadcast scenario.

[0050] Figure 4 A schematic diagram showing the acquisition of the object authorization information and object audio and video information of the first object according to an embodiment of the present disclosure is schematically shown.

[0051] As Figure 4 As shown, the live broadcast scenario 400 includes a second host side 410 for initiating a live broadcast and a second object side 420 used by the first object that has joined the live broadcast scenario 400. The second host side 410 includes a second host live broadcast interface 411, and the second host live broadcast interface 411 may include an imitation button 412. The second object side 420 may include a first object viewing interface 421. The host's audio and video information can be displayed in both the second host live broadcast interface 411 and the first object viewing interface 421.

[0052] According to an embodiment of the present disclosure, when the host using the second host side 410 clicks the imitation button 412 in the second host live broadcast interface 411, a first virtual connection instruction for opening a virtual connection channel can be generated at the object side (such as the second object side 420) in the live broadcast scenario. The first virtual connection instruction can be displayed in the form of a connection button on the first object viewing interface 421 of the second object side 420, such as the connection button 422 in the first object viewing interface 421. The first object can click the connection button 422 to open the virtual connection channel between the second host side 410 and the second object side 420, and a virtual connection result 430 can be obtained. The virtual connection result 430 can indicate that after the virtual connection channel between the second host side 410 and the second object side 420 is opened, the second host side 410 can only display the host's audio and video information in the second host live broadcast interface 411, and the second object side 420 can display the host's audio and video information and the first object's audio and video information in the first object viewing interface 421.

[0053] According to an embodiment of the present disclosure, when the first object clicks the co-host button 422, a first prompt message 423 may be generated on the first object viewing interface 421. The first prompt message 423 may include selectable object authorization information, as well as an agree option and a disagree option. The selectable object authorization information may include allowing the reading of object identification information, allowing the reading of object audio information, allowing the reading of object video information, etc., and is not limited thereto. After selecting the corresponding object authorization information and receiving an operation of selecting the agree option, a virtual co-host channel may be opened, and object audio-visual information that is authorized by the first object to be read may be obtained based on the second object end 420.

[0054] It should be noted that, among the selectable object authorization information, information such as allowing the reading of object identification information, allowing the reading of object audio information, and allowing the reading of object video information may be default selected. The first object may directly click the agree option to obtain the object authorization information of the first object. The selected state of allowing the reading of object identification information may not be changeable. The selected states of allowing the reading of object audio information and allowing the reading of object video information may be changed to an unselected state according to the actual needs of the first object.

[0055] Through the above embodiments of the present disclosure, a mimicry function that supports users to mimic the host can be implemented based on a virtual co-host channel in a live broadcast scenario. By obtaining user audio-visual information during this process, it is beneficial to achieve real-time matching of user audio-visual information and host audio-visual information, and improve the user interaction ability in the live broadcast scenario.

[0056] According to an embodiment of the present disclosure, the method for obtaining object audio-visual information may further include: when it is detected that the second object enters the live broadcast scenario, in response to receiving an instruction indicating that the host activates the mimicry function, a countdown message and a second virtual co-host instruction for opening a virtual co-host channel are generated on the second object viewing interface in the live broadcast room. In response to determining that the second object executes the second virtual co-host instruction within the time period corresponding to the countdown message, the object authorization information and object audio-visual information of the second object are obtained.

[0057] It should be noted that the second object, the second object viewing interface, and the second virtual co-host instruction may have the same or similar features as the aforementioned first object, the first object viewing interface, and the first virtual co-host instruction, and will not be elaborated here.

[0058] According to an embodiment of the present disclosure, the countdown information can be used to control the valid time of the second virtual co-hosting instruction, which may indicate that the second virtual co-hosting instruction is only valid within the time period corresponding to the countdown information. The second object can control the object terminal to execute the second virtual co-hosting instruction within the valid time corresponding to the countdown information, open the virtual co-hosting channel, and obtain the object authorization information and object audio-video information of the second object. When the countdown ends and no operation to execute the second virtual co-hosting instruction is received, the second object cannot open the virtual co-hosting channel and cannot participate in the imitation process.

