WO2021147480A1 - 直播辅助方法及电子设备 - Google Patents

直播辅助方法及电子设备 Download PDF

Info

Publication number
WO2021147480A1
WO2021147480A1 PCT/CN2020/128677 CN2020128677W WO2021147480A1 WO 2021147480 A1 WO2021147480 A1 WO 2021147480A1 CN 2020128677 W CN2020128677 W CN 2020128677W WO 2021147480 A1 WO2021147480 A1 WO 2021147480A1
Authority
WO
WIPO (PCT)
Prior art keywords
attribute information
live broadcast
anchor
portrait model
room
Prior art date
Application number
PCT/CN2020/128677
Other languages
English (en)
French (fr)
Inventor
陈霄
Original Assignee
北京达佳互联信息技术有限公司
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 北京达佳互联信息技术有限公司 filed Critical 北京达佳互联信息技术有限公司
Priority to EP20916077.9A priority Critical patent/EP4096222A4/en
Publication of WO2021147480A1 publication Critical patent/WO2021147480A1/zh
Priority to US17/407,495 priority patent/US20210385506A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H20/00—Arrangements for broadcast or for distribution combined with broadcast
    • H04H20/38—Arrangements for distribution where lower stations, e.g. receivers, interact with the broadcast
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/02—Arrangements for generating broadcast information; Arrangements for generating broadcast-related information with a direct linking to broadcast information or to broadcast space-time; Arrangements for simultaneous generation of broadcast information and broadcast-related information
    • H04H60/06—Arrangements for scheduling broadcast services or broadcast-related services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
    • H04N21/25866—Management of end-user data
    • H04N21/25891—Management of end-user data being end-user preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/27—Server based end-user applications
    • H04N21/274—Storing end-user multimedia data in response to end-user request, e.g. network recorder
    • H04N21/2743—Video hosting of uploaded data from client
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4524—Management of client data or end-user data involving the geographical location of the client
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/654—Transmission by server directed to the client
    • H04N21/6547—Transmission by server directed to the client comprising parameters, e.g. for client setup
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/65—Transmission of management data between client and server
    • H04N21/658—Transmission by the client directed to the server
    • H04N21/6582—Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
    • H04H60/46—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for recognising users' preferences

Definitions

  • the present disclosure relates to the field of Internet technology, and in particular to a live broadcast auxiliary method and electronic equipment.
  • the present disclosure provides a live broadcast auxiliary method and electronic equipment, so as to at least solve the problem that the related technology cannot fully and timely respond to the real-time request of the audience.
  • the technical solutions of the present disclosure are as follows:
  • a live broadcast assistance method including:
  • first attribute information of the target live broadcast room wherein the first attribute information is attribute information related to historical live events of the target live broadcast room;
  • the anchor portrait model assist the anchor corresponding to the target live broadcast room to perform a live broadcast event.
  • a live broadcast auxiliary device including:
  • An information acquisition unit configured to perform acquisition of first attribute information of a target live broadcast room; wherein the first attribute information is attribute information related to a historical live event of the target live broadcast room;
  • the model determining unit is configured to execute training a preset initial anchor portrait model according to the first attribute information to obtain the anchor portrait model;
  • the auxiliary live broadcast unit is configured to perform, according to the anchor portrait model, assist the anchor corresponding to the target live room to perform the live broadcast activity.
  • an electronic device including:
  • a memory for storing executable instructions of the processor
  • the processor is configured to be implemented when the instruction is executed
  • first attribute information of the target live broadcast room wherein the first attribute information is attribute information related to historical live events of the target live broadcast room;
  • the anchor portrait model assist the anchor corresponding to the target live broadcast room to perform a live broadcast event.
  • the first attribute information is the attribute information related to the historical live events of the target live room.
  • the preset initial anchor portrait model is trained to obtain a full response to the first live room According to the anchor portrait model of the attribute information, assist the anchor corresponding to the target live room to perform the live broadcast activity according to the anchor portrait model.
  • the anchor portrait model that can fully reflect the attribute information of the target live room assists the anchor corresponding to the target live room to carry out the live event, which is conducive to the anchor corresponding to the target live room to respond to the audience's real-time request in a comprehensive and timely manner during the live broadcast process, avoiding real-time requests The phenomenon of being ignored, while avoiding the phenomenon of failure to achieve the expected effect or loss of audience.
  • Fig. 1 is a flowchart showing a live broadcast assistance method according to an embodiment
  • Fig. 2 is a flowchart showing an implementable manner of step S200 according to an embodiment
  • Fig. 3 is a flowchart showing an implementable manner of step S200 according to an embodiment
  • Fig. 4 is a flowchart showing an implementable manner of step S200 according to an embodiment
  • Fig. 5 is a specific implementation flowchart of a live broadcast assistance method according to an embodiment
  • Fig. 6 is a data analysis flowchart of the server according to an embodiment
  • Fig. 7 is a flow chart showing data collection according to an embodiment
  • Fig. 8 is a block diagram showing a live broadcast auxiliary device according to an embodiment
  • Fig. 9 is a block diagram showing an electronic device according to an embodiment
  • Fig. 10 is a block diagram of a live broadcast auxiliary device according to an embodiment.
  • Fig. 1 is a flowchart of a live broadcast assistance method according to an embodiment. As shown in Fig. 1, the method includes the following steps:
  • step S100 first attribute information of the target live broadcast room is acquired; wherein the first attribute information is attribute information related to historical live broadcast activities of the target live broadcast room.
  • step S200 according to the first attribute information, a preset initial anchor portrait model is trained to obtain the anchor portrait model.
