WO2023083186A1 - 直播内容的处理方法、电子设备、可读存储介质及计算机程序产品 - Google Patents

直播内容的处理方法、电子设备、可读存储介质及计算机程序产品 Download PDF

Info

Publication number
WO2023083186A1
WO2023083186A1 PCT/CN2022/130672 CN2022130672W WO2023083186A1 WO 2023083186 A1 WO2023083186 A1 WO 2023083186A1 CN 2022130672 W CN2022130672 W CN 2022130672W WO 2023083186 A1 WO2023083186 A1 WO 2023083186A1
Authority
WO
WIPO (PCT)
Prior art keywords
message
target
user
live
video segment
Prior art date
Application number
PCT/CN2022/130672
Other languages
English (en)
French (fr)
Inventor
钟宜峰
吴耀华
李鹏飞
李琳
Original Assignee
咪咕文化科技有限公司
中国移动通信集团有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 咪咕文化科技有限公司, 中国移动通信集团有限公司 filed Critical 咪咕文化科技有限公司
Publication of WO2023083186A1 publication Critical patent/WO2023083186A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21Server components or server architectures
    • H04N21/218Source of audio or video content, e.g. local disk arrays
    • H04N21/2187Live feed
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/235Processing of additional data, e.g. scrambling of additional data or processing content descriptors
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • H04N21/2393Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/435Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/437Interfacing the upstream path of the transmission network, e.g. for transmitting client requests to a VOD server
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • H04N21/478Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting

Definitions

  • the present disclosure relates to the technical field of communication, and in particular, to a method for processing live content, electronic equipment, a readable storage medium, and a computer program product.
  • the user equipment on the live broadcast side can broadcast the program through the live application program (Application, APP), and the user equipment on the audience side can also watch the live broadcast through the live APP. programme.
  • the user equipment on the audience side can communicate and interact with the anchor of the user equipment on the live broadcast side in real time by sending barrage, and the anchor can also select the audience's questions in the barrage to answer in real time.
  • the interaction between the anchor and the audience is mainly realized through the audience's message and the anchor's response.
  • the anchor may miss some messages and the message cannot be effectively answered.
  • the present disclosure provides a processing method, electronic equipment, readable storage medium and computer program product of live content, which solves the problem of low efficiency in the interaction between the audience and the anchor in the current live broadcast scene.
  • embodiments of the present disclosure provide a method for processing live content, which is applied to a server, and the method includes:
  • the target message information matches the first message message processed by the second user, determine the target video segment corresponding to the target message information; 2. Generating a reply from the user to the first message;
  • determining the target video segment corresponding to the target message information includes:
  • the target video segment corresponding to the target message information is determined according to the correspondence between historical message information and historical live video segments.
  • the target video clip corresponding to the target message information before determining the target video clip corresponding to the target message information according to the correspondence between historical message information and historical live video clips, it also includes:
  • the intercepting the target video segment related to the first message information from the live video data includes:
  • a video segment corresponding to the target semantic content is intercepted from the live video data;
  • the video segment corresponding to the content is determined as the target video segment.
  • the target video clip corresponding to the target message information before determining the target video clip corresponding to the target message information according to the correspondence between historical message information and historical live video clips, it also includes:
  • the target video segment is the second user-side terminal intercepted from the live video data and corresponding to the first message message relevant video clips;
  • the corresponding relationship between the first message information and the target video segment is determined as the corresponding relationship between historical message information and historical live video segments.
  • the first user-side device after receiving the target message information sent by the first user-side device, it further includes:
  • the target message information includes N second message messages
  • M pieces of second message messages containing the same content in the N second message messages are merged to obtain a third message message; wherein, M , N is an integer greater than 1, and M ⁇ N;
  • the third message includes message content and the number M of the second message.
  • an embodiment of the present disclosure provides a method for processing live content, which is applied to a first user-side device, and the method includes:
  • the target video segment is when the server matches the target message message with the first message message processed by the second user sent, the target video segment is generated by the reply of the second user to the first message in the historical live broadcast;
  • the playing the target video segment includes:
  • an embodiment of the present disclosure provides a method for processing live content, which is applied to a second user-side device, and the method includes:
  • the intercepting the target video segment related to the first message information from the live video data includes:
  • a video segment corresponding to the target semantic content is intercepted from the live video data, and the A video segment corresponding to the target semantic content is determined to be the target video segment.
  • the method for processing live content further includes:
  • the third message message is obtained after the server merges M pieces of second message messages containing the same content sent by the audience device; wherein, M is greater than an integer of 1;
  • the displaying the third message includes:
  • an embodiment of the present disclosure provides a device for processing live content, which is applied to a server, and the device includes:
  • the first receiving part is configured to receive the target message information sent by the first user-side device in a live broadcast scenario
  • the first processing part is configured to determine the target video segment corresponding to the target message information when the target message information matches the first message information processed by the second user; wherein, the target video segment Generated by the reply of the second user to the first message in the historical live broadcast;
  • the first sending part is configured to send the target video segment to the first user-side device.
  • the first processing portion includes:
  • the first processing part is configured to determine the target video segment corresponding to the target message information according to the corresponding relationship between historical message information and historical live video segments.
  • the device also includes:
  • the acquisition part is configured to acquire the live video data of the second user-side device and the live video data of the first user-side device before determining the target video segment corresponding to the target message information according to the correspondence between historical message information and historical live video segments.
  • the intercepting part is configured to intercept a target video segment related to the first message from the live video data
  • the establishing part is configured to establish a corresponding relationship between historical message information and historical live video segments according to the first message information and the target video segment.
  • the intercepted portion includes:
  • the second processing part is configured to perform semantic analysis processing on the first message to obtain the first semantic content corresponding to the first message;
  • the third processing part is configured to perform speech recognition and semantic analysis processing on the audio data in the live video data, and obtain the second semantic content corresponding to the live video data;
  • the intercepting part is configured to intercept a video segment corresponding to the target semantic content from the live video data when the second semantic content matches the target semantic content related to the first semantic content; A video segment corresponding to the target semantic content is determined as the target video segment.
  • the device also includes:
  • the second receiving part is configured to, before determining the target video segment corresponding to the target message information according to the corresponding relationship between the historical message information and the historical live video segment, receive the first message sent by the second user side device.
  • a target video segment corresponding to the message message wherein, the target video segment is a video segment related to the first message message intercepted by the second user-side terminal from the live video data;
  • the second processing part is configured to determine the corresponding relationship between the first message information and the target video segment as the corresponding relationship between historical message information and historical live video segments.
  • the device also includes:
  • the merging part is configured to, after receiving the target message information sent by the first user-side device, if the target message information includes N pieces of second message information, combine the N pieces of second message information containing M The second message information is merged to obtain the third message information; wherein, M and N are integers greater than 1, and M ⁇ N;
  • the second sending part is configured to send the third message to the second user side device.
  • the third message includes message content and the number M of the second message.
  • an embodiment of the present disclosure provides a device for processing live content, which is applied to a first user-side device, and the device includes:
  • the sending part is configured to send the target message information to the server in the live broadcast scene
  • the receiving part is configured to receive the target video segment sent by the server according to the target message information; wherein, the target video segment is the first message message processed by the server between the target message message information and the second user If they match, the target video segment is generated by the reply of the second user to the first tag message in the historical live broadcast;
  • the playback part is configured to play the target video segment.
  • the playback section includes:
  • the playing part is configured to play the target video segment in the second playing window when the live video data is playing in the first playing window.
  • an embodiment of the present disclosure provides an apparatus for processing live content, which is applied to a second user-side device, and the apparatus includes:
  • the acquisition part is configured to collect live video data and obtain the first message sent by the first user-side device in a live broadcast scene;
  • the intercepting part is configured to intercept a target video segment related to the first message from the live video data
  • the sending part is configured to send the target video segment corresponding to the first message to a server.
  • the intercepted portion includes:
  • the first processing part is configured to perform semantic analysis and processing on the first message to obtain the first semantic content corresponding to the first message;
  • the second processing part is configured to perform speech recognition and semantic analysis processing on the audio data in the live video data, and obtain the second semantic content corresponding to the live video data;
  • the intercepting part is configured to intercept a video segment corresponding to the target semantic content from the live video data when the target semantic content related to the first semantic content is matched from the second semantic content , and determine the video segment corresponding to the target semantic content as the target video segment.
  • the device also includes:
  • the receiving part is configured to receive the third message message sent by the server; wherein, the third message message is obtained after the server merges and processes M pieces of second message messages containing the same content sent by the audience device; Wherein, M is an integer greater than 1;
  • the display part is configured to display the third message information.
  • the display portion includes:
  • the display part is configured to display the message content of the third message message and the number M of second message messages corresponding to the third message message.
  • an embodiment of the present disclosure provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and operable on the processor;
  • the electronic device when the electronic device is a server, when the processor executes the computer program, the steps of the method for processing live content as described in the first aspect above are realized;
  • the electronic device is the first user-side device
  • the processor executes the computer program
  • the steps of the method for processing live content as described in the second aspect above are implemented;
  • the electronic device is the second user-side device
  • the processor executes the computer program
  • the steps of the method for processing live content as described in the third aspect above are implemented.
  • an embodiment of the present disclosure provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above first aspect or the second aspect or the third aspect is realized Steps in the method for processing live content.
  • an embodiment of the present disclosure provides a computer program product, the computer program product includes a computer program or an instruction, and when the computer program or instruction is run on a computer, the computer executes the above first aspect Or the steps of the method for processing live content described in the second aspect or the third aspect.
  • the target message information sent by the first user-side device (such as the audience-side device) is received; match, then determine the target video segment corresponding to the target message information; and send the target video segment to the first user-side device, so that the first user-side device can obtain the relevant reply of its message message in time, And because the target video segment is generated by the reply of the second user to the first message in the historical live broadcast, it can reduce the second user's repeated replies to the same message, and then improve the performance of the audience and the anchor in the live broadcast scene. interaction efficiency.
  • FIG. 1 shows a flowchart of a method for processing live content on the server side of an embodiment of the present disclosure
  • FIG. 2 shows a block diagram of a processing device for live content on the server side of an embodiment of the present disclosure
  • Fig. 3 represents one of the block diagrams of the electronic device of the embodiment of the present disclosure
  • FIG. 4 shows a flowchart of a method for processing live content of a first user-side device according to an embodiment of the present disclosure
  • FIG. 5 shows a block diagram of a method for processing live content of a first user-side device according to an embodiment of the present disclosure
  • FIG. 6 shows the second block diagram of the electronic device according to the embodiment of the present disclosure
  • FIG. 7 shows a flow chart of a method for processing live content of a second user-side device according to an embodiment of the present disclosure
  • Fig. 8 shows a block diagram of a method for processing live content of a second user-side device according to an embodiment of the present disclosure.
  • sequence numbers of the following processes do not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not be implemented in the present disclosure.
  • the implementation of the examples constitutes no limitation. Additionally, the terms “system” and “network” are often used interchangeably herein.
  • B corresponding to A means that B is associated with A, and B can be determined according to A.
  • determining B according to A does not mean determining B only according to A, and B may also be determined according to A and/or other information.
  • the electronic equipment may be a mobile phone (or mobile phone), or other equipment capable of sending or receiving wireless signals, including user equipment, personal digital assistant (Personal Digital Assistant, PDA), wireless modem, wireless communication device, Handheld devices, laptop computers, cordless phones, Wireless Local Loop (WLL) stations, Customer Premise Equipment (CPE) or mobile smart hotspots capable of converting mobile signals to WiFi signals, smart home appliances, or Other devices, servers, etc. that can spontaneously communicate with the mobile communication network without human operation.
  • PDA Personal Digital Assistant
  • WLL Wireless Local Loop
  • CPE Customer Premise Equipment
  • mobile smart hotspots capable of converting mobile signals to WiFi signals, smart home appliances, or Other devices, servers, etc. that can spontaneously communicate with the mobile communication network without human operation.
  • the embodiments of the present disclosure provide a method for processing live content, which solves the problem of inefficiency in the interaction between the audience and the host in the current live broadcast scene.
  • the embodiment of the present disclosure provides a method for processing live content, which is applied to a server, and the method includes:
  • Step 11 In the live broadcast scenario, receive the target message information sent by the first user-side device.
  • the first user can be understood as a user watching the live broadcast, and the first user-side device can also be called a viewer-side device (or viewer device); the first user watches the live broadcast through the first user-side device During the process, a message can be sent through the message function of the live broadcast APP in the first user-side device, so as to realize the interaction with the second user (ie, the live broadcast user, or called the anchor).
  • the first user-side device can also be called a viewer-side device (or viewer device); the first user watches the live broadcast through the first user-side device
  • a message can be sent through the message function of the live broadcast APP in the first user-side device, so as to realize the interaction with the second user (ie, the live broadcast user, or called the anchor).
  • Step 12 If the target message information matches the first message message processed by the second user, determine a target video segment corresponding to the target message information.