[0059] According to an embodiment of the present disclosure, the process of obtaining the object authorization information and object audio-video information of the second object is basically the same as the Figure 4 process shown. The difference is that in this embodiment, when receiving an instruction indicating that the host starts the imitation function, a countdown information and a second virtual co-hosting instruction can be generated simultaneously on the viewing interface of the second object. The second object needs to execute the second virtual co-hosting instruction within the time period corresponding to the countdown information to participate in the imitation process.

[0060] Through the above embodiments of the present disclosure, countdown information can be set for the process of opening the virtual co-hosting channel, which is beneficial to improving the integrity of the imitation process, especially applicable to live broadcast scenarios with high requirements for participation integrity, and can effectively improve the live broadcast interaction effect in such scenarios.

[0061] According to an embodiment of the present disclosure, after obtaining the host audio-video information and the target object audio-video information based on the foregoing method, the above operation S210 can be executed. When the obtained target object audio-video information only includes the target object voice information, the above operation S210 can include: obtaining the host voice information according to the host audio-video information. Performing real-time matching on the host voice information and the target object voice information to obtain a voice matching result.

[0062] According to an embodiment of the present disclosure, when the obtained target object authorization information only includes object identifier authorization information that allows reading of object identifier information and audio authorization information that allows reading of object audio information, the obtained target object audio-visual information may only include target object voice information. The host voice information and the target object voice information may each include at least one of voice content information, voice print information, voice timbre information, etc., and is not limited thereto. Real-time matching of the host voice information and the target object voice information may include at least one of the following: Matching the voice content information of the host voice information and the target object voice information respectively to obtain a voice content matching result. Matching the voice print information of the host voice information and the target object voice information respectively to obtain a voice print matching result. Matching the voice timbre information of the host voice information and the target object voice information respectively to obtain a voice timbre matching result, etc. And is not limited thereto. According to at least one of the voice content matching result, the voice print matching result, the voice timbre matching result, etc., the voice matching result may be determined.

[0063] According to an embodiment of the present disclosure, real-time matching of the host voice information and the target object voice information may be performed to implement a voice imitation function. The voice matching result may include a voice similarity degree and a voice matching degree. For example, when at least one of the voice content, voice print, voice timbre, etc. of the host voice information and the target object voice information is the same or similar, there may be a high similarity degree between the host voice information and the target object voice information. For example, when the host voice information may be the previous line of lyrics information and the target object voice information may be the next line of lyrics information, there may be a high matching degree between the host voice information and the target object voice information. After obtaining the voice matching result according to the voice similarity degree or the voice matching degree, the object to be recommended during the voice imitation process may be determined according to the voice matching result.

[0064] Through the above embodiments of the present disclosure, the voice imitation function may be implemented in a live broadcast scenario. By performing real-time matching of the host voice information and the target object voice information in the live broadcast scenario and obtaining the voice matching result, the potential information exchange between the host and the user in the live broadcast scenario may be increased, and the user interaction ability during the voice imitation process may be improved.

[0065] According to an embodiment of the present disclosure, when the obtained target object audio-visual information only includes target object action information, the above operation S210 may include: obtaining host action information according to the host audio-visual information. Performing real-time matching of the host action information and the target object action information to obtain an action matching result.

[0066] According to an embodiment of the present disclosure, in the case where the obtained target object authorization information only includes object identification authorization information that permits reading of object identification information and video authorization information that permits reading of object video information, the obtained target object audio-visual information may include target object action information.

[0067] According to an embodiment of the present disclosure, the host action information and the target object action information may be matched in real time to implement an action imitation function. The action matching result may characterize the similarity degree of the object's imitation of the host, and is not limited thereto.

[0068] For example, in scenarios such as fitness and dancing, the object joining the live broadcast scene may imitate the actions of the host. By enabling the virtual connection channel, obtaining the object identification authorization information and the video authorization information, the target object action information can be collected. By performing real-time matching on the target object action information and the host action information, the similarity degree of imitation can be obtained. After obtaining the action matching result based on the similarity degree of imitation, the object to be recommended during the action imitation process can be determined according to the action matching result.