  • step S300 according to the host portrait model, the host corresponding to the target live broadcast room is assisted to perform the live broadcast event.
  • the live broadcast room refers to the platform where the network anchor conducts live broadcasts on major live broadcast platform websites. Viewers can find and enter the corresponding live broadcast room by entering the anchor name or channel number and room number on the live broadcast platform website where the anchor is located.
  • the target live broadcast room is a live broadcast room that requires live broadcast assistance.
  • the first attribute information is the attribute information corresponding to the target live room, including the type of the live room (normal live room, theme live room, game live broadcast, etc.), terminal location and inverse geography (country city area street), networking environment, time Stamp, live broadcast progress (show activities that have been carried out, etc.).
  • the feature set of the first attribute information is extracted, and the feature set of the first attribute information is used to train the preset initial anchor portrait model to obtain the anchor portrait model.
  • the first attribute information of the target live broadcast room may be attribute information in the historical live broadcast record of the host of the target live broadcast room, or may be the current attribute information of the target live broadcast room.
  • the anchor portrait model is obtained through training, the anchor portrait model is used to assist the anchor corresponding to the target live broadcast room in the live broadcast activity. While the live broadcast is being carried out, the server can continuously obtain the attribute information of the target live broadcast room, and use the current attribute information to update the first attribute information, and perform the host portrait model according to the updated first attribute information.
  • Update to ensure that the anchor portrait model trained with the latest data is used to assist the anchor corresponding to the target live room in the live broadcast activity, and to improve the applicability of the model.
  • the host portrait model assisting the host corresponding to the target live room to carry out live activities, mainly including: recommending a personalized live broadcast method for the host, changing the existing one-way communication into a two-way mode, and enriching the interaction between the host and the audience.
  • the above-mentioned live broadcast auxiliary method obtains the first attribute information of the target live broadcast room.
  • the first attribute information is attribute information related to the historical live broadcast activity of the target live broadcast room.
  • the preset initial anchor portrait model is trained to obtain a comprehensive The anchor portrait model that reflects the attribute information of the first live broadcast room, according to the anchor portrait model, assists the anchor corresponding to the target live broadcast room to perform the live broadcast activity.
  • the present disclosure can enable the host corresponding to the target live broadcast room to fully and timely respond to the real-time request of the audience during the live broadcast process, avoiding the phenomenon that the real-time request is ignored, and avoiding the phenomenon that the expected effect is not achieved or the audience is lost.
  • Fig. 2 is a flowchart of an implementable manner of step S200 according to an embodiment. As shown in Fig. 2, it includes the following steps:
  • step S211 the initial anchor portrait model is trained according to the first attribute information, and the anchor corresponding to the target live room is assisted to perform the live broadcast activity, and second attribute information is obtained; wherein the second attribute information is the real-time attribute information of the live broadcast activity .
  • step S212 the first attribute information is updated based on the second attribute information, and the anchor portrait model is iteratively trained.
  • the preset rules are determined according to the type of the target live broadcast room and user needs, and no specific limitation is made here. For example, according to the frequency needs of the user, iterative training is performed every 5 minutes to update the anchor portrait model.
  • training the initial anchor portrait model using the first attribute information will result in an anchor portrait model.
  • the anchor portrait model is equivalent to a live room assistant and can assist the anchor corresponding to the target live room to perform live events.
  • collect the second attribute information of the target live room in real time update the first attribute information with the second attribute information, and perform iterative training according to preset rules to obtain a new anchor portrait model to improve the anchor portrait model Real-time applicability.
  • the first attribute information may also be updated through the second attribute information, and the anchor sliding model is iteratively trained based on the updated first attribute information, so as to determine the final anchor sliding model.
  • the initial anchor portrait model is trained according to the first attribute information, and the anchor corresponding to the target live room is assisted in the live broadcast activity to obtain the second attribute information, and the first attribute information is updated based on the second attribute information, and the anchor is iteratively trained
  • the portrait model in this way, can use the newly collected second attribute information to update the host portrait model, improve the real-time applicability of the host portrait model, and avoid the phenomenon that the live content is not real-time due to the use of old data.
  • Fig. 3 is a flowchart of an implementable manner of step S200 according to an embodiment. As shown in Fig. 3, it includes the following steps:
  • step S221 the preset third attribute information is acquired; where the third attribute information is attribute information related to the live event corresponding to the target live broadcast room.
  • step S222 according to the first attribute information and the third attribute information, the preset initial anchor portrait model is trained to obtain the anchor portrait model.
  • the third attribute information is preset attribute information, including the response mode customized by the host in the target live broadcast room or the response mode in a specific scene or environment. For example, when the type of the target live room is a game live room, the response methods that are not related to the game are blocked.
  • the first attribute information and the third attribute information are used to train the preset initial anchor portrait model, so that the obtained anchor portrait model can make corresponding assistance according to the preset third attribute information
  • more personalized auxiliary forms are presented, and the anchor's personalized characteristics are reflected in the live broadcast process, so as to avoid the lack of anchor characteristics when the anchor portrait model assists the live broadcast.
  • Fig. 4 is a flowchart of an implementable manner of step S200 according to an embodiment. As shown in Fig. 4, it includes the following steps:
  • step S231 fourth attribute information related to the first attribute information is acquired; where the fourth attribute information is attribute information of the live room associated with the target live room.
  • step S232 a preset initial anchor portrait model is trained according to the first attribute information and the fourth attribute information to obtain the anchor portrait model.