  • the target video segment is generated by the second user's reply to the first message in the historical live broadcast.
  • the second user may be understood as a live broadcast user (or called an anchor).
  • the second user-side device that is, the live-streaming device, or called the live-streaming device
  • the server performs voice recognition and semantic analysis on the live broadcast content of the live broadcast user.
  • the target message sent by the first user-side device message and if the target message matches the first message that the second user has processed, the target video segment corresponding to the relevant reply content of the first message can be searched from historical live video data.
  • the matching of the target message information with the first message information that has been processed by the second user may be: the target message information is the first message information that has been processed by the second user.
  • the matching of the target message information with the first message information processed by the second user may also be: the semantic content corresponding to the target message information is the same as the semantic content corresponding to the first message information; wherein, the semantic content
  • the content can be determined by semantic analysis of the message, and the same semantic content can be understood as containing the same/similar keywords (such as "efficacy”, “function”, and “effect” can be understood as similar keywords).
  • the matching of the target message information with the first message information processed by the second user may also be: the target message information contains the same/similar keywords as the first message information, etc., and the embodiment of the present disclosure does not This is the limit.
  • Step 13 Send the target video segment to the first user-side device.
  • the server may send the target video segment to the first user-side device in a video stream manner.
  • the server may also be called a live broadcast platform system.
  • the target message information sent by the first user-side device (such as the audience-side device) is received; match, then determine the target video segment corresponding to the target message information; and send the target video segment to the first user-side device, so that the first user-side device can obtain the relevant reply of its message message in time, and Since the target video segment is generated by the reply of the second user to the first message in the historical live broadcast, it is possible to reduce the second user's repeated replies to the same message, thereby improving the relationship between the audience and the anchor in the live broadcast scene. Interactive efficiency.
  • determining the target video segment corresponding to the target message information includes:
  • the target video segment corresponding to the target message information is determined according to the correspondence between historical message information and historical live video segments.
  • the second user-side device or server performs speech recognition and semantic analysis on the live broadcast content of the live broadcast user, and can create a message for the video clips related to the message information sent by the first user-side device during the live broadcast Correspondence between information and corresponding video clips, and store it as the corresponding relationship between historical message information and historical live video clips, so that when receiving the target message information sent by the first user side device and the historical message information
  • the target video segment corresponding to the target message information can be determined from the historical live video segments, so that the first user-side device can obtain the relevant reply of its message information in time, and reduce the repetition of the same message information by the second user. answer, which in turn improves the interaction efficiency between the audience and the anchor in the live broadcast scene.
  • the method before determining the target video segment corresponding to the target message information according to the correspondence between historical message information and historical live video segments, the method further includes:
  • the sequence relationship between obtaining the live video data of the second user-side device and obtaining the first message information sent by the first user-side device is not limited. Live video data, and then obtain the first message information sent by the first user-side device; or, first obtain the first message message sent by the first user-side device, and then obtain the live video data of the second user-side device; or, The live video data of the second user-side device and the first message information sent by the first user-side device can be acquired simultaneously.
  • the second user-side device can perform real-time speech recognition on the live audio during the live broadcast, and the text result after speech recognition is sent to the server for storage, or the server side can also use the received second user-side device to send Perform speech recognition on the live video data; in this way, the server side can determine according to the first message message sent by the first user-side device and the text result after speech recognition according to the obtained text result after speech recognition and the corresponding live video data.
  • the intercepting the target video segment related to the first message information from the live video data includes:
  • a video segment corresponding to the target semantic content is intercepted from the live video data;
  • the corresponding video segment is determined as the target video segment.
  • the server side can perform speech recognition and semantic analysis (such as using machine reading comprehension analysis, QA model, etc.) for the audio data in the received live video data, and at the same time perform semantic analysis on the first message sent by the first user-side device. Analyze, and combine the results obtained by the semantic analysis of the two to determine which message is being answered in the live video data, as well as the start time point and end time point of the reply, and the reply between the start time point and the end time point
  • the video is edited and saved in the form of a message corresponding to a reply video, that is, the video segment corresponding to the first message is determined, and the corresponding relationship between the two is established and stored in the database, that is, a "standard reply library" is formed.
  • the server can perform text semantic analysis on the target message information.
  • the server side can directly send The standard reply video (i.e. the target video) corresponding to the target message information is sent to the first user side device (such as sending the standard reply video to the first user side device in the form of a video stream), so that the first user side can Know the reply corresponding to its message information in time, avoid the interaction efficiency drop caused by missing relevant message information on the second user side, and also avoid the second user side from repeatedly replying to the same message information, thereby improving the efficiency of the first user side and the second user side. Interaction efficiency on the user side during live broadcast.
  • the method before determining the target video segment corresponding to the target message information according to the correspondence between historical message information and historical live video segments, the method further includes:
  • the target video segment is the second user-side terminal intercepted from the live video data and corresponding to the first message message relevant video clips;
  • the corresponding relationship between the first message information and the target video segment is determined as the corresponding relationship between historical message information and historical live video segments.
  • the second user's device can display the message sent by the first user's device, and the second user (that is, the host) can reply to the message during the live broadcast.
  • the second user side device can perform speech recognition and semantic analysis on the second user's reply (such as using machine reading comprehension analysis, QA model, etc.), and can also analyze the second user's reply.
  • the server may have the database, and the second user-side device may send the correspondence relationship between the established message information and its corresponding reply video to the server, and the server shall store it in its database; or, the database It can also be set independently of the server.
  • the second user-side device can upload the correspondence between the established message and its corresponding reply video to the database for storage, and the server can call the stored message in the database to correspond to it.
  • the corresponding relationship of the reply video, etc., the embodiments of the present disclosure are not limited thereto.
  • the method further includes:
  • the target message information includes N second message messages
  • M pieces of second message messages containing the same content in the N second message messages are merged to obtain a third message message; wherein, M , N is an integer greater than 1, and M ⁇ N;
  • the third message includes message content and the number M of the second message.
  • the N pieces of second message information may be message information sent by multiple different first user-side devices, or may be multiple message messages sent by one first user-side device. This is the limit.
  • the message information sent by the first user-side device can be collected in the server, and the server performs text semantic analysis on the received message information sent by the first user-side device, and performs a text analysis on the message information that is judged to have the same meaning. Merge to obtain a merged message, so that only one merged message can be displayed on the second user side device (such as when the second user side device displays the message, it can be correspondingly displayed at the nickname of the message.
  • the embodiment of the present disclosure also provides a live content processing device 200, which is applied to a server, and the device 200 includes:
  • the first receiving part 210 is configured to receive the target message information sent by the first user-side device in a live broadcast scenario
  • the first processing part 220 is configured to determine the target video segment corresponding to the target message information if the target message information matches the first message message processed by the second user; wherein, the target video segment is composed of generating a reply from the second user to the first message in the historical live broadcast;
  • the first sending part 230 is configured to send the target video segment to the first user-side device.
  • the first processing part 220 includes:
  • the first processing part is configured to determine the target video segment corresponding to the target message information according to the corresponding relationship between historical message information and historical live video segments.
  • the device 200 also includes:
  • the acquisition part is configured to acquire the live video data of the second user-side device and the live video data of the first user-side device before determining the target video segment corresponding to the target message information according to the correspondence between historical message information and historical live video segments.
  • the intercepting part is configured to intercept a target video segment related to the first message from the live video data
  • the establishing part is configured to establish a corresponding relationship between historical message information and historical live video segments according to the first message information and the target video segment.
  • the intercepted part includes:
  • the second processing part is configured to perform semantic analysis processing on the first message to obtain the first semantic content corresponding to the first message;
  • the third processing part is configured to perform speech recognition and semantic analysis processing on the audio data in the live video data, and obtain the second semantic content corresponding to the live video data;
  • the intercepting part is configured to intercept a video segment corresponding to the target semantic content from the live video data if the target semantic content related to the first semantic content is matched in the second semantic content;
  • the video segment corresponding to the target semantic content is determined as the target video segment.
  • the device 200 also includes:
  • the second receiving part is configured to, before determining the target video segment corresponding to the target message information according to the corresponding relationship between the historical message information and the historical live video segment, receive the first message sent by the second user side device.
  • a target video segment corresponding to the message message wherein, the target video segment is a video segment related to the first message message intercepted by the second user-side terminal from the live video data;
  • the second processing part is configured to determine the corresponding relationship between the first message information and the target video segment as the corresponding relationship between historical message information and historical live video segments.
  • the device 200 also includes:
  • the merging part is configured to, after receiving the target message information sent by the first user-side device, if the target message information includes N pieces of second message information, combine the N pieces of second message information containing M The second message information is merged to obtain the third message information; wherein, M and N are integers greater than 1, and M ⁇ N;
  • the second sending part is configured to send the third message to the second user side device.
  • the third message includes message content and the number M of the second message.
  • the above-mentioned apparatus in the embodiment of the present disclosure can realize each process of the above-mentioned method for processing live content on the server side, and can achieve the same technical effect.
  • an embodiment of the present disclosure also provides an electronic device.
  • the electronic device is a server, including a processor 301, a memory 302, and a 301, the processor 301 implements the steps of the above method for processing live content on the server side when the computer program is executed.
  • the electronic device may further include a transceiver 303 for receiving and sending data under the control of the processor 301 .
  • the bus architecture may include any number of interconnected buses and bridges, one or more processors 301 represented by the processor 301 and various circuits of the memory 302 represented by the memory 302 are linked together.
  • the bus architecture can also link together various other circuits such as peripherals, voltage regulators, and power management circuits, etc., which are well known in the art and therefore will not be further described herein.
  • the bus interface provides the interface.
  • Transceiver 303 may be a plurality of elements, ie, including a transmitter and a transceiver, providing a means for communicating with various other devices over a transmission medium.
  • the processor 301 is responsible for managing the bus architecture and general processing, and the memory 302 can store data used by the processor when performing operations.
  • an embodiment of the present disclosure also provides a readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method for processing live content on the server side are implemented, and the same technical effect can be achieved.
  • an embodiment of the present disclosure also provides a method for processing live content, which is applied to a first user-side device, and the method includes:
  • Step 41 In the live broadcast scenario, send the target message information to the server.
  • the first user-side device may also be called a viewer-side device (or viewer device), etc.
  • the first user is a user who watches a live broadcast; the first user watches a live broadcast through the first user-side device , the message can be sent through the message function of the live broadcast APP in the first user-side device, so as to realize the interaction with the second user (that is, the live broadcast user, or called the anchor).
  • the server can also be called a live broadcast platform system.
  • Step 42 Receive the target video segment sent by the server according to the target message information.
  • the target video clip is sent by the server when the target message information matches the first message message processed by the second user, and the target video clip is sent by the second user in the historical live broadcast. A user's reply to the first message is generated.
  • the second user may be understood as a live broadcast user (or called an anchor).
  • the second user-side device that is, the live-streaming device, or called the live-streaming device
  • the server side may receive the first user-side device
  • the target message information sent is judged to be the first message message processed by the second user
  • the target video segment corresponding to the relevant reply content of the first message message can be searched from the historical live video data, And send the video segment to the first user-side device.
  • the matching of the target message information with the first message information that has been processed by the second user may be: the target message information is the first message information that has been processed by the second user.