[0069] Through the above embodiments of the present disclosure, the action imitation function can be implemented in the live broadcast scene. By performing real-time matching on the host action information and the target object action information in the live broadcast scene and obtaining the action matching result, the potential information exchange between the host and the user in the live broadcast scene can be increased, and the user interaction ability during the action imitation process can be improved.

[0070] According to an embodiment of the present disclosure, in the case where the obtained target object audio-visual information includes target object voice information and target object action information, the above operation S210 may further include: obtaining the host voice information and the host action information according to the host audio-visual information. Performing real-time matching on the host voice information and the target object voice information to obtain a voice matching result. Performing real-time matching on the host action information and the target object action information to obtain an action matching result. Obtaining a target matching result for determining the object to be recommended according to at least one of the voice matching result and the action matching result.

[0071] Through the above embodiments of the present disclosure, the multi-functional imitation function can be implemented in the live broadcast scene. By performing real-time matching on the host audio-visual information and the target object audio-visual information in the live broadcast scene and obtaining the matching result, the potential information exchange between the host and the user in the live broadcast scene can be increased, and the user interaction ability in the live broadcast scene can be improved.

[0072] According to an embodiment of the present disclosure, the above operation S220 may include: determining the matching object audio-visual information whose matching degree with the host audio-visual information is greater than a preset threshold according to the matching result. Determining the target object corresponding to the matching object audio-visual information as the object to be recommended.

[0073] According to an embodiment of the present disclosure, the matching degree may include the above similarity degree or matching degree. The preset threshold may be preset by the live broadcast system in advance, or may be custom-set and adjusted by the anchor, which is not limited herein. In this embodiment, an object with a better imitation effect may be determined as the object to be recommended according to whether the matching degree is greater than the preset threshold.

[0074] Through the above embodiments of the present disclosure, by determining an object with a high matching degree with the anchor's audio-visual information as the object to be recommended, the user interaction ability can be effectively improved, and the activity of the live broadcast scenario can be increased.

[0075] According to an embodiment of the present disclosure, after obtaining the matching result, the above object recommendation method may further include: determining the first object-to-be-recommended authorization information of the object to be recommended. According to the first object-to-be-recommended authorization information, the object-to-be-recommended identification information of the object to be recommended is sent to the anchor live broadcast interface of the live broadcast scenario, so as to facilitate the real connection and interaction between the anchor in the live broadcast scenario and the object to be recommended.

[0076] According to an embodiment of the present disclosure, the first object-to-be-recommended authorization information may include object-to-be-recommended identification authorization information. The object-to-be-recommended identification information may include the object's real ID, object's anonymous ID, etc., and is not limited thereto. After determining the object to be recommended, when obtaining the object-to-be-recommended authorization information of the object to be recommended, the object-to-be-recommended identification information of the object to be recommended may be obtained, and the object-to-be-recommended identification information may be sent to the anchor live broadcast interface. The anchor may select one or more objects for real connection and interaction according to the object-to-be-recommended identification information recommended on the anchor live broadcast interface.

[0077] Through the above embodiments of the present disclosure, by sending the object-to-be-recommended identification information to the anchor live broadcast interface, providing an opportunity for the object to be recommended to have real connection and interaction with the anchor, the user interaction ability in the live broadcast scenario can be further improved, and the activity of the live broadcast room can be effectively increased.

[0078] According to an embodiment of the present disclosure, sending the object-to-be-recommended identification information of the object to be recommended to the anchor live broadcast interface of the live broadcast scenario according to the first object-to-be-recommended authorization information may include: in response to receiving an instruction indicating that the anchor ends the imitation function, according to the first object-to-be-recommended authorization information, sending at least one of the matching result related to the object to be recommended and the first object-to-be-recommended audio-visual information and the object-to-be-recommended identification information to the anchor live broadcast interface.