  • the anchor portrait model can learn and record the behavior of users participating in the live broadcast, but in the case of insufficient data vouchers for the first attribute information in the early stage, the characteristics of the live broadcast on similar topics can be summarized to obtain the fourth attribute information, and Use the fourth attribute information and a small amount of the first attribute information to train the preset initial anchor portrait model to obtain the anchor portrait model to assist the anchor in the live broadcast activities, so as to realize the personalized customization of the live room and anchor characteristics, and accelerate the accumulation of attribute information data .
  • the live room attribute data set is obtained; the correlation analysis is performed on the live room attribute data set and the first attribute information, and the live room attribute data set whose correlation meets the preset condition is determined as the fourth attribute information.
  • the preset conditions are determined according to the type of the anchor and the expected effect, and there is no specific limitation here, and the conditions that can be screened out with greater relevance or satisfy the user's requirements shall prevail.
  • a correlation analysis is performed on the live broadcast room attribute data set and the first attribute information, and the live broadcast room attribute data set whose correlation satisfies a preset condition is determined as the fourth attribute information.
  • the fourth attribute information related to the first attribute information is obtained; where the fourth attribute information is the attribute information of the live broadcast room associated with the target live broadcast room, and the training is performed based on the first attribute information and the fourth attribute information
  • the preset initial anchor portrait model is obtained, which can realize the personalized customization of the live broadcast room and anchor characteristics, and accelerate the accumulation of attribute information data.
  • step S300 it is an implementable manner of step S300, including:
  • Detect the instruction information of the target live room when it detects that the target live room initiates an instruction, respond to the instruction and assist the anchor corresponding to the target live room to perform the live broadcast activity according to the anchor portrait model.
  • the first attribute information is detected; when the first attribute information satisfies a preset polling rule, the anchor corresponding to the target live room is assisted to perform the live broadcast activity according to the anchor portrait model.
  • the present disclosure introduces a recommendation system to generate an anchor portrait model, and uses the anchor portrait model as a recommendation model.
  • the collected data information is used to collect historical instructions (including voice, text and other formats), content tags in the live broadcast room, Context information such as the location where the live broadcast occurs, terminal equipment, etc. is used as the first attribute information to train the initial host portrait model and save the results corresponding to each host.
  • the timing for obtaining the host portrait model recommendation includes a trigger type and a polling type.
  • the trigger type is specifically, when the target live room initiation instruction (host or viewer initiated instruction) is detected, respond to the instruction and obtain the response content with the result from the server according to the host's portrait model, and assist the target live room to correspond
  • the host of the host conducts a live event
  • the polling type is specifically to detect the first attribute information; when the first attribute information meets the preset polling rules (for example, the request is initiated periodically or the request is initiated when a specific condition is met), according to the host
  • the portrait model obtains the training results of the server and assists the anchor corresponding to the target live broadcast room to carry out live broadcast activities.
  • triggering and polling are used to provide auxiliary trigger conditions for the host portrait model, and assist the host corresponding to the target live room to perform live broadcast activities, which can alleviate the problem of insufficient information, such as insufficient information, leading to a decrease in the interactive time between live broadcasts and insufficient viewers. .
  • Fig. 5 is a specific implementation flowchart of a live broadcast assistance method according to an embodiment. As shown in Fig. 5, the main process of the present disclosure includes: data collection on the terminal, data analysis on the server, terminal acquisition and usage analysis results.
  • host 1, host 2,..., host N represent a large number of hosts in the module "data collection on the terminal”
  • host 1, host 2,..., host M represent the module "terminal acquisition and use analysis results"
  • the data collection on the terminal includes: on each live broadcast terminal (each terminal corresponds to a host), the robot (the equipment deployed by the host's portrait model) collects instructions during the service user (anchor and audience) request (instruction)
  • the content and the contextual content of the live broadcast room including information such as network, geographic information, live broadcast category tags, etc., are packaged and sent to the remote server.
  • the data analysis on the server side includes: the server side analyzes the packaged content, converts the uploaded content into a feature set, as the input data for the next step, and trains the portrait of each anchor according to the input data.
  • the input data range includes all the historical activities that the anchor participates in And used functions, etc., and save the trained anchor portrait model; in some embodiments, it also includes other data analysis work, such as analyzing the similarity between the portraits, aggregating the portraits whose similarity exceeds the threshold, and inputting Data filtering and anti-cheating work; in the case of insufficient data for an anchor in the early stage, there is insufficient input for training and learning.
  • the output result will use other anchor portraits with similar live content, or the bottom strategy (according to the specific business Scene decision).
  • the data analysis of the server specifically includes: the server analyzes the data uploaded by the terminal to obtain the following two forms of input characteristics: 1.
  • Context information includes but is not limited to the type of live broadcast room (normal live broadcast room, theme live broadcast room, game live broadcast, etc.), The location and reverse geography of the terminal (country urban area streets), networking environment, time stamp, live broadcast progress (show activities that have been carried out, etc.); 2.
  • Voice and text content instructions and text data initiated by the host and audience.
  • FIG. 6 it is a flowchart of data analysis of the server according to an embodiment.
  • the data analysis process on the server side includes: the server side contains, analyzes, and performs feature engineering on the uploaded data, which mainly includes semantic analysis, noise filtering, data conversion, feature selection, dimensionality reduction, etc., to calculate the feature set representing user attributes .
  • feature engineering you can know the high-frequency behaviors of each user, and add it to the supervised training learning to get the hobbies and characteristics of each user; construct a user correlation data set, perform similarity analysis, and have similar hobbies , User collection of historical behavior activities and live broadcast room content, based on the live broadcast room voice robot to generate the user's anchor portrait collection.
  • the server will receive new upload data in a fixed period, repeat the above process, update the results of the existing anchor profile model, iteratively train the model, and save the trained anchor profile model parameters.