  • the matching of the target message information with the first message information processed by the second user may also be: the semantic content corresponding to the target message information is the same as the semantic content corresponding to the first message information; wherein, the semantic content
  • the content can be determined by semantic analysis of the message, and the same semantic content can be understood as containing the same/similar keywords (such as "efficacy”, “function”, and “effect” can be understood as similar keywords).
  • the matching of the target message information with the first message information processed by the second user may also be: the target message information contains the same/similar keywords as the first message information, etc., and the embodiment of the present disclosure does not This is the limit.
  • the server may send the target video segment to the first user-side device in a video stream manner.
  • Step 43 Play the target video segment.
  • the playing the target video segment includes: playing the target video segment in the second playback window when the live video data is played in the first playback window.
  • the first user-side device plays the target video segment, continue to play the current live video data (as the current live video data band audio) in the first playback window, and show the target video segment in the second playback window (If the target video segment does not have audio, the original audio can be voice recognized and displayed in the form of subtitles).
  • the first play window and the second play window can be displayed in a split-screen play mode, for example, the display screen can be divided into two display areas, wherein one display area corresponds to the first play window, and the other display area corresponds to Second playback window.
  • the first play window can be displayed in full screen, the second play window is located on the display layer of the first play window, and the display area size of the second play window is smaller than the display area size of the first play window, that is, the second play window
  • the second play window is displayed in a play mode similar to a small window, and the embodiments of the present disclosure are not limited thereto.
  • the split-screen play mode or the small-window play mode can be closed, and the single-screen (or full-screen) display of the real-time live stream (ie, the currently live video data) can be continued.
  • the user of the first user-side device can also click to play the target video segment at any time, so that the first user can review the reply video that has been broadcasted at any time.
  • the target message information in the live broadcast scene, send the target message information to the server, receive the target video segment sent by the server according to the target message information, and play the target video segment.
  • the target video segment since the target video segment is sent by the server when the target message information matches the first message message processed by the second user, the target video segment is generated by the first message in the historical live broadcast.
  • the reply of the second user to the first message is generated, so that the first user-side device can obtain the relevant reply of its message in time, and can reduce the second user's repeated replies to the same message, thereby improving the performance of the live broadcast scene. Interaction efficiency between viewers and hosts.
  • an embodiment of the present disclosure provides an apparatus 500 for processing live content, which is applied to a first user-side device.
  • the apparatus 500 includes:
  • the sending part 510 is configured to send the target message information to the server in the live broadcast scene;
  • the receiving part 520 is configured to receive the target video segment sent by the server according to the target message information; wherein, the target video segment is the first message processed by the server between the target message information and the second user. When the information matches, the target video segment is generated by the reply of the second user to the first message in the historical live broadcast;
  • the playing part 530 is configured to play the target video segment.
  • the playing part 530 includes:
  • the playing part is configured to play the target video segment in the second playing window when the live video data is playing in the first playing window.
  • the above-mentioned apparatus in the embodiment of the present disclosure can realize each process of the above-mentioned method for processing live content of the first user-side device, and can achieve the same technical effect.
  • an embodiment of the present disclosure also provides an electronic device.
  • the electronic device is a first user-side device, including: a processor 601, a memory 603, and stored in the memory 603 and can A computer program running on the processor 601; wherein, the memory 603 is connected to the processor 601 through the bus interface 602, and the memory 603 is used to store programs and programs used by the processor 601 when performing operations data, the processor 601 invokes and executes the programs and data stored in the memory 603 .
  • the electronic device further includes a transceiver 604, the transceiver 604 is connected to the bus interface 602, and is used to receive and send data under the control of the processor 601; the processor 601 is used to read the computer program in the memory 603 , and realize the steps of the method for processing the live broadcast content of the first user-side device when the computer program is executed.
  • the bus architecture may include any number of interconnected buses and bridges, and one or more processors represented by processor 601 and various circuits of memory represented by memory 603 are linked together.
  • the bus architecture can also link together various other circuits such as peripherals, voltage regulators, and power management circuits, etc., which are well known in the art and therefore will not be further described herein.
  • the bus interface provides the interface.
  • Transceiver 604 may be a plurality of elements, including a transmitter and a transceiver, providing a means for communicating with various other devices over a transmission medium.
  • the user interface 605 may also be an interface capable of connecting externally and internally to required devices, and the connected devices include but are not limited to keypads, displays, speakers, microphones, joysticks, and the like.
  • the processor 601 is responsible for managing the bus architecture and general processing, and the memory 603 can store data used by the processor 601 when performing operations.
  • an embodiment of the present disclosure also provides a readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of the method for processing the live content of the first user-side device are implemented, and the same technical effect.
  • an embodiment of the present disclosure also provides a method for processing live content, which is applied to a second user-side device, and the method includes:
  • Step 71 In a live broadcast scenario, collect live video data and acquire first message information sent by the first user-side device.
  • the second user side device may collect live video data of the second user (that is, the anchor) in real time.
  • the first user may be understood as a user watching a live broadcast
  • the first user-side device may also be called a viewer-side device (or viewer device).
  • the first user can send message information through the message function of the live broadcast APP in the first user-side device, so as to realize communication with the second user (ie, the live broadcast user, or called the anchor) Interaction, for example, the first user-side device can send the first message to the server, and the server sends the first message to the second user-side device, so that the second user-side device can obtain the first message The first message information sent by the user-side device.
  • Step 72 Intercepting a target video segment related to the first message from the live video data.
  • the second user-side device can perform real-time speech recognition on the live broadcast audio during the live broadcast, and determine the A target video segment related to the first message in the live video data.
  • Step 73 Send the target video segment corresponding to the first message to a server.
  • the server may also be called a live broadcast platform system.
  • the server may have a database
  • the second user-side device may send the correspondence between the established message information and its corresponding reply video to the server, and store it in its database by the server, so as to call the database subsequently
  • the corresponding relationship between the message information stored in the database and the corresponding reply video can also be set independently of the server, such as the second user-side device can upload the established message information and the corresponding reply video correspondence to the database.
  • the server may call the corresponding relationship between the message information stored in the database and the corresponding reply video, etc., and the embodiments of the present disclosure are not limited thereto.
  • the second user-side device may also perform real-time speech recognition on the live audio during the live broadcast, and the text result after the speech recognition is sent to the server and stored, so that the server side can text results and corresponding live video data, so that the target video related to the first message information in the live video data can be determined according to the first message message sent by the first user-side device and the text result after speech recognition fragment.
  • the intercepting the target video segment related to the first message information from the live video data includes:
  • a video segment corresponding to the target semantic content is intercepted from the live video data, and the target semantic content A video segment corresponding to the content is determined to be the target video segment.
  • the second user's device can display the message sent by the first user's device, and the second user (that is, the host) can reply to the message during the live broadcast.
  • the second user side device can perform speech recognition and semantic analysis on the second user's reply (such as using machine reading comprehension analysis, QA model, etc.), and can also analyze the second user's reply.
  • the method for processing live content further includes:
  • the third message message is obtained after the server merges M pieces of second message messages containing the same content sent by the audience device; wherein, M is greater than an integer of 1;
  • the displaying the third message information includes:
  • the N pieces of second message information may be message information sent by multiple different first user-side devices, or may be multiple message messages sent by one first user-side device. This is the limit.
  • the message information sent by the first user-side device can be collected in the server, and the server performs text semantic analysis on the received message information sent by the first user-side device, and performs a text analysis on the message information that is judged to have the same meaning. Merge to obtain a merged message, so that only one merged message can be displayed on the second user side device (such as when the second user side device displays the message, it can be correspondingly displayed at the nickname of the message.
  • the embodiment of the present disclosure also provides an apparatus 800 for processing live content, which is applied to a second user-side device.
  • the apparatus 800 includes:
  • the obtaining part 810 is configured to collect live video data and obtain the first message sent by the first user-side device in a live broadcast scene;
  • the intercepting part 820 is configured to intercept a target video segment related to the first message from the live video data
  • the sending part 830 is configured to send the target video segment corresponding to the first message to a server.
  • the intercepting part 820 includes:
  • the first processing part is configured to perform semantic analysis and processing on the first message to obtain the first semantic content corresponding to the first message;
  • the second processing part is configured to perform speech recognition and semantic analysis processing on the audio data in the live video data, and obtain the second semantic content corresponding to the live video data;
  • the intercepting part is configured to intercept a video segment corresponding to the target semantic content from the live video data if the target semantic content related to the first semantic content is matched from the second semantic content, and A video segment corresponding to the target semantic content is determined as the target video segment.
  • the device 800 also includes:
  • the receiving part is configured to receive the third message message sent by the server; wherein, the third message message is obtained after the server merges and processes M pieces of second message messages containing the same content sent by the audience device; Wherein, M is an integer greater than 1;
  • the display part is configured to display the third message information.
  • the display part includes:
  • the display part is configured to display the message content of the third message message and the number M of second message messages corresponding to the third message message.
  • the above-mentioned apparatus in the embodiment of the present disclosure can realize each process of the above-mentioned method for processing live content of the second user-side device, and can achieve the same technical effect.
  • an embodiment of the present disclosure also provides an electronic device.
  • the electronic device is a second user-side device, including: a processor 601, a memory 603, and stored in the memory 603.
  • the electronic device further includes a transceiver 604, the transceiver 604 is connected to the bus interface 602, and is used to receive and send data under the control of the processor 601; the processor 601 is used to read the computer program in the memory 603 , and realize the steps of the method for processing the live content of the second user-side device when the computer program is executed.
  • the bus architecture may include any number of interconnected buses and bridges, and one or more processors represented by processor 601 and various circuits of memory represented by memory 603 are linked together.
  • the bus architecture can also link together various other circuits such as peripherals, voltage regulators, and power management circuits, etc., which are well known in the art and therefore will not be further described herein.
  • the bus interface provides the interface.
  • Transceiver 604 may be a plurality of elements including a transmitter and a transceiver, providing a means for communicating with various other devices over a transmission medium.
  • the user interface 605 may also be an interface capable of connecting externally and internally to required devices, and the connected devices include but are not limited to keypads, displays, speakers, microphones, joysticks, and the like.
  • the processor 601 is responsible for managing the bus architecture and general processing, and the memory 603 can store data used by the processor 601 when performing operations.
  • an embodiment of the present disclosure also provides a readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of the method for processing the live content of the second user-side device are implemented, and the same technical effect.
  • An embodiment of the present disclosure provides a computer program product, the computer program product includes a computer program or an instruction, and when the computer program or instruction is run on a computer, the computer executes the above-mentioned service side or first user
  • the steps of the method for processing the live broadcast content of the user-side device or the second user-side device can achieve the same technical effect.
  • the disclosed methods and devices may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may be physically included separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above-mentioned integrated units implemented in the form of software functional units may be stored in a computer-readable storage medium.
  • the above-mentioned software functional units are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the sending and receiving methods described in various embodiments of the present disclosure.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), magnetic disk or optical disc, etc., which can store program codes. medium.
  • Embodiments of the present disclosure provide a method for processing live content, electronic equipment, a readable storage medium, and a computer program product, wherein the method for processing live content includes: receiving a target message sent by a first user-side device in a live broadcast scene information; in the case where the target message information matches the first message message processed by the second user, determine the target video segment corresponding to the target message information; wherein, the target video segment is obtained from the historical live broadcast generating a reply from the second user to the first message; and sending the target video segment to the first user-side device.
  • the method for processing live content in the embodiments of the present disclosure solves the problem of low efficiency in the interaction between the viewer and the anchor in the current live broadcast scene.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本公开提供了一种直播内容的处理方法、电子设备、可读存储介质及计算机程序产品,其中所述方法包括:在直播场景下,接收第一用户侧设备发送的目标留言信息;若所述目标留言信息与第二用户已处理过的第一留言信息相匹配,则确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;将所述目标视频片段发送至所述第一用户侧设备。