[0079] According to an embodiment of the present disclosure, the first object to be recommended authorization information may further include at least one of the following: historical audio authorization information, historical video authorization information, real-time audio authorization information, real-time video authorization information, etc., and is not limited thereto. The matching result may be represented by text information indicating matching or non-matching, or may be represented by digital information characterizing the matching degree, and is not limited thereto. The first object to be recommended audio-visual information may include at least one of the following: historical audio information and historical video information of the object to be recommended during the process of participating in the imitation, real-time audio information and real-time video information of the object to be recommended, etc.

[0080] According to an embodiment of the present disclosure, the host can initiate an instruction to end the imitation on the host live broadcast interface. In response to determining that the object end has received the instruction, according to the first object to be recommended authorization information, one or more of the matching result, historical audio information, historical video information, real-time audio information, real-time video information, and the object to be recommended identification information can be sent to the user viewing interface and the host live broadcast interface for the host or the host and other objects participating in the live broadcast scenario to view.

[0081] Through the above embodiments of the present disclosure, the relevant information of the object to be recommended can be sent to the host live broadcast interface, enriching the live broadcast content of the live broadcast scenario and facilitating increasing the activity of the live broadcast scenario.

[0082] According to an embodiment of the present disclosure, the above object recommendation method may further include: in response to determining that the object to be recommended accepts a real connection request initiated by the host of the live broadcast scenario, obtaining the second object to be recommended authorization information and the second object to be recommended audio-visual information of the object to be recommended. According to the second object to be recommended authorization information, the second object to be recommended audio-visual information is sent to the host live broadcast interface of the live broadcast scenario.

[0083] It should be noted that the second object to be recommended authorization information may have the same or similar characteristics as the first object to be recommended authorization information, and the second object to be recommended audio-visual information may have the same or similar characteristics as the first object to be recommended audio-visual information, which will not be elaborated here.

[0084] According to an embodiment of the present disclosure, the host can select a target object to be recommended for interaction according to the object recommended in the host live broadcast interface, and can initiate a real connection request to the selected target object to be recommended on the host live broadcast interface. This request can be sent to the user viewing interface of the target object to be recommended. The target object to be recommended can select to accept or not accept this real connection request on this user viewing interface.

[0085] It should be noted that real co-hosting interaction can establish a live interaction that is perceptible to both the host side and the object side for the objects participating in the live interaction in the live broadcast scenario. For the objects that join the real co-hosting interaction, the host's audio-visual information and the target object's audio-visual information can be viewed on both the host's live broadcast interface and the user's viewing interface in the live broadcast scenario. And the interface displaying the host's audio-visual information and the target object's audio-visual information can be viewed by other users participating in the live broadcast scenario.

[0086] According to an embodiment of the present disclosure, in the case where it is determined that the target recommended object chooses to accept the real co-hosting request, one or more of the matching result, historical audio information, historical video information, real-time audio information, real-time video information of the target recommended object, and the object identification information of the target recommended object can be sent to the host's live broadcast interface for the host and other objects participating in the live broadcast scenario to view in real time according to the second recommended object authorization information.

[0087] Figure 5 Schematically shows a schematic diagram of the process of realizing real co-hosting interaction according to an embodiment of the present disclosure.

[0088] As Figure 5 shown, the live broadcast scenario 500 includes a third host terminal 510 for initiating a live broadcast and a third object terminal 520 used by a certain third object determined in the live broadcast scenario 500. The third host terminal 510 includes a third host live broadcast interface 511. The third host live broadcast interface 511 may include an interaction button 512, and may display the host's audio-visual information and the object identification information and corresponding matching results of the third object recommended for the host's audio-visual information, such as recommended id1: matching degree 95%, recommended id2: matching degree 90%, recommended id3: matching degree 10%, etc. The third object terminal 520 may be, for example, the object terminal used by the third object with the object identification information of id1. The third object terminal 520 may include a third object viewing interface 521. The third object viewing interface 521 may display the host's audio-visual information and the third object's audio-visual information.