  • the terminal obtains and uses the analysis results, including: after the anchor opens the terminal, obtains the anchor portrait model training result of the server through command trigger or polling, and feeds the result back to the anchor in the form of text, voice, etc., and improves iteratively Personalization of the anchor portrait model.
  • FIG. 7 it is a flow chart of data collection according to an embodiment, in which illegal instructions that do not meet the requirements will be discarded.
  • the collection and detection process is carried out at the same time as the anchor portrait model receives user instructions.
  • the content detection is also performed on the server side. After the detection is passed, it will be included in the effective data storage, otherwise it will be discarded.
  • the content will be encrypted and packaged to prevent it from being captured and cracked by a third party.
  • the host portrait model (usually presented in the form of an intelligent voice robot in the actual live broadcast) mainly has three scenarios when the analysis result is fed back to the host or user in the live broadcast room: 1. There is not much interaction with the voice robot (such as the first use), service
  • the client issues a recommended strategy based on the portrait results of other users in similar live broadcast environments and content; 2.
  • the server predicts the current environment based on the timestamp and the context of the live broadcast room (the user and the robot have not interacted for a long time), and then based on the user's portrait results The recommended strategy is issued; 3.
  • the current live broadcast environment is in a special scene (festival, competition, etc.), and the server recommends a strategy based on the special scene.
  • Fig. 8 is a block diagram showing a live broadcast auxiliary device according to an embodiment.
  • the device includes an information acquisition unit 801, a model determination unit 802, and an auxiliary live broadcast unit 803.
  • the information acquisition unit 801 is configured to perform acquisition of first attribute information of the target live broadcast room; where the first attribute information is attribute information related to historical live events in the target live broadcast room;
  • the model determining unit 802 is configured to perform training of a preset initial anchor portrait model according to the first attribute information to obtain the anchor portrait model;
  • the auxiliary live broadcast unit 803 is configured to perform, according to the anchor portrait model, assist the anchor corresponding to the target live room to perform the live broadcast activity.
  • the model determining unit 802 is specifically configured to execute:
  • the initial anchor portrait model is trained according to the first attribute information, assists the anchor corresponding to the target live room to perform the live event, and obtains second attribute information; wherein, the second attribute information is for performing the live event Real-time attribute information;
  • the first attribute information is updated based on the second attribute information, and the anchor portrait model is iteratively trained.
  • the information obtaining unit 801 may also be configured to perform obtaining preset third attribute information; wherein, the third attribute information is attribute information related to the live event corresponding to the target live broadcast room ;
  • the model determining unit 802 is further configured to perform training of a preset initial anchor portrait model according to the first attribute information and the third attribute information to obtain the anchor portrait model.
  • the information acquiring unit 801 may also be configured to perform acquiring fourth attribute information related to the first attribute information; wherein, the fourth attribute information is associated with the target live broadcast room Attribute information of the live broadcast room;
  • the model determining unit 802 is further configured to perform training of a preset initial anchor portrait model according to the first attribute information and the fourth attribute information to obtain the anchor portrait model.
  • the information acquiring unit 801 may be configured to execute:
  • the auxiliary live broadcast unit 803 may be configured to perform:
  • the auxiliary live broadcast unit 803 may be configured to perform:
  • Fig. 9 is a block diagram showing an electronic device 900 for live broadcast assistance according to an embodiment.
  • the device 900 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
  • the device 900 may include one or more of the following components: a processing component 902, a memory 904, a power component 906, a multimedia component 908, an audio component 910, an input/output (Input/Output, I/O) interface 912, The sensor component 914, and the communication component 916.
  • the processing component 902 generally controls the overall operations of the device 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the foregoing method.
  • the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components.
  • the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.
  • the memory 904 is configured to store various types of data to support the operation of the device 900. Examples of these data include instructions for any application or method operating on the device 900, contact data, phone book data, messages, pictures, videos, and so on.
  • the memory 904 can be implemented by any type of volatile or non-volatile storage devices or their combination, such as static random access memory (Static Random-Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically erasable programmable read-only memory).
  • EEPROM Erasable Programmable Read-Only Memory
  • EPROM Erasable Programmable Read-Only Memory
  • PROM Programmable Read-Only Memory
  • Read Only Memory ROM
  • magnetic memory flash memory, magnetic disk or optical disk.
  • the power supply component 906 provides power to various components of the device 900.
  • the power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 900.
  • the multimedia component 908 includes a screen that provides an output interface between the device 900 and the user.
  • the screen may include a liquid crystal display (Liquid Crystal Display, LCD) and a touch panel (Touch Panel, TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, sliding, and gestures on the touch panel. The touch sensor can not only sense the boundary of the touch or slide action, but also detect the duration and pressure related to the touch or slide operation.
  • the multimedia component 908 includes a front camera and/or a rear camera. When the device 900 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 910 is configured to output and/or input audio signals.
  • the audio component 910 includes a microphone (Microphone, MIC).
  • the microphone is configured to receive external audio signals.
  • the received audio signal may be further stored in the memory 904 or transmitted via the communication component 916.
  • the audio component 910 further includes a speaker for outputting audio signals.
  • the I/O interface 912 provides an interface between the processing component 902 and a peripheral interface module.
  • the above-mentioned peripheral interface module may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
  • the sensor component 914 includes one or more sensors for providing the device 900 with various aspects of state evaluation.
  • the sensor component 914 can detect the on/off status of the device 900 and the relative positioning of components, such as the display and keypad of the device 900.