Description

直播内容的处理方法、电子设备、可读存储介质及计算机程序产品
相关申请的交叉引用
本公开基于申请号为202111348138.7、申请日为2021年11月15日、申请名称为“直播内容的处理方法、电子设备及可读存储介质”的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本公开作为参考。
技术领域
本公开涉及通信技术领域,尤其涉及一种直播内容的处理方法、电子设备、可读存储介质及计算机程序产品。
背景技术
随着互联网信息技术的飞速发展,网络直播也变得越来越普遍,直播侧用户设备可以通过直播应用程序(Application,APP)进行节目直播,观众侧用户设备也可以通过直播APP观看所直播的节目。在直播场景下,观众侧用户设备可以通过发送弹幕的方式与直播侧用户设备的主播进行实时地交流互动,主播也可以选取观众在弹幕中的提问进行实时地解答。但是,目前在直播场景下,主播与观众的互动主要通过观众留言和主播回应来实现,这种互动方式在观众提问数量较多时,主播侧可能遗漏某些留言导致该留言不能被有效到答复,或者由于观众观看直播的时间不同存在观众留言重复的情况,导致主播需要重复回答相同的问题,降低了直播场景下观众和主播的互动效率。
发明内容
本公开提供一种直播内容的处理方法、电子设备、可读存储介质及计算机程序产品,解决了目前直播场景下的观众和主播的互动方式存在效率低的问题。
第一方面,本公开的实施例提供一种直播内容的处理方法,应用于服务器,所述方法包括:
在直播场景下,接收第一用户侧设备发送的目标留言信息;
在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
将所述目标视频片段发送至所述第一用户侧设备。
在一些实施例中,所述在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段,包括:
根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段。
在一些实施例中,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息;
从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
根据所述第一留言信息和所述目标视频片段,建立历史留言信息与历史直播视频片段之间的对应关系。
在一些实施例中,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
在所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段;将所述目标语义内容对应的视频片段确定为所述目标视频片段。
在一些实施例中,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
接收第二用户侧设备发送的与所述第一留言信息对应的目标视频片段;其中,所述目标视频片段是所述第二用户侧终端从直播视频数据中截取的与所述第一留言信息相关的视频片段;
将所述第一留言信息与所述目标视频片段的对应关系,确定为历史留言信息和历史直播的视频片段的对应关系。
在一些实施例中,所述接收第一用户侧设备发送的目标留言信息之后,还包括:
在所述目标留言信息包括N条第二留言信息的情况下,将所述N条第二留言信息中包含相同内容的M条第二留言信息进行合并处理,获得第三留言信息;其中,M、N为大于1的整数,且M≤N;
将所述第三留言信息发送至第二用户侧设备。
在一些实施例中,所述第三留言信息中包括留言内容,以及所述第二留言信息的条数M。
第二方面,本公开实施例提供一种直播内容的处理方法,应用于第一用户侧设备,所述方法包括:
在直播场景下,向服务器发送目标留言信息;
接收所述服务器根据所述目标留言信息发送的目标视频片段;其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
播放所述目标视频片段。
在一些实施例中,所述播放所述目标视频片段包括:
在第一播放窗口播放直播的视频数据的情况下,在第二播放窗口播放所述目标视频片段。
第三方面,本公开实施例提供一种直播内容的处理方法,应用于第二用户侧设备,所述方法包括:
在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息;
从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
将与所述第一留言信息对应的所述目标视频片段发送至服务器。
在一些实施例中,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
在从所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段,并将所述目标语义内容对应的视频片段确定为与所述目标视频片段。
在一些实施例中,所述直播内容的处理方法还包括:
接收所述服务器发送的第三留言信息;其中,所述第三留言信息是所述服务器将观众设备发送的包含相同内容的M条第二留言信息进行合并处理后得到的;其中,M为大于1的整数;
显示所述第三留言信息。
在一些实施例中,所述显示所述第三留言信息,包括:
显示所述第三留言信息的留言内容,以及所述第三留言信息对应的第二留言信息的条数M。
第四方面,本公开实施例提供了一种直播内容的处理装置,应用于服务器,所述装置包括:
第一接收部分,配置为在直播场景下,接收第一用户侧设备发送的目标留言信息;
第一处理部分,配置为在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
第一发送部分,配置为将所述目标视频片段发送至所述第一用户侧设备。
在一些实施例中,所述第一处理部分包括:
第一处理部分,配置为根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段。
在一些实施例中,所述装置还包括:
获取部分,配置为在根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息;
截取部分,配置为从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
建立部分,配置为根据所述第一留言信息和所述目标视频片段,建立历史留言信息与历史直播视频片段之间的对应关系。
在一些实施例中,所述截取部分包括:
第二处理部分,配置为对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
第三处理部分,配置为对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
截取部分,配置为在所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段;将所述目标语义内容对应的视频片段确定为所述目标视频片段。
在一些实施例中,所述装置还包括:
第二接收部分,配置为在根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,接收第二用户侧设备发送的与所述第一留言信息对应的目标视频片段;其中,所述目标视频片段是所述第二用户侧终端从直播视频数据中截取的与所述第一留言信息相关的视频片段;
第二处理部分,配置为将所述第一留言信息与所述目标视频片段的对应关系,确定为历史留言信息和历史直播的视频片段的对应关系。
在一些实施例中,所述装置还包括:
合并部分,配置为接收第一用户侧设备发送的目标留言信息之后,在所述目标留言信息包括N条第二留言信息的情况下,将所述N条第二留言信息中包含相同内容的M 条第二留言信息进行合并处理,获得第三留言信息;其中,M、N为大于1的整数,且M≤N;
第二发送部分,配置为将所述第三留言信息发送至第二用户侧设备。
在一些实施例中,所述第三留言信息中包括留言内容,以及所述第二留言信息的条数M。
第五方面,本公开实施例提供一种直播内容的处理装置,应用于第一用户侧设备,所述装置包括:
发送部分,配置为在直播场景下,向服务器发送目标留言信息;
接收部分,配置为接收所述服务器根据所述目标留言信息发送的目标视频片段;其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一标留言信息的回复生成;
播放部分,配置为播放所述目标视频片段。
在一些实施例中,所述播放部分包括:
播放部分,配置为在第一播放窗口播放直播的视频数据的情况下,在第二播放窗口播放所述目标视频片段。
第六方面,本公开实施例提供一种直播内容的处理装置,应用于第二用户侧设备,所述装置包括:
获取部分,配置为在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息;
截取部分,配置为从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
发送部分,配置为将与所述第一留言信息对应的所述目标视频片段发送至服务器。
在一些实施例中,所述截取部分包括:
第一处理部分,配置为对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
第二处理部分,配置为对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
截取部分,配置为在从所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段,并将所述目标语义内容对应的视频片段确定为与所述目标视频片段。
在一些实施例中,所述装置还包括:
接收部分,配置为接收所述服务器发送的第三留言信息;其中,所述第三留言信息是所述服务器将观众设备发送的包含相同内容的M条第二留言信息进行合并处理后得到的;其中,M为大于1的整数;
显示部分,配置为显示所述第三留言信息。
在一些实施例中,所述显示部分包括:
显示部分,配置为显示所述第三留言信息的留言内容,以及所述第三留言信息对应的第二留言信息的条数M。
第七方面,本公开实施例提供一种电子设备,包括:处理器、存储器及存储在所述存储器上并可在所述处理器上运行的计算机程序;
其中,在所述电子设备为服务器的情况下,所述处理器执行所述计算机程序时实现如上第一方面所述的直播内容的处理方法的步骤;
在所述电子设备为第一用户侧设备的情况下,所述处理器执行所述计算机程序时实 现如上第二方面所述的直播内容的处理方法的步骤;
在所述电子设备为第二用户侧设备的情况下,所述处理器执行所述计算机程序时实现如上第三方面所述的直播内容的处理方法的步骤。
第八方面,本公开实施例提供一种可读存储介质,所述可读存储介质上存储有计算机程序,所述计算机程序被处理器执行时实现如上第一方面或第二方面或第三方面所述的直播内容的处理方法的步骤。
第九方面,本公开实施例提供一种计算机程序产品,所述计算机程序产品包括计算机程序或指令,在所述计算机程序或指令在计算机上运行的情况下,使得所述计算机执行如上第一方面或第二方面或第三方面所述的直播内容的处理方法的步骤。
本公开的实施例,在直播场景下,接收第一用户侧设备(如观众侧设备)发送的目标留言信息;若所述目标留言信息与第二用户(主播)已处理过的第一留言信息相匹配,则确定所述目标留言信息对应的目标视频片段;并将所述目标视频片段发送至所述第一用户侧设备,从而使得第一用户侧设备可以及时获得其留言信息的相关答复,并且由于所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成,从而可以减少第二用户针对相同留言信息的重复答复,进而提高了直播场景下观众和主播的互动效率。
附图说明
为了更清楚地说明本公开实施例的技术方案,下面将对本公开实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1表示本公开实施例服务器侧的直播内容的处理方法的流程图;
图2表示本公开实施例服务器侧的直播内容的处理装置的框图;
图3表示本公开实施例电子设备的框图之一;
图4表示本公开实施例第一用户侧设备的直播内容的处理方法的流程图;
图5表示本公开实施例第一用户侧设备的直播内容的处理方法的框图;
图6表示本公开实施例电子设备的框图之二;
图7表示本公开实施例第二用户侧设备的直播内容的处理方法的流程图;
图8表示本公开实施例第二用户侧设备的直播内容的处理方法的框图。
具体实施方式
为使本公开要解决的技术问题、技术方案和优点更加清楚,下面将结合附图及具体实施例进行详细描述。在下面的描述中,提供诸如具体的配置和组件的特定细节仅仅是为了帮助全面理解本公开的实施例。因此,本领域技术人员应该清楚,可以对这里描述的实施例进行各种改变和修改而不脱离本公开的范围和精神。另外,为了清楚和简洁,省略了对已知功能和构造的描述。
应理解,说明书通篇中提到的“一个实施例”或“一实施例”意味着与实施例有关的特定特征、结构或特性包括在本公开的至少一个实施例中。因此,在整个说明书各处出现的“在一个实施例中”或“在一实施例中”未必一定指相同的实施例。此外,这些特定的特征、结构或特性可以任意适合的方式结合在一个或多个实施例中。
在本公开的各种实施例中,应理解,下述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本公开实施例的实施过程构成任何限定。另外,本文中术语“系统”和“网络”在本文中常可互换使用。
在本公开所提供的实施例中,应理解,“与A相应的B”表示B与A相关联,根据 A可以确定B。但还应理解,根据A确定B并不意味着仅仅根据A确定B,还可以根据A和/或其它信息确定B。
本公开实施例中,电子设备可以是移动电话(或手机),或者其他能够发送或接收无线信号的设备,包括用户设备、个人数字助理(Personal Digital Assistant,PDA)、无线调制解调器、无线通信装置、手持装置、膝上型计算机、无绳电话、无线本地回路(Wireless Local Loop,WLL)站、能够将移动信号转换为WiFi信号的客户终端(Customer Premise Equipment,CPE)或移动智能热点、智能家电、或其他不通过人的操作就能自发与移动通信网络通信的设备、服务器等。
在一些实施例中,本公开的实施例提供了一种直播内容的处理方法,解决了目前直播场景下的观众和主播的互动方式存在效率低的问题。
如图1所示,本公开实施例提供了一种直播内容的处理方法,应用于服务器,所述方法包括:
步骤11:在直播场景下,接收第一用户侧设备发送的目标留言信息。
可选地,所述第一用户可以理解为观看直播的用户,所述第一用户侧设备也可以称为观众侧设备(或观众设备)等;第一用户在通过第一用户侧设备观看直播的过程中,可以通过第一用户侧设备中直播APP的留言功能发送留言信息,以实现与第二用户(即直播用户,或称为主播)的互动。
步骤12:在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段。
其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成。