[0089] According to an embodiment of the present disclosure, when a host who is live streaming using the third host terminal 510 clicks the interaction button 512 to initiate a real connection request to an object with object identification information of id1, an instruction for accepting or rejecting the real connection request can be generated at the third object terminal 520. The instruction can be displayed in the form of an accept button and a reject button on the third object viewing interface 521 of the third object terminal 520, such as the accept button 522 and the reject button 523 in the third object viewing interface 521. The object with object identification information of id1 can click the reject button 523 to reject the real connection request. The object with object identification information of id1 can also click the accept button 522 to accept the real connection request and obtain a real connection result 530. The real connection result 530 can indicate that during the real connection interaction process, the third host terminal 510 can display the host audio-visual information and the third object audio-visual information of the third object that accepts the real connection request in the third host live streaming interface 511, and the display content in the third object viewing interface 521 of the third object terminal 520 can remain unchanged, that is, the host audio-visual information and the third object audio-visual information can be displayed.

[0090] According to an embodiment of the present disclosure, when the object with object identification information of id1 clicks the accept button 522, a second prompt message 524 can be generated in the third object viewing interface 521. The second prompt message 524 can include selectable object authorization information, as well as an agree option and a disagree option. The selectable object authorization information can include allowing reading of object identification information, allowing reading of object audio information, allowing reading of object video information, etc., and is not limited thereto. After selecting the corresponding object authorization information and receiving an operation of selecting the agree option, the process of the real connection interaction characterized by the real connection result 530 can be entered.

[0091] It should be noted that in the selectable object authorization information, the selected and unselected states and the changeable and unchangeable states of information such as allowing reading of object identification information, allowing reading of object audio information, allowing reading of object video information, etc. have been described in the foregoing embodiments and will not be elaborated herein.

[0092] Through the above embodiments of the present disclosure, objects for interacting with the host can be recommended for the live streaming scenario according to the matching result. In this way, the interactivity in the live streaming scenario can be effectively enhanced, and the user activity in the live streaming scenario can be improved.

[0093] Figure 6 Schematically shows an architecture diagram of a live streaming system for object recommendation based on virtual connection according to an embodiment of the present disclosure.

[0094] As Figure 6As shown in the figure, the host can initiate a live broadcast using the first client 610, and the live audio and video information 611 of the initiated live broadcast can be transmitted in the form of a live stream based on the stream engine module 620. The object that needs to watch the live broadcast can use the second client 630 to pull the live stream based on the stream engine module 620. After the object using the second client 630 enables the virtual live channel in the second client 630, the second client 630 can collect the object audio and video information 631 of the object. The AI platform 640 can match the object audio and video information 631 and the live audio and video information 611 pulled based on the stream engine module 620 to obtain a matching result 650. The matching result 650 can be fed back to the first client 610 and the second client 620 through the live broadcast background.

[0095] According to an embodiment of the present disclosure, referring to Figure 6 As shown in the figure, the AI platform 640 may include a first action recognition engine 641, a second action recognition engine 642, a first speech recognition engine 643, a second speech recognition engine 644, a first other engine 645, a second other engine 646, etc., and is not limited thereto. The first action recognition engine 641 can be used to obtain the host action information from the host audio and video information. The second action recognition engine 642 can be used to obtain the object action information from the object audio and video information. The first speech recognition engine 643 can be used to obtain the host speech information from the host audio and video information. The second speech recognition engine 644 can be used to obtain the object speech information from the object audio and video information. Both the first speech recognition engine 643 and the second speech recognition engine 644 may include at least one of functions such as content recognition, voiceprint recognition, and timbre recognition. By obtaining the information of each modality of the host side and the object side based on these engines and then matching the information of the same modality, the matching result 650 can be obtained.

[0096] According to an embodiment of the present disclosure, the above object recommendation method can be executed by the AI platform 640.