  • the sensor component 914 can also detect the position change of the device 900 or a component of the device 900. The presence or absence of contact with the device 900, the orientation or acceleration/deceleration of the device 900, and the temperature change of the device 900.
  • the sensor component 914 may include a proximity sensor configured to detect the presence of nearby objects when there is no physical contact.
  • the sensor component 914 may also include a light sensor, such as a Complementary Metal-Oxide Semiconductor (CMOS) or Charge Coupled Device (CCD) image sensor for use in imaging applications.
  • CMOS Complementary Metal-Oxide Semiconductor
  • CCD Charge Coupled Device
  • the sensor component 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
  • the communication component 916 is configured to facilitate wired or wireless communication between the device 900 and other devices.
  • the device 900 can access a wireless network based on a communication standard, such as Wireless-Fidelity (WiFi), an operator network (such as 2G, 3G, 4G, or 5G), or a combination thereof.
  • WiFi Wireless-Fidelity
  • the communication component 916 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 916 further includes a Near Field Communication (NFC) module to facilitate short-range communication.
  • NFC Near Field Communication
  • the NFC module can be based on radio frequency identification (Radio Frequency Identification, RFID) technology, Infrared Data Association (Infrared Data Association, IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (Bluetooth, BT) technology and Other technologies to achieve.
  • RFID Radio Frequency Identification
  • IrDA Infrared Data Association
  • UWB Ultra Wide Band
  • Bluetooth Bluetooth, BT
  • the device 900 may be configured by one or more application specific integrated circuits (ASIC), digital signal processors (Digital Signal Processor, DSP), and digital signal processing devices (Digital Signal Processor Device, DSPD). ), programmable logic device (Programmable Logic Device, PLD), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), controller, microcontroller, microprocessor or other electronic components to implement the above methods .
  • ASIC application specific integrated circuits
  • DSP Digital Signal Processor
  • DSPD Digital Signal Processor Device
  • PLD programmable logic device
  • Field-Programmable Gate Array Field-Programmable Gate Array
  • controller microcontroller, microprocessor or other electronic components to implement the above methods .
  • a storage medium including instructions is also provided, for example, the memory 904 including instructions, and the foregoing instructions may be executed by the processor 920 of the device 900 to complete the foregoing method.
  • the storage medium may be a non-transitory computer-readable storage medium.
  • the non-transitory computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), or a compact disk read-only memory (Compact Access Memory). Disk Read Only Memory, CD-ROM), magnetic tapes, floppy disks and optical data storage devices, etc.
  • Fig. 10 is a block diagram showing a device 1000 for live broadcast assistance according to an embodiment.
  • the device 1000 may be provided as a server.