可选地,所述第二用户可以理解为直播用户(或称为主播)。在直播过程中,由第二用户侧设备(即直播侧设备,或称为直播设备)或服务器对直播用户的直播内容进行语音识别和语义分析,当接收到第一用户侧设备发送的目标留言信息时,且如果该目标留言信息与第二用户已经处理过的第一留言信息相匹配,则可以从历史直播的视频数据中查找与该第一留言信息的相关答复内容对应的目标视频片段。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配可以是:所述目标留言信息为第二用户已经处理过的第一留言信息。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配还可以是:所述目标留言信息对应的语义内容与所述第一留言信息对应的语义内容相同;其中,语义内容可以通过对留言信息进行语义分析确定,语义内容相同可以理解为包含相同/相近的关键词(如“功效”、“功能”、“效果”可以理解为相近的关键词)。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配还可以是:目标留言信息中包含与所述第一留言信息相同/相近的关键词等,本公开实施例不以此为限。
步骤13:将所述目标视频片段发送至所述第一用户侧设备。
可选地,所述服务器可以将所述目标视频片段以视频流的方式发送至所述第一用户侧设备。其中,该服务器也可以称为直播平台系统。
该实施例中,在直播场景下,接收第一用户侧设备(如观众侧设备)发送的目标留言信息;若所述目标留言信息与第二用户(主播)已处理过的第一留言信息相匹配,则确定所述目标留言信息对应的目标视频片段;并将所述目标视频片段发送至所述第一用户侧设备,从而使得第一用户侧设备可以及时获得其留言信息的相关答复,并且由于所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成,从而可以减少第二用户针对相同留言信息的重复答复,进而提高了直播场景下观众和主播的互动效率。
可选地,所述若所述目标留言信息与第二用户已处理过的第一留言信息相匹配,则确定所述目标留言信息对应的目标视频片段,包括:
根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段。
例如:在直播过程中,由第二用户侧设备或服务器对直播用户的直播内容进行语音识别和语义分析,针对直播过程中与第一用户侧设备发送的留言信息相关的视频片段,可以建立留言信息与相应的视频片段之间的对应关系,并将其作为历史留言信息和历史直播视频片段的对应关系进行存储,以便于在接收到第一用户侧设备发送的目标留言信息与历史留言信息相同时,可以从历史直播的视频片段中确定与该目标留言信息对应的目标视频片段,以使得第一用户侧设备可以及时获得其留言信息的相关答复,以及减少第二用户针对相同留言信息的重复答复,进而提高了直播场景下观众和主播的互动效率。
可选地,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息;
从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
根据所述第一留言信息和所述目标视频片段,建立历史留言信息与历史直播视频片段之间的对应关系。
可选地,本公开实施例中获取第二用户侧设备的直播视频数据,以及获取第一用户侧设备发送的第一留言信息的时序关系并不限定,如可以先获取第二用户侧设备的直播视频数据,再获取第一用户侧设备发送的第一留言信息;或者,也可以先获取第一用户侧设备发送的第一留言信息,再获取第二用户侧设备的直播视频数据;或者,可以同时获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息等。
例如:第二用户侧设备可以在直播过程中,对直播音频进行实时语音识别,语音识别后的文字结果发送到服务器并进行存储,或者服务器侧也可以根据接收到的第二用户侧设备发送的直播视频数据进行语音识别;这样服务器侧可以根据获得的语音识别后的文字结果以及相应的直播视频数据,从而可以根据第一用户侧设备发送的第一留言信息和语音识别后的文字结果,确定所述直播视频数据中与所述第一留言信息相关的目标视频片段。
可选地,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
若在所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容,则从所述直播视频数据中截取与所述目标语义内容对应的视频片段;将所述目标语义内容对应的视频片段确定为所述目标视频片段。
例如:服务器侧可以针对接收到的直播视频数据中的音频数据进行语音识别和语义分析(如采用机器阅读理解分析、QA模型等),同时对第一用户侧设备发送的第一留言信息进行语义分析,并结合两者语义分析得到的结果判断直播视频数据中是在答复哪条留言信息,以及答复的起始时间点和结束时间点,并将起始时间点和结束时间点之间的回复视频进行剪辑保存,保存形式为一条留言信息对应一个回复视频,即确定第一留言信息对应的视频片段,从而建立两者的对应关系并存储至数据库中,即形成一个“标准回复库”。
这样,在第一用户侧设备发送的目标留言信息到达服务器时,服务器可以对该目标留言信息进行文本语义分析,如果该目标留言信息已存在于“标准回复库”中,则服务器侧可以直接将该目标留言信息对应的标准回复视频(即目标视频)发送到第一用户侧设备(如将所述标准回复视频以视频流的方式发送到第一用户侧设备),从而使得第一用户侧可以及时获知其留言信息对应的回复,避免由于第二用户侧遗漏相关留言信息导致的交互效率下降,并且还可以避免第二用户侧重复回复相同的留言信息,从而可以提高第一用户侧和第二用户侧在直播时的交互效率。
可选地,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
接收第二用户侧设备发送的与所述第一留言信息对应的目标视频片段;其中,所述目标视频片段是所述第二用户侧终端从直播视频数据中截取的与所述第一留言信息相关的视频片段;
将所述第一留言信息与所述目标视频片段的对应关系,确定为历史留言信息和历史直播的视频片段的对应关系。
例如:在直播场景下,第二用户的设备可以显示第一用户侧设备发送的留言信息,第二用户(即主播)可以在直播过程中针对留言信息进行回复。在第二用户对相应的留言信息进行回复时,第二用户侧设备可以对第二用户的回复进行语音识别和语义分析(如采用机器阅读理解分析、QA模型等),同时还可以对第二用户侧设备所显示的留言信息进行语义分析,并结合两者语义分析得到的结果判断第二用户在回复哪条留言信息,以及回复的起始时间点和结束时间点,并将起始时间点和结束时间点之间的回复视频进行剪辑保存,保存形式为一条留言信息对应一个回复视频,即确定第一留言信息对应的视频片段,从而建立两者的对应关系并存储至数据库中,即形成一个“标准回复库”。
可选地,所述服务器可以具有所述数据库,该第二用户侧设备可以将建立的留言信息与其对应的回复视频的对应关系发送给服务器,并由服务器存储至其数据库中;或者,该数据库也可以独立于该服务器设置,如第二用户侧设备可以将建立的留言信息与其对应的回复视频的对应关系上传至所述数据库进行存储,该服务器可以调用该数据库中所存储的留言信息与其对应的回复视频的对应关系等,本公开实施例不以此为限。
可选地,所述接收第一用户侧设备发送的目标留言信息之后,还包括:
在所述目标留言信息包括N条第二留言信息的情况下,将所述N条第二留言信息中包含相同内容的M条第二留言信息进行合并处理,获得第三留言信息;其中,M、N为大于1的整数,且M≤N;
将所述第三留言信息发送至第二用户侧设备。可选地,所述第三留言信息中包括留言内容,以及所述第二留言信息的条数M。
可选地,所述N条第二留言信息可以是多个不同的第一用户侧设备发送的留言信息,也可以是一个第一用户侧设备发送的多个留言信息等,本公开实施例不以此为限。
该实施例中,第一用户侧设备发送的留言信息可以在服务器中进行汇集,服务器对接收到的第一用户侧设备发送的留言信息进行文本语义分析,对被判断为同一含义的留言信息进行归并,得到一条合并后的留言信息,从而在第二用户侧设备上可以仅展示一条合并后的留言信息(如在第二用户侧设备显示该留言信息时,可以在留言昵称处对应显示相应的留言内容,以及标明该条留言信息中归并的留言数量等),使得第二用户侧设备上留言信息显示的清洁性,提高第二用户查看留言信息的效率,以及方便第二用户了解问题热度,并可以减少过多相同内容的留言信息导致其他留言信息被遗漏的概率。
如图2所示,本公开实施例还提供一种直播内容的处理装置200,应用于服务器,所述装置200包括:
第一接收部分210,配置为在直播场景下,接收第一用户侧设备发送的目标留言信息;
第一处理部分220,配置为若所述目标留言信息与第二用户已处理过的第一留言信息相匹配,则确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
第一发送部分230,配置为将所述目标视频片段发送至所述第一用户侧设备。
可选地,所述第一处理部分220包括:
第一处理部分,配置为根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段。
可选地,所述装置200还包括:
获取部分,配置为在根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息;
截取部分,配置为从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
建立部分,配置为根据所述第一留言信息和所述目标视频片段,建立历史留言信息与历史直播视频片段之间的对应关系。
可选地,所述截取部分包括:
第二处理部分,配置为对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
第三处理部分,配置为对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
截取部分,配置为若在所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容,则从所述直播视频数据中截取与所述目标语义内容对应的视频片段;将所述目标语义内容对应的视频片段确定为所述目标视频片段。
可选地,所述装置200还包括:
第二接收部分,配置为在根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,接收第二用户侧设备发送的与所述第一留言信息对应的目标视频片段;其中,所述目标视频片段是所述第二用户侧终端从直播视频数据中截取的与所述第一留言信息相关的视频片段;
第二处理部分,配置为将所述第一留言信息与所述目标视频片段的对应关系,确定为历史留言信息和历史直播的视频片段的对应关系。
可选地,所述装置200还包括:
合并部分,配置为接收第一用户侧设备发送的目标留言信息之后,在所述目标留言信息包括N条第二留言信息的情况下,将所述N条第二留言信息中包含相同内容的M条第二留言信息进行合并处理,获得第三留言信息;其中,M、N为大于1的整数,且M≤N;
第二发送部分,配置为将所述第三留言信息发送至第二用户侧设备。
可选地,所述第三留言信息中包括留言内容,以及所述第二留言信息的条数M。
本公开实施例中的上述装置能够实现上述服务器侧的直播内容的处理方法的各个过程,并能达到相同的技术效果。
如图3所示,本公开实施例还提供一种电子设备,可选地,所述电子设备为服务器,包括处理器301、存储器302及存储在所述存储器302上并可在所述处理器301上运行的计算机程序,所述处理器301执行所述计算机程序时实现上述服务器侧的直播内容的 处理方法的步骤。
可选地,所述电子设备还可以包括收发机303,用于在处理器301的控制下接收和发送数据。
其中,总线架构可以包括任意数量的互联的总线和桥,由处理器301代表的一个或多个处理器301和存储器302代表的存储器302的各种电路链接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路链接在一起,这些都是本领域所公知的,因此,本文不再对其进行进一步描述。总线接口提供接口。收发机303可以是多个元件,即包括发送机和收发机,提供用于在传输介质上与各种其他装置通信的单元。处理器301负责管理总线架构和通常的处理,存储器302可以存储处理器在执行操作时所使用的数据。
本领域技术人员可以理解,实现上述实施例的全部或者部分步骤可以通过硬件来完成,也可以通过计算机程序来指示相关的硬件来完成,所述计算机程序包括执行上述方法的部分或者全部步骤的指令;且该计算机程序可以存储于一可读存储介质中,存储介质可以是任何形式的存储介质。
另外,本公开实施例还提供一种可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述服务器侧的直播内容的处理方法的步骤,且能达到相同的技术效果。
以上实施例就服务侧对本公开的直播内容的处理方法进行说明,以下结合实施例对第一用户侧设备的直播内容的处理方法进行说明。
如图4所示,本公开实施例还提供一种直播内容的处理方法,应用于第一用户侧设备,所述方法包括:
步骤41:在直播场景下,向服务器发送目标留言信息。
可选地,所述第一用户侧设备也可以称为观众侧设备(或观众设备)等,第一用户即为观看直播的用户;第一用户在通过第一用户侧设备观看直播的过程中,可以通过第一用户侧设备中直播APP的留言功能发送留言信息,以实现与第二用户(即直播用户,或称为主播)的互动。所述服务器也可以称为直播平台系统。
步骤42:接收所述服务器根据所述目标留言信息发送的目标视频片段。
其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成。
可选地,所述第二用户可以理解为直播用户(或称为主播)。在直播过程中,由第二用户侧设备(即直播侧设备,或称为直播设备)或服务器对直播用户的直播内容进行语音识别和语义分析,服务器侧可以根据接收到的第一用户侧设备发送的目标留言信息,判断该目标留言信息是第二用户已经处理过的第一留言信息时,可以从历史直播的视频数据中查找与该第一留言信息的相关答复内容对应的目标视频片段,并将该视频片段发送至所述第一用户侧设备。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配可以是:所述目标留言信息为第二用户已经处理过的第一留言信息。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配还可以是:所述目标留言信息对应的语义内容与所述第一留言信息对应的语义内容相同;其中,语义内容可以通过对留言信息进行语义分析确定,语义内容相同可以理解为包含相同/相近的关键词(如“功效”、“功能”、“效果”可以理解为相近的关键词)。
可选地,目标留言信息与第二用户已经处理过的第一留言信息相匹配还可以是:目标留言信息中包含与所述第一留言信息相同/相近的关键词等,本公开实施例不以此为限。
可选地,所述服务器可以将所述目标视频片段以视频流的方式发送至所述第一用户侧设备。
步骤43:播放所述目标视频片段。