[0097] Through the above embodiments of the present disclosure, by enabling virtual video connection, real-time imitation can be performed during the host's live broadcast. During the imitation process, relevant AI technologies such as video recognition and speech recognition are combined to score the matching degree, automatically identify the objects that meet the matching conditions and recommend them to the host, which can improve the interaction ability between the audience and the host and enhance the activity of the live broadcast room.

[0098] Figure 7 Schematically shows a block diagram of an object recommendation device according to an embodiment of the present disclosure.

[0099] As Figure 7 shown, the object recommendation device 700 includes a matching module 710 and a first determination module 720.

[0100] A matching module 710 is configured to match the host audio-visual information from a live broadcast scenario with the target object audio-visual information to obtain a matching result, where the target object audio-visual information is the audio-visual information of a target object that has opened a virtual connection channel in the live broadcast scenario, and the virtual connection channel is used to collect the target object audio-visual information when the target object authorization information is obtained.

[0101] A first determination module 720 is configured to determine the object to be recommended according to the matching result.

[0102] According to an embodiment of the present disclosure, the target object audio-visual information includes target object voice information. The matching module includes a first obtaining unit and a first matching unit.

[0103] The first obtaining unit is configured to obtain host voice information according to the host audio-visual information.

[0104] The first matching unit is configured to perform real-time matching on the host voice information and the target object voice information to obtain a voice matching result.

[0105] According to an embodiment of the present disclosure, the target object audio-visual information includes target object action information. The matching module includes a second obtaining unit and a second matching unit.

[0106] The second obtaining unit is configured to obtain host action information according to the host audio-visual information.

[0107] The second matching unit is configured to perform real-time matching on the host action information and the target object action information to obtain an action matching result.

[0108] According to an embodiment of the present disclosure, the first determination module includes a first determination unit and a second determination unit.

[0109] The first determination unit is configured to determine the matching object audio-visual information whose matching degree with the host audio-visual information is greater than a preset threshold according to the matching result.

[0110] The second determination unit is configured to determine the target object corresponding to the matching object audio-visual information as the object to be recommended.

[0111] According to an embodiment of the present disclosure, the object recommendation device further includes a first generation module and a first acquisition module.

[0112] The first generation module is configured to, when detecting that a first object enters the live broadcast scenario, in response to receiving an instruction indicating that the host enables an imitation function, generate a first virtual connection instruction for opening a virtual connection channel on the first object viewing interface in the live broadcast scenario.

[0113] The first acquisition module is configured to acquire the object authorization information and object audio-visual information of the first object in response to determining that the first object executes the first virtual co-hosting instruction.

[0114] According to an embodiment of the present disclosure, the object recommendation device further includes a second generation module and a second acquisition module.

[0115] The second generation module is configured to, when detecting that a second object enters the live scene, in response to receiving an instruction indicating that the host enables the imitation function, generate countdown information and a second virtual co-hosting instruction for opening a virtual co-hosting channel on the viewing interface of the second object in the live room.

[0116] The second acquisition module is configured to acquire the object authorization information and object audio-visual information of the second object in response to determining that the second object executes the second virtual co-hosting instruction within the time period corresponding to the countdown information.

[0117] According to an embodiment of the present disclosure, the object recommendation device further includes a second determination module and a first sending module.

[0118] The second determination module is configured to determine the first recommended object authorization information of the object to be recommended.

[0119] The first sending module is configured to send the recommended object identification information of the object to be recommended to the host live interface of the live scene according to the first recommended object authorization information, so as to facilitate real co-hosting interaction between the host in the live scene and the object to be recommended.

[0120] According to an embodiment of the present disclosure, the first sending module includes a sending unit.

[0121] The sending unit is configured to, in response to receiving an instruction indicating that the host ends the imitation function, send at least one of the matching result related to the object to be recommended and the first recommended object audio-visual information and the recommended object identification information to the host live interface according to the first recommended object authorization information.

[0122] According to an embodiment of the present disclosure, the object recommendation device further includes a third acquisition module and a second sending module.

[0123] The third acquisition module is configured to acquire the second recommended object authorization information and the second recommended object audio-visual information of the object to be recommended in response to determining that the object to be recommended accepts a real co-hosting request initiated by the host in the live scene.