  • the apparatus 1000 includes a processing component 1022, which further includes one or more processors, and a memory resource represented by a memory 1032, for storing instructions executable by the processing component 1022, such as application programs.
  • the application program stored in the memory 1032 may include one or more modules each corresponding to a set of instructions.
  • the processing component 1022 is configured to execute instructions to execute the above-mentioned live broadcast assistance method.
  • the device 1000 may also include a power component 1026 configured to perform power management of the device 1000, a wired or wireless network interface 1050 configured to connect the device 1000 to a network, and an input output (I/O) interface 1058.
  • the device 1000 can operate based on an operating system stored in the memory 1032, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Graphics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开关于一种直播辅助方法及电子设备。该直播辅助方法可以包括：获取目标直播间的第一属性信息，第一属性信息为目标直播间的历史直播活动相关的属性信息；根据第一属性信息，训练预设的初始主播画像模型，得到能够全面反应第一直播间的属性信息的主播画像模型；根据主播画像模型，辅助目标直播间对应的主播进行直播活动。这样，借助于全面反映目标直播间属性信息的主播画像模型辅助目标直播间对应的主播进行直播活动，利用目标直播间对应的主播在直播过程中全面及时地应对观众的实时请求，避免造成无法达到预期效果或观众流失的现象。

Description

直播辅助方法及电子设备
本申请要求在2020年01月22日提交中国专利局、申请号为202010074650.6、申请名称为“直播辅助方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及互联网技术领域，尤其涉及一种直播辅助方法及电子设备。
背景技术
随着互联网技术的发展以及人们对文化艺术的大量需求，直播行业以其信息传递的及时性和互动性迎来了空前的繁荣发展。为了达到预期的直播效果，吸引更多的观众，主播需要进行大量的准备工作，人为记住大量的互动环节和方法，并根据直播的实时状态进行直播行为的调整，这对主播的整体素质提出了较高的要求。
然而，发明人发现，观众的请求各种各样，依靠主播人为现场处理，必然无法全面及时地应对观众的实时请求，导致部分观众实时请求被忽略。
发明内容
本公开提供一种直播辅助方法及电子设备，以至少解决相关技术中无法全面及时地应对观众的实时请求的问题。本公开的技术方案如下：
根据本公开实施例的第一方面，提供一种直播辅助方法，包括：
获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
根据本公开实施例的第二方面，提供一种直播辅助装置，包括：
信息获取单元，被配置为执行获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
模型确定单元，被配置为执行根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
辅助直播单元，被配置为执行根据所述主播画像模型，辅助所述目标直播间对应的主 播进行直播活动。
根据本公开实施例的第三方面，提供一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令时实现，
获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
本公开的实施例提供的技术方案至少带来以下有益效果：
获取目标直播间的第一属性信息，第一属性信息为目标直播间的历史直播活动相关的属性信息，根据第一属性信息，训练预设的初始主播画像模型，得到能够全面反应第一直播间的属性信息的主播画像模型，进而根据主播画像模型，辅助目标直播间对应的主播进行直播活动。这样，借助于能全面反映目标直播间属性信息的主播画像模型辅助目标直播间对应的主播进行直播活动，利于目标直播间对应的主播在直播过程中全面及时地应对观众的实时请求，避免实时请求被忽略的现象，同时避免造成无法达到预期效果或观众流失的现象。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是根据一实施例示出的一种直播辅助方法的流程图；
图2是根据一实施例示出的步骤S200的一种可实施方式的流程图；
图3是根据一实施例示出的步骤S200的一种可实施方式的流程图；
图4是根据一实施例示出的步骤S200的一种可实施方式的流程图；
图5是根据一实施例示出的直播辅助方法的具体实现流程图；
图6是根据一实施例示出的服务端的数据分析流程图；
图7是根据一实施例示出的数据收集的流程图；
图8是根据一实施例示出的一种直播辅助装置的框图；
图9是根据一实施例示出的一种电子设备的框图；
图10是根据一实施例示出的一种直播辅助装置的框图。
具体实施方式
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
图1是根据一实施例示出的一种直播辅助方法的流程图，如图1所示，包括以下步骤：
在步骤S100中，获取目标直播间的第一属性信息；其中，第一属性信息为目标直播间的历史直播活动相关的属性信息。
在步骤S200中，根据第一属性信息，训练预设的初始主播画像模型，得到主播画像模型。
在步骤S300中，根据主播画像模型，辅助目标直播间对应的主播进行直播活动。
其中，直播间指的是网络主播在各大直播平台网站进行直播的平台,观众可以通过在主播所在的直播平台网站输入主播名称或频道号以及房间号等方式查找并进入对应的直播间。目标直播间为需要进行直播辅助的直播间。第一属性信息是与目标直播间对应的属性信息，包括直播间的类型(普通直播间、主题直播间、游戏直播等)、终端的位置和逆地理(国家城市地区街道)、联网环境、时间戳、直播进度(已开展的秀场活动等)。
在一些实施例中，在获取到目标直播间的第一属性信息后，提取第一属性信息的特征集，应用第一属性信息的特征集训练预设的初始主播画像模型，得到主播画像模型。其中，目标直播间的第一属性信息可以是目标直播间的主播的历史直播记录中的属性信息，也可以是目标直播间当前的属性信息。当训练得到主播画像模型，应用该主播画像模型辅助目标直播间对应的主播进行直播活动。在进行直播活动的同时，服务器可以不间断地对目标直播间的属性信息进行获取，并采用当前的属性信息对第一属性信息进行更新，并根据更新后的第一属性信息对主播画像模型进行更新，以保证采用最新数据训练得到的主播画像模型辅助目标直播间对应的主播进行直播活动，提高模型的适用性。其中，根据主播画像模型，辅助目标直播间对应的主播进行直播活动，主要包括：为主播推荐个性化的直播方法，将已有的单向沟通改成双向模式，丰富主播与观众的互动。