可选地,所述播放所述目标视频片段包括:在第一播放窗口播放直播的视频数据的情况下,在第二播放窗口播放所述目标视频片段。
例如:在第一用户侧设备播放所述目标视频片段时,在第一播放窗口继续播放当前直播的视频数据(如该当前直播的视频数据带音频),在第二播放窗口展示该目标视频片段(如该目标视频片段不带音频,可以将原音频进行语音识别,以字幕形式展示)。
可选地,第一播放窗口和第二播放窗口可以采用分屏的播放模式进行显示,如可以将显示屏划分为两个显示区域,其中一个显示区域对应第一播放窗口,另一个显示区域对应第二播放窗口。或者,第一播放窗口可以全屏显示,第二播放窗口位于所述第一播放窗口的显示层之上,且第二播放窗口的显示区域尺寸小于所述第一播放窗口的显示区域尺寸,即第二播放窗口以类似小窗口的播放模式进行显示等,本公开实施例不以此为限。
可选地,在所述目标视频片段播放完成后,可以关闭分屏的播放模式或者小窗口的播放模式,继续单屏(或全屏)显示实时直播流(即当前直播的视频数据)。可选地,第一用户侧设备的用户还可以随时点击播放该目标视频片段,方便第一用户可以随时复看一直播过的回复视频。
上述方案中,在直播场景下,向服务器发送目标留言信息,接收所述服务器根据所述目标留言信息发送的目标视频片段,并播放所述目标视频片段。其中,由于所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成,从而使得第一用户侧设备可以及时获得其留言信息的相关答复,并且可以减少第二用户针对相同留言信息的重复答复,进而提高了直播场景下观众和主播的互动效率。
如图5所示,本公开实施例提供一种直播内容的处理装置500,应用于第一用户侧设备,所述装置500包括:
发送部分510,配置为在直播场景下,向服务器发送目标留言信息;
接收部分520,配置为接收所述服务器根据所述目标留言信息发送的目标视频片段;其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
播放部分530,配置为播放所述目标视频片段。
可选地,所述播放部分530包括:
播放部分,配置为在第一播放窗口播放直播的视频数据的情况下,在第二播放窗口播放所述目标视频片段。
本公开实施例中的上述装置能够实现上述第一用户侧设备的直播内容的处理方法的各个过程,并能达到相同的技术效果。
如图6所示,本公开实施例还提供一种电子设备,可选地,所述电子设备为第一用户侧设备,包括:处理器601、存储器603及存储在所述存储器603上并可在所述处理器601上运行的计算机程序;其中,存储器603通过总线接口602与所述处理器601相连接,所述存储器603用于存储所述处理器601在执行操作时所使用的程序和数据,处理器601调用并执行所述存储器603中所存储的程序和数据。
其中,所述电子设备还包括收发机604,所述收发机604与总线接口602连接,用 于在处理器601的控制下接收和发送数据;处理器601用于读取存储器603中的计算机程序,并在执行所述计算机程序时实现上述第一用户侧设备的直播内容的处理方法的步骤。
需要说明的是,在图6中,总线架构可以包括任意数量的互联的总线和桥,由处理器601代表的一个或多个处理器和存储器603代表的存储器的各种电路链接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路链接在一起,这些都是本领域所公知的,因此,本文不再对其进行进一步描述。总线接口提供接口。收发机604可以是多个元件,即包括发送机和收发机,提供用于在传输介质上与各种其他装置通信的单元。针对不同的终端,用户接口605还可以是能够外接内接需要设备的接口,连接的设备包括但不限于小键盘、显示器、扬声器、麦克风、操纵杆等。处理器601负责管理总线架构和通常的处理,存储器603可以存储处理器601在执行操作时所使用的数据。
本领域技术人员可以理解,实现上述实施例的全部或者部分步骤可以通过硬件来完成,也可以通过计算机程序来指示相关的硬件来完成,所述计算机程序包括执行上述方法的部分或者全部步骤的指令;且该计算机程序可以存储于一可读存储介质中,存储介质可以是任何形式的存储介质。
另外,本公开实施例还提供一种可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述第一用户侧设备的直播内容的处理方法的步骤,且能达到相同的技术效果。
以上实施例就服务侧和第一用户侧设备分别对本公开的直播内容的处理方法进行说明,以下结合实施例对第二用户侧设备的直播内容的处理方法进行说明。
如图7所示,本公开实施例还提供一种直播内容的处理方法,应用于第二用户侧设备,所述方法包括:
步骤71:在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息。
可选地,在直播场景下,第二用户侧设备(即直播侧设备,或称为直播设备)可以实时的采集第二用户(即主播)的直播视频数据。
可选地,所述第一用户可以理解为观看直播的用户,所述第一用户侧设备也可以称为观众侧设备(或观众设备)等。第一用户在通过第一用户侧设备观看直播的过程中,可以通过第一用户侧设备中直播APP的留言功能发送留言信息,以实现与第二用户(即直播用户,或称为主播)的互动,如所述第一用户侧设备可以将第一留言信息发送至服务器,由服务器将该第一留言信息发送至所述第二用户侧设备,从而所述第二用户侧设备可以获取第一用户侧设备发送的第一留言信息。
步骤72:从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段。
例如:所述第二用户侧设备可以在直播过程中,对直播音频进行实时语音识别,并根据获得的语音识别后的文字结果,以及第一用户侧设备发送的第一留言信息,确定所述直播视频数据中与所述第一留言信息相关的目标视频片段。
步骤73:将与所述第一留言信息对应的所述目标视频片段发送至服务器。
可选地,所述服务器也可以称为直播平台系统。
可选地,所述服务器可以具有数据库,该第二用户侧设备可以将建立的留言信息与其对应的回复视频的对应关系发送给服务器,并由服务器存储至其数据库中,以便于后续调用该数据库中所存储的留言信息与其对应的回复视频的对应关系;或者,该数据库也可以独立于该服务器设置,如第二用户侧设备可以将建立的留言信息与其对应的回复视频的对应关系上传至所述数据库进行存储,该服务器可以调用该数据库中所存储的留 言信息与其对应的回复视频的对应关系等,本公开实施例不以此为限。
上述方案中,在直播场景下,通过采集直播视频数据以及获取第一用户侧设备发送的第一留言信息,以及从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,将与所述第一留言信息对应的所述目标视频片段发送至服务器,以使得服务器在接收第一用户侧设备发送的目标留言信息并判断所述目标留言信息与第二用户已处理过的第一留言信息相匹配时,确定所述目标留言信息对应的目标视频片段,并将所述目标视频片段发送至所述第一用户侧设备,以使得第一用户侧设备可以及时获得其留言信息的相关答复,并且可以减少第二用户针对相同留言信息的重复答复,进而提高了直播场景下观众和主播的互动效率。
可选地,所述第二用户侧设备还可以在直播过程中,对直播音频进行实时语音识别,语音识别后的文字结果发送到服务器并进行存储,以便于服务器侧可以根据获得的语音识别后的文字结果以及相应的直播视频数据,从而可以根据第一用户侧设备发送的第一留言信息和语音识别后的文字结果,确定所述直播视频数据中与所述第一留言信息相关的目标视频片段。
可选地,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
若从所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容,则从所述直播视频数据中截取与所述目标语义内容对应的视频片段,并将所述目标语义内容对应的视频片段确定为与所述目标视频片段。
例如:在直播场景下,第二用户的设备可以显示第一用户侧设备发送的留言信息,第二用户(即主播)可以在直播过程中针对留言信息进行回复。在第二用户对相应的留言信息进行回复时,第二用户侧设备可以对第二用户的回复进行语音识别和语义分析(如采用机器阅读理解分析、QA模型等),同时还可以对第二用户侧设备所显示的留言信息进行语义分析,并结合两者语义分析得到的结果判断第二用户在回复哪条留言信息,以及回复的起始时间点和结束时间点,并将起始时间点和结束时间点之间的回复视频进行剪辑保存,保存形式为一条留言信息对应一个回复视频,即确定第一留言信息对应的视频片段,从而建立两者的对应关系并存储至数据库中,即形成一个“标准回复库”。
可选地,所述直播内容的处理方法还包括:
接收所述服务器发送的第三留言信息;其中,所述第三留言信息是所述服务器将观众设备发送的包含相同内容的M条第二留言信息进行合并处理后得到的;其中,M为大于1的整数;
显示所述第三留言信息。
可选地,所述显示所述第三留言信息,包括:
显示所述第三留言信息的留言内容,以及所述第三留言信息对应的第二留言信息的条数M。
可选地,所述N条第二留言信息可以是多个不同的第一用户侧设备发送的留言信息,也可以是一个第一用户侧设备发送的多个留言信息等,本公开实施例不以此为限。
该实施例中,第一用户侧设备发送的留言信息可以在服务器中进行汇集,服务器对接收到的第一用户侧设备发送的留言信息进行文本语义分析,对被判断为同一含义的留言信息进行归并,得到一条合并后的留言信息,从而在第二用户侧设备上可以仅展示一 条合并后的留言信息(如在第二用户侧设备显示该留言信息时,可以在留言昵称处对应显示相应的留言内容,以及标明该条留言信息中归并的留言数量等),使得第二用户侧设备上留言信息显示的清洁性,提高第二用户查看留言信息的效率,以及方便第二用户了解问题热度,并可以减少过多相同内容的留言信息导致其他留言信息被遗漏的概率。
如图8所示,本公开实施例还提供一种直播内容的处理装置800,应用于第二用户侧设备,所述装置800包括:
获取部分810,配置为在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息;
截取部分820,配置为从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
发送部分830,配置为将与所述第一留言信息对应的所述目标视频片段发送至服务器。
可选地,所述截取部分820包括:
第一处理部分,配置为对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
第二处理部分,配置为对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
截取部分,配置为若从所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容,则从所述直播视频数据中截取与所述目标语义内容对应的视频片段,并将所述目标语义内容对应的视频片段确定为与所述目标视频片段。
可选地,所述装置800还包括:
接收部分,配置为接收所述服务器发送的第三留言信息;其中,所述第三留言信息是所述服务器将观众设备发送的包含相同内容的M条第二留言信息进行合并处理后得到的;其中,M为大于1的整数;
显示部分,配置为显示所述第三留言信息。
可选地,所述显示部分包括:
显示部分,配置为显示所述第三留言信息的留言内容,以及所述第三留言信息对应的第二留言信息的条数M。
本公开实施例中的上述装置能够实现上述第二用户侧设备的直播内容的处理方法的各个过程,并能达到相同的技术效果。
继续参见图6,本公开实施例还提供一种电子设备,可选地,所述电子设备为第二用户侧设备,包括:处理器601、存储器603及存储在所述存储器603上并可在所述处理器601上运行的计算机程序;其中,存储器603通过总线接口602与所述处理器601相连接,所述存储器603用于存储所述处理器601在执行操作时所使用的程序和数据,处理器601调用并执行所述存储器603中所存储的程序和数据。
其中,所述电子设备还包括收发机604,所述收发机604与总线接口602连接,用于在处理器601的控制下接收和发送数据;处理器601用于读取存储器603中的计算机程序,并在执行所述计算机程序时实现上述第二用户侧设备的直播内容的处理方法的步骤。
需要说明的是,在图6中,总线架构可以包括任意数量的互联的总线和桥,由处理器601代表的一个或多个处理器和存储器603代表的存储器的各种电路链接在一起。总线架构还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路链接在一起,这些都是本领域所公知的,因此,本文不再对其进行进一步描述。总线接口提供接口。收发机604可以是多个元件,即包括发送机和收发机,提供用于在传输介质上与各 种其他装置通信的单元。针对不同的终端,用户接口605还可以是能够外接内接需要设备的接口,连接的设备包括但不限于小键盘、显示器、扬声器、麦克风、操纵杆等。处理器601负责管理总线架构和通常的处理,存储器603可以存储处理器601在执行操作时所使用的数据。
本领域技术人员可以理解,实现上述实施例的全部或者部分步骤可以通过硬件来完成,也可以通过计算机程序来指示相关的硬件来完成,所述计算机程序包括执行上述方法的部分或者全部步骤的指令;且该计算机程序可以存储于一可读存储介质中,存储介质可以是任何形式的存储介质。
另外,本公开实施例还提供一种可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述第二用户侧设备的直播内容的处理方法的步骤,且能达到相同的技术效果。
本公开实施例提供还一种计算机程序产品,所述计算机程序产品包括计算机程序或指令,在所述计算机程序或指令在计算机上运行的情况下,使得所述计算机执行如上服务侧或第一用户侧设备或第二用户侧设备的直播内容的处理方法的步骤,且能达到相同的技术效果。
在本公开所提供的几个实施例中,应该理解到,所揭露方法和装置,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理包括,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元,可以存储在一个计算机可读取存储介质中。上述软件功能单元存储在一个存储介质中,包括若干指令用使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述收发方法的部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述的是本公开的优选实施方式,应当指出对于本技术领域的普通人员来说,在不脱离本公开所述的原理前提下还可以作出若干改进和润饰,这些改进和润饰也在本公开的保护范围内。
工业实用性
本公开实施例提供了一种直播内容的处理方法、电子设备、可读存储介质及计算机程序产品,其中,直播内容的处理方法包括:在直播场景下,接收第一用户侧设备发送的目标留言信息;在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;将所述目标视频片段发送至所述第一用户侧设备。本公开实施例中的直播内容的处理方法解决了目前直播场景下的观众和主播的互动方式存在效率低的问题。