[0124] The second sending module is configured to send the second recommended object audio-visual information to the host live interface of the live scene according to the second recommended object authorization information.

[0125] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0126] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the object recommendation method of the present disclosure.

[0127] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the object recommendation method of the present disclosure.

[0128] According to an embodiment of the present disclosure, a computer program product includes a computer program, the computer program is stored on at least one of a readable storage medium and an electronic device, and the computer program implements the object recommendation method of the present disclosure when executed by a processor.

[0129] Figure 8 A schematic block diagram of an exemplary electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0130] As Figure 8 shown, the device 800 includes a computing unit 801, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0131] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as a keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as a disk, optical disc, etc.; and communication unit 809, such as a network card, modem, wireless communication transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0132] Computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 801 executes the various methods and processes described above, such as the object recommendation method. For example, in some embodiments, the object recommendation method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the object recommendation method described above can be executed. Alternatively, in other embodiments, computing unit 801 can be configured to execute the object recommendation method in any other suitable way (e.g., by means of firmware).

[0133] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on the remote machine or server.

[0135] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] In order to provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0137] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0138] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, or a server of a distributed system, or a server incorporating a blockchain.

[0139] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0140] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. An object recommendation method, including: matching the host audio - video information from the live - broadcast scenario with the target object audio - video information to obtain a matching result, where the target object audio - video information is the audio - video information of the target object that opens a virtual connection channel through the live - broadcast scenario, and the virtual connection channel is used to collect the target object audio - video information when the target object authorization information is obtained; and determining the object to be recommended according to the matching result; and when it is detected that a first object enters the live - broadcast scenario, in response to receiving an instruction indicating that the host activates the imitation function, generating a first virtual connection instruction for opening the virtual connection channel on the viewing interface of the first object in the live - broadcast scenario; and in response to determining that the first object executes the first virtual connection instruction, obtaining the object authorization information and object audio - video information of the first object.

2. The method according to claim 1, wherein, the target object audio - video information includes target object voice information; the matching the host audio - video information from the live - broadcast scenario with the target object audio - video information to obtain a matching result includes: obtaining host voice information according to the host audio - video information; and performing real - time matching on the host voice information and the target object voice information to obtain a voice matching result.

3. The method according to claim 1 or 2, wherein, the target object audio - video information includes target object action information; the matching the host audio - video information from the live - broadcast scenario with the target object audio - video information to obtain a matching result includes: obtaining host action information according to the host audio - video information; and performing real - time matching on the host action information and the target object action information to obtain an action matching result.

4. The method according to any one of claims 1 - 3, wherein, the determining the object to be recommended according to the matching result includes: determining the matching object audio - video information whose matching degree with the host audio - video information is greater than a preset threshold according to the matching result; and determining the target object corresponding to the matching object audio - video information as the object to be recommended.

5. The method according to any one of claims 1 - 4, further including: when it is detected that a second object enters the live - broadcast scenario, in response to receiving an instruction indicating that the host activates the imitation function, generating countdown information and a second virtual connection instruction for opening the virtual connection channel on the viewing interface of the second object in the live - broadcast scenario; and in response to determining that the second object executes the second virtual connection instruction within the time period corresponding to the countdown information, obtaining the object authorization information and object audio - video information of the second object.

6. The method according to any one of claims 1 - 5, further including: determining the first recommended object authorization information of the object to be recommended; sending the recommended object identification information of the object to be recommended to the host live - broadcast interface of the live - broadcast scenario according to the first recommended object authorization information, so as to facilitate real - time connection and interaction between the host in the live - broadcast scenario and the object to be recommended.

7. The method according to claim 6, wherein, sending the identification information of the object to be recommended to the live broadcast interface of the host in the live broadcast scenario according to the authorization information of the first object to be recommended includes: In response to receiving an instruction indicating that the host ends the imitation function, according to the authorization information of the first object to be recommended, sending at least one of the matching result related to the object to be recommended and the audio-visual information of the first object to be recommended and the identification information of the object to be recommended to the live broadcast interface of the host.