上述直播辅助方法，获取目标直播间的第一属性信息，第一属性信息为目标直播间的历史直播活动相关的属性信息，根据第一属性信息，训练预设的初始主播画像模型，得到能够全面反应第一直播间的属性信息的主播画像模型，根据主播画像模型，辅助目标直播间对应的主播进行直播活动。
在一些实施例中，本公开可以使得目标直播间对应的主播在直播过程中全面及时地应对观众的实时请求，避免实时请求被忽略的现象，同时避免造成无法达到预期效果或观众流失的现象。
图2是根据一实施例示出的步骤S200的一种可实施方式的流程图，如图2所示，包括以下步骤：
在步骤S211中，根据第一属性信息对初始主播画像模型进行训练，辅助目标直播间对应的主播进行直播活动，并得到第二属性信息；其中，第二属性信息为进行直播活动的实时属性信息。
在步骤S212中，基于第二属性信息更新第一属性信息，迭代训练主播画像模型。
其中，预设规则根据目标直播间的类型和用户需要而定，此处不进行具体限定，例如，根据用户的频率需要，每隔5分钟进行一次迭代训练，对主播画像模型进行更新。
在一些实施例中，应用第一属性信息对初始主播画像模型进行训练会得到一个主播画像模型，该主播画像模型相当于一个直播间助手，可以辅助目标直播间对应的主播进行直播活动。在直播过程中，实时采集目标直播间的第二属性信息，应用第二属性信息对第一属性信息进行更新，并进行按照预设规则迭代训练，得到新的主播画像模型，以提高主播画像模型的实时适用性。在一些实施例中，还可以通过第二属性信息更新第一属性信息，基于更新后的第一属性信息对所述主播滑向模型进行迭代训练，从而确定最终的主播滑向模型。
上述实施例中，根据第一属性信息对初始主播画像模型进行训练，辅助目标直播间对应的主播进行直播活动，得到第二属性信息，并基于第二属性信息更新第一属性信息，迭代训练主播画像模型，这样，能够采用新采集到的第二属性信息对主播画像模型进行更新，提高主播画像模型的实时适用性，避免采用老数据造成的直播内容没有实时性的现象。
图3是根据一实施例示出的步骤S200的一种可实施方式的流程图，如图3所示，包括以下步骤：
在步骤S221中，获取预设的第三属性信息；其中，第三属性信息为目标直播间对应的直播活动相关的属性信息。
在步骤S222中，根据第一属性信息和第三属性信息，训练预设的初始主播画像模型，得到主播画像模型。
其中，第三属性信息为预设的属性信息，包括目标直播间的主播定制的响应方式或特 定场景或者环境下的响应方式。例如，当目标直播间的类型为游戏直播间的情况下，屏蔽与游戏无关的响应方式。
在一些实施例中，应用第一属性信息和第三属性信息，训练预设的初始主播画像模型，以使得到的主播画像模型能根据用于预设的第三属性信息做出相应的辅助性响应，呈现更多的个性化辅助形式，在直播过程中体现出主播的个性化特征，避免主播画像模型辅助直播时缺少主播特色的现象。
图4是根据一实施例示出的步骤S200的一种可实施方式的流程图，如图4所示，包括以下步骤：
在步骤S231中，获取与第一属性信息相关的第四属性信息；其中，第四属性信息为与目标直播间关联的直播间的属性信息。
在步骤S232中，根据第一属性信息和第四属性信息训练预设的初始主播画像模型，得到主播画像模型。
在一些实施例中，主播画像模型能够学习和记录参与直播的用户行为，但是在前期第一属性信息的数据凭证不足的情况下，可以汇总相似主题直播的活动特点，得到第四属性信息，并采用第四属性信息和少量的第一属性信息训练预设的初始主播画像模型，得到主播画像模型，辅助主播的直播活动，以实现直播间和主播特色的个性化定制，加快属性信息数据的积累。
在一些实施例中，获取直播间属性数据集；对直播间属性数据集与第一属性信息进行相关性分析，将相关性满足预设条件的直播间属性数据集确定为第四属性信息。
其中，预设条件根据主播的类型和预期的效果而定，此处不进行具体限定，以能筛选出相关性较大或满足用户要求的条件为准。
在一些实施例中，对直播间属性数据集与第一属性信息进行相关性分析，并将相关性满足预设条件的直播间属性数据集确定为第四属性信息。
上述实施例中，通过获取与第一属性信息相关的第四属性信息；其中，第四属性信息为与目标直播间关联的直播间的属性信息，并根据第一属性信息和第四属性信息训练预设的初始主播画像模型，得到主播画像模型，能实现直播间和主播特色的个性化定制，加快属性信息数据的积累。
在一些实施例中，为步骤S300的可实施方式，包括：
对目标直播间的指令信息进行检测；当检测到目标直播间发起指令时，响应于指令，并根据主播画像模型，辅助目标直播间对应的主播进行直播活动。
在一些实施例中，对第一属性信息进行检测；当第一属性信息满足预设的轮询规则时，根据主播画像模型，辅助目标直播间对应的主播进行直播活动。
在一些实施例中，本公开引入推荐系统，生成主播画像模型，并将主播画像模型作为 推荐模型，采用收集到的数据信息收集历史指令(包括语音、文字等格式)、直播间的内容标签、直播发生的位置、终端设备等上下文信息作为第一属性信息训练初始主播画像模型并将对应每个主播的结果保存。其中，在主播画像模型辅助目标直播间对应的主播进行直播活动时，获取主播画像模型推荐的时机包括触发式和轮询式。其中，触发式具体为，当检测到目标直播间发起指令(主播或者观众发起指令)时，响应于指令，并根据主播画像模型，从服务端获取带有结果的响应内容，辅助目标直播间对应的主播进行直播活动；轮询式具体为，对第一属性信息进行检测；当第一属性信息满足预设的轮询规则(例如，定期发起请求或满足特定条件时发起请求)时，根据主播画像模型，获取服务端的训练结果，辅助目标直播间对应的主播进行直播活动。
上述实施例中，采用触发式和轮询式，为主播画像模型提供辅助触发条件，辅助目标直播间对应的主播进行直播活动，可以缓解信息不足等导致直播间互动时长下降，观众人数不足的问题。
图5是根据一实施例示出的直播辅助方法的具体实现流程图，如图5所示，本公开的主要流程包括：终端上的数据收集、服务端的数据分析、终端获取和使用分析结果。
图5中的主播1、主播2、……、主播N表示模块“终端上的数据收集”中的大量主播，主播1、主播2、……、主播M表示模块“终端获取和使用分析结果”中的大量主播。
终端上的数据收集，包括：在各个直播终端上(每个终端对应一个主播)，机器人(主播画像模型所部署的设备)在服务用户(主播和观众)的要求(发出指令)期间，收集指令内容和直播间上下文内容，含网络、地理信息、直播类别标签等信息，并将内容打包以后发送到远程服务端。
服务端的数据分析，包括：服务端对打包内容解析，将上传内容转为特征集，作为下一步的输入数据，根据输入数据训练每个主播的画像，输入数据范围包括所有主播参与到的历史活动和使用过的功能等，并将训练得到的主播画像模型保存；在一些实施例中，还包括其他数据分析工作，例如分析各画像之间的相似度，对相似度超过阈值的画像聚合，输入数据的过滤防作弊等工作；在前期针对一个主播数据量不够的情况下，训练学习没有充足的输入，此时输出结果会使用其他开过相似直播内容的主播画像，或者兜底策略(根据具体业务场景决定)。服务端的数据分析具体包括：服务端解析终端上传的数据，获得以下两种形式的输入特征：1.上下文信息包括但不限于直播间的类型(普通直播间、主题直播间、游戏直播等)、终端的位置和逆地理(国家城市地区街道)、联网环境、时间戳、直播进度(已开展的秀场活动等)；2.语音和文本内容：主播和观众发起的指令、文本数据。如图6所示，为根据一实施例示出的服务端的数据分析流程图。其中，服务端的数据分析过程包括：服务端对上传的数据收容、解析、进行特征工程，主要包括语义解析、过滤噪声值、数据转换、特征选择、降维等步骤，计算表示用户属性的特征集合。其中，通过特 征工程可以知道每个用户的高频次行为活动，并加入到监督训练学习中，得到每个用户的爱好和特点；构建用户相关性数据集，进行相似度分析，将具有相似爱好，历史行为活动和直播间内容的用户收录一个集合中，基于直播间语音机器人生成用户的主播画像集合。服务端会按照固定的周期收入新的上传数据，重复上述流程，更新已有的主播画像模型的结果，迭代训练模型，并将训练好的主播画像模型参数保存。