Claims (19)

  1. 一种直播内容的处理方法,应用于服务器,所述方法包括:
    在直播场景下,接收第一用户侧设备发送的目标留言信息;
    在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
    将所述目标视频片段发送至所述第一用户侧设备。
  2. 根据权利要求1所述的直播内容的处理方法,其中,所述在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段,包括:
    根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段。
  3. 根据权利要求2所述的直播内容的处理方法,其中,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
    获取第二用户侧设备的直播视频数据以及第一用户侧设备发送的第一留言信息;
    从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
    根据所述第一留言信息和所述目标视频片段,建立历史留言信息与历史直播视频片段之间的对应关系。
  4. 根据权利要求3所述的直播内容的处理方法,其中,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
    对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
    对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
    在所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段;将所述目标语义内容对应的视频片段确定为所述目标视频片段。
  5. 根据权利要求2所述的直播内容的处理方法,其中,所述根据历史留言信息和历史直播视频片段的对应关系,确定与所述目标留言信息对应的所述目标视频片段之前,还包括:
    接收第二用户侧设备发送的与所述第一留言信息对应的目标视频片段;其中,所述目标视频片段是所述第二用户侧终端从直播视频数据中截取的与所述第一留言信息相关的视频片段;
    将所述第一留言信息与所述目标视频片段的对应关系,确定为历史留言信息和历史直播的视频片段的对应关系。
  6. 根据权利要求1所述的直播内容的处理方法,其中,所述接收第一用户侧设备发送的目标留言信息之后,还包括:
    在所述目标留言信息包括N条第二留言信息的情况下,将所述N条第二留言信息中包含相同内容的M条第二留言信息进行合并处理,获得第三留言信息;其中,M、N为大于1的整数,且M≤N;
    将所述第三留言信息发送至第二用户侧设备。
  7. 根据权利要求6所述的直播内容的处理方法,其中,所述第三留言信息中包括留言内容,以及所述第二留言信息的条数M。
  8. 一种直播内容的处理方法,应用于第一用户侧设备,所述方法包括:
    在直播场景下,向服务器发送目标留言信息;
    接收所述服务器根据所述目标留言信息发送的目标视频片段;其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
    播放所述目标视频片段。
  9. 根据权利要求8所述的直播内容的处理方法,其中,所述播放所述目标视频片段包括:
    在第一播放窗口播放直播的视频数据的情况下,在第二播放窗口播放所述目标视频片段。
  10. 一种直播内容的处理方法,应用于第二用户侧设备,所述方法包括:
    在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息;
    从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
    将与所述第一留言信息对应的所述目标视频片段发送至服务器。
  11. 根据权利要求10所述的直播内容的处理方法,其中,所述从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段,包括:
    对所述第一留言信息进行语义分析处理,获得所述第一留言信息对应的第一语义内容;
    对所述直播视频数据中的音频数据进行语音识别和语义分析处理,获得所述直播视频数据对应的第二语义内容;
    在从所述第二语义内容中匹配到与所述第一语义内容相关的目标语义内容的情况下,从所述直播视频数据中截取与所述目标语义内容对应的视频片段,并将所述目标语义内容对应的视频片段确定为与所述目标视频片段。
  12. 根据权利要求10所述的直播内容的处理方法,其中,还包括:
    接收所述服务器发送的第三留言信息;其中,所述第三留言信息是所述服务器将观众设备发送的包含相同内容的M条第二留言信息进行合并处理后得到的;其中,M为大于1的整数;
    显示所述第三留言信息。
  13. 根据权利要求12所述的直播内容的处理方法,其中,所述显示所述第三留言信息,包括:
    显示所述第三留言信息的留言内容,以及所述第三留言信息对应的第二留言信息的条数M。
  14. 一种直播内容的处理装置,应用于服务器,所述装置包括:
    第一接收部分,配置为在直播场景下,接收第一用户侧设备发送的目标留言信息;
    第一处理部分,配置为在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下,确定所述目标留言信息对应的目标视频片段;其中,所述目标视频片段由历史直播中所述第二用户对所述第一留言信息的回复生成;
    第一发送部分,配置为将所述目标视频片段发送至所述第一用户侧设备。
  15. 一种直播内容的处理装置,应用于第一用户侧设备,所述装置包括:
    发送部分,配置为在直播场景下,向服务器发送目标留言信息;
    接收部分,配置为接收所述服务器根据所述目标留言信息发送的目标视频片段;其中,所述目标视频片段是所述服务器在所述目标留言信息与第二用户已处理过的第一留言信息相匹配的情况下发送的,所述目标视频片段由历史直播中所述第二用户对所述第 一标留言信息的回复生成;
    播放部分,配置为播放所述目标视频片段。
  16. 一种直播内容的处理装置,应用于第二用户侧设备,所述装置包括:
    获取部分,配置为在直播场景下,采集直播视频数据以及获取第一用户侧设备发送的第一留言信息;
    截取部分,配置为从所述直播视频数据中截取与所述第一留言信息相关的目标视频片段;
    发送部分,配置为将与所述第一留言信息对应的所述目标视频片段发送至服务器。
  17. 一种电子设备,包括:处理器、存储器及存储在所述存储器上并可在所述处理器上运行的计算机程序;
    其中,在所述电子设备为服务器的情况下,所述处理器执行所述计算机程序时实现如权利要求1至7中任一项所述的直播内容的处理方法的步骤;
    在所述电子设备为第一用户侧设备的情况下,所述处理器执行所述计算机程序时实现如权利要求8或9中任一项所述的直播内容的处理方法的步骤;
    在所述电子设备为第二用户侧设备的情况下,所述处理器执行所述计算机程序时实现如权利要求10至13中任一项所述的直播内容的处理方法的步骤。
  18. 一种可读存储介质,所述可读存储介质上存储有计算机程序,所述计算机程序被处理器执行时实现如权利要求1至13中任一项所述的直播内容的处理方法的步骤。
  19. 一种计算机程序产品,所述计算机程序产品包括计算机程序或指令,在所述计算机程序或指令在计算机上运行的情况下,使得所述计算机执行如权利要求1至13中任一项所述的直播内容的处理方法的步骤。
PCT/CN2022/130672 2021-11-15 2022-11-08 直播内容的处理方法、电子设备、可读存储介质及计算机程序产品 WO2023083186A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111348138.7 2021-11-15
CN202111348138.7A CN114071174A (zh) 2021-11-15 2021-11-15 直播内容的处理方法、电子设备及可读存储介质

Publications (1)

Publication Number Publication Date
WO2023083186A1 true WO2023083186A1 (zh) 2023-05-19

Family

ID=80272158

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/130672 WO2023083186A1 (zh) 2021-11-15 2022-11-08 直播内容的处理方法、电子设备、可读存储介质及计算机程序产品

Country Status (2)

Country Link
CN (1) CN114071174A (zh)
WO (1) WO2023083186A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114071174A (zh) * 2021-11-15 2022-02-18 咪咕文化科技有限公司 直播内容的处理方法、电子设备及可读存储介质
CN115119017B (zh) * 2022-05-17 2023-12-08 上海南燕信息技术有限公司 基于人工智能的医疗健康保险推荐及管理方法和系统
CN115544237A (zh) * 2022-12-02 2022-12-30 北京红棉小冰科技有限公司 基于直播场景的对话数据集构建方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106878819A (zh) * 2017-01-20 2017-06-20 合网络技术(北京)有限公司 一种网络直播中信息交互的方法、系统及装置
CN108419138A (zh) * 2018-02-05 2018-08-17 平安科技(深圳)有限公司 直播互动装置、方法及计算机可读存储介质
CN112073741A (zh) * 2020-08-31 2020-12-11 腾讯科技(深圳)有限公司 直播信息的处理方法、装置、电子设备及存储介质
CN112351288A (zh) * 2019-08-07 2021-02-09 阿里巴巴集团控股有限公司 直播信息处理方法、装置、服务器、终端以及存储介质
CN113301360A (zh) * 2020-08-31 2021-08-24 阿里巴巴集团控股有限公司 一种信息的提示方法、计算设备及存储介质
CN114071174A (zh) * 2021-11-15 2022-02-18 咪咕文化科技有限公司 直播内容的处理方法、电子设备及可读存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108391179B (zh) * 2018-04-26 2021-07-27 腾讯科技(深圳)有限公司 直播数据处理方法、装置、服务器、终端及存储介质
CN112765990B (zh) * 2020-12-31 2024-01-12 平安科技(深圳)有限公司 直播弹幕实时合并方法、装置、计算机设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106878819A (zh) * 2017-01-20 2017-06-20 合网络技术(北京)有限公司 一种网络直播中信息交互的方法、系统及装置
CN108419138A (zh) * 2018-02-05 2018-08-17 平安科技(深圳)有限公司 直播互动装置、方法及计算机可读存储介质
CN112351288A (zh) * 2019-08-07 2021-02-09 阿里巴巴集团控股有限公司 直播信息处理方法、装置、服务器、终端以及存储介质
CN112073741A (zh) * 2020-08-31 2020-12-11 腾讯科技(深圳)有限公司 直播信息的处理方法、装置、电子设备及存储介质
CN113301360A (zh) * 2020-08-31 2021-08-24 阿里巴巴集团控股有限公司 一种信息的提示方法、计算设备及存储介质
CN114071174A (zh) * 2021-11-15 2022-02-18 咪咕文化科技有限公司 直播内容的处理方法、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN114071174A (zh) 2022-02-18

Similar Documents

Publication Publication Date Title
WO2023083186A1 (zh) 直播内容的处理方法、电子设备、可读存储介质及计算机程序产品
WO2019134235A1 (zh) 一种直播互动方法、装置、终端设备及存储介质
US20160295269A1 (en) Information pushing method, device and system
CN103067776A (zh) 节目推送方法、系统及智能显示设备、云端服务器
CN104185040A (zh) 应用同步方法、应用服务器及终端
KR101991188B1 (ko) 홍보 정보의 처리방법, 장치, 디바이스 및 비휘발성 컴퓨터 저장매체
WO2018095219A1 (zh) 媒体信息处理方法和装置
WO2021249323A1 (zh) 一种信息处理方法、系统、装置、电子设备及存储介质
US11652763B2 (en) Information display method and apparatus, and electronic device
CN111163330A (zh) 直播视频的渲染方法、装置、系统、设备及存储介质
CN111818383B (zh) 视频数据的生成方法、系统、装置、电子设备及存储介质
CN113573090A (zh) 游戏直播中的内容显示方法、装置、系统和存储介质
WO2023143299A1 (zh) 消息展示方法、装置、设备及存储介质
CN113766270A (zh) 视频播放方法、系统、服务器、终端设备、以及电子设备
US11227290B1 (en) Systems and methods for delivering in-application messages
CN108833983A (zh) 播放数据获取方法、装置、设备以及存储介质
CN106792125A (zh) 一种视频播放方法及其终端、系统
CN110351577B (zh) 直播信息处理方法及装置、存储介质、电子设备
CN103826158A (zh) 一种网络直播装置和方法
CN103152615A (zh) 多媒体信息发布的方法及装置
CN109194971A (zh) 一种为多媒体文件的生成方法及装置
US8583150B2 (en) Personalized channel service providing system, real-time channel service providing method, and personalized channel service providing system method
CN108712434A (zh) 一种基于高清视频直播录播会议会诊的实现方法
CN115514989A (zh) 一种数据传输方法、系统及存储介质
CN112118213B (zh) 一种线上的视频数据输出方法、系统及云平台

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22891980

Country of ref document: EP

Kind code of ref document: A1