8. The method according to any one of claims 1-7, further including: In response to determining that the object to be recommended accepts the real connection request initiated by the host in the live broadcast scenario, obtaining the authorization information of the second object to be recommended and the audio-visual information of the second object to be recommended of the object to be recommended; and According to the authorization information of the second object to be recommended, sending the audio-visual information of the second object to be recommended to the live broadcast interface of the host in the live broadcast scenario.

9. An object recommendation device, including: A matching module, configured to match the audio-visual information of the host in the live broadcast scenario with the audio-visual information of the target object to obtain a matching result, wherein the audio-visual information of the target object is the audio-visual information of the target object that opens a virtual connection channel in the live broadcast scenario, and the virtual connection channel is used to collect the audio-visual information of the target object when the authorization information of the target object is obtained; and A first determination module, configured to determine the object to be recommended according to the matching result; and A first generation module, configured to, in response to receiving an instruction indicating that the host enables the imitation function when detecting that a first object enters the live broadcast scenario, generate a first virtual connection instruction for opening the virtual connection channel in the viewing interface of the first object in the live broadcast scenario; and a first acquisition module, configured to, in response to determining that the first object executes the first virtual connection instruction, obtain the object authorization information and the object audio-visual information of the first object.

10. The device according to claim 9, wherein, The audio-visual information of the target object includes the voice information of the target object; the matching module includes: A first obtaining unit, configured to obtain the voice information of the host according to the audio-visual information of the host; and A first matching unit, configured to perform real-time matching on the voice information of the host and the voice information of the target object to obtain a voice matching result.

11. The device according to claim 9 or 10, wherein, The audio-visual information of the target object includes the action information of the target object; the matching module includes: A second obtaining unit, configured to obtain the action information of the host according to the audio-visual information of the host; and A second matching unit, configured to perform real-time matching on the action information of the host and the action information of the target object to obtain an action matching result.

12. The device according to any one of claims 9-11, wherein, The first determination module includes: A first determination unit, configured to determine the matching object audio-visual information with a matching degree greater than a preset threshold with the audio-visual information of the host according to the matching result; and A second determination unit, configured to determine, as the object to be recommended, a target object corresponding to the audio-visual information of the matching object.

13. The apparatus according to any one of claims 9-12, further comprising: A second generation module, configured to, when detecting that a second object enters the live scene, in response to receiving an instruction indicating that the host enables the imitation function, generate countdown information and a second virtual connection instruction for enabling the virtual connection channel on a viewing interface of the second object in the live scene; and A second acquisition module, configured to, in response to determining that the second object executes the second virtual connection instruction within a time period corresponding to the countdown information, acquire object authorization information and object audio-visual information of the second object.

14. The apparatus according to any one of claims 9-13, further comprising: A second determination module, configured to determine first recommended object authorization information of the object to be recommended; A first sending module, configured to send, according to the first recommended object authorization information, identification information of the object to be recommended to a live broadcast interface of the host in the live scene, so that the host in the live scene and the object to be recommended can perform real connection interaction.

15. The apparatus according to claim 14, wherein the first sending module comprises: A sending unit, configured to, in response to receiving an instruction indicating that the host ends the imitation function, send at least one of a matching result related to the object to be recommended and first recommended object audio-visual information and the identification information of the object to be recommended to the host live broadcast interface according to the first recommended object authorization information.

16. The apparatus according to any one of claims 9-15, further comprising: A third acquisition module, configured to, in response to determining that the object to be recommended accepts a real connection request initiated by the host in the live scene, acquire second recommended object authorization information and second recommended object audio-visual information of the object to be recommended; and A second sending module, configured to send the second recommended object audio-visual information to the host live broadcast interface according to the second recommended object authorization information.

17. An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

19. A computer program product, comprising a computer program, the computer program being stored on at least one of a readable storage medium and an electronic device, and the computer program, when executed by a processor, implements the method according to any one of claims 1-8.

Images