终端获取和使用分析结果，包括：在主播打开终端以后，通过指令触发或者轮询的方式获取服务端的主播画像模型训练结果，并将该结果以文本、语音等形式反馈给主播，并通过迭代提升主播画像模型的个性化。如图7所示，为根据一实施例示出的数据收集的流程图，其中，不符合要求的非法指令会被抛弃。
采集和检测过程与主播画像模型接收用户指令同时进行，内容的检测也在服务端执行，通过检测以后被纳入有效数据存储，否则抛弃。内容的发送会被加密打包，防止被第三方抓包破解。
主播画像模型(在实际直播中通常以智能语音机器人的形式呈现)将分析结果反馈给直播间主播或用户的时机主要有三个场景：1.和语音机器人的交互不多(如首次使用)，服务端根据相似直播环境和内容下其他用户的画像结果下发推荐的策略；2.服务端根据时间戳和直播间上下文预测目前的环境(用户和机器人长时间未互动)，就根据用户的画像结果下发推荐的策略；3.当前直播环境处于特殊场景中(节日，比赛等)，服务端推荐基于特殊场景的策略。
图8是根据一实施例示出的一种直播辅助装置框图。参照图8，该装置包括信息获取单元801、模型确定单元802和辅助直播单元803。
信息获取单元801，被配置为执行获取目标直播间的第一属性信息；其中，第一属性信息为目标直播间的历史直播活动相关的属性信息；
模型确定单元802，被配置为执行根据第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
辅助直播单元803，被配置为执行根据主播画像模型，辅助目标直播间对应的主播进行直播活动。
在一些实施例中，所述模型确定单元802具体被配置为执行：
根据所述第一属性信息对所述初始主播画像模型进行训练，辅助所述目标直播间对应的主播进行直播活动，并得到第二属性信息；其中，所述第二属性信息为进行直播活动的实时属性信息；
基于所述第二属性信息更新所述第一属性信息，迭代训练所述主播画像模型。
在一些实施例中，所述信息获取单元801，还可以被配置为执行获取预设的第三属性信息；其中，所述第三属性信息为所述目标直播间对应的直播活动相关的属性信息；
所述模型确定单元802，还被配置为执行根据所述第一属性信息和所述第三属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
在一些实施例中，所述信息获取单元801，还可以被配置为执行获取与所述第一属性信息相关的第四属性信息；其中，所述第四属性信息为与所述目标直播间关联的直播间的属性信息；
所述模型确定单元802，还被配置为执行根据所述第一属性信息和所述第四属性信息训练预设的初始主播画像模型，得到所述主播画像模型。
在一些实施例中，所述信息获取单元801可以被配置为执行：
获取直播间属性数据集；
对所述直播间属性数据集与所述第一属性信息进行相关性分析，将相关性满足预设条件的直播间属性数据集确定为所述第四属性信息。
在一些实施例中，所述辅助直播单元803可以被配置为执行：
对所述目标直播间的指令信息进行检测；
当检测到所述目标直播间发起指令时，响应于所述指令，并根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
在一些实施例中，所述辅助直播单元803可以被配置为执行：
对所述第一属性信息进行检测；
当所述第一属性信息满足预设的轮询规则时，根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
关于上述实施例中的装置，其中各个单元执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图9是根据一实施例示出的一种用于直播辅助的电子设备900的框图。例如，设备900可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图9，设备900可以包括以下一个或多个组件：处理组件902，存储器904，电力组件906，多媒体组件908，音频组件910，输入/输出(Input/Output，I/O)的接口912，传感器组件914，以及通信组件916。
处理组件902通常控制设备900的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件902可以包括一个或多个处理器920来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件902可以包括一个或多个模块，便于处理组件902和其他组件之间的交互。例如，处理组件902可以包括多媒体模块，以方便多媒体组件908和处理组件902之间的交互。
存储器904被配置为存储各种类型的数据以支持在设备900的操作。这些数据的示例包 括用于在设备900上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器904可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(Static Random-Access Memory，SRAM)，电可擦除可编程只读存储器(Electrically-Erasable Programmable Read-Only Memory，EEPROM)，可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)，可编程只读存储器(Programmable Read Only Memory，PROM)，只读存储器(Read Only Memory，ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件906为设备900的各种组件提供电力。电源组件906可以包括电源管理系统，一个或多个电源，及其他与为设备900生成、管理和分配电力相关联的组件。
多媒体组件908包括在设备900和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(Liquid Crystal Display，LCD)和触摸面板(Touch Panel，TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件908包括一个前置摄像头和/或后置摄像头。当设备900处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件910被配置为输出和/或输入音频信号。例如，音频组件910包括一个麦克风(Microphone，MIC)，当设备900处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器904或经由通信组件916发送。在一些实施例中，音频组件910还包括一个扬声器，用于输出音频信号。
I/O接口912为处理组件902和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件914包括一个或多个传感器，用于为设备900提供各个方面的状态评估。例如，传感器组件914可以检测到设备900的打开/关闭状态，组件的相对定位，例如组件为设备900的显示器和小键盘，传感器组件914还可以检测设备900或设备900一个组件的位置改变，用户与设备900接触的存在或不存在，设备900方位或加速/减速和设备900的温度变化。传感器组件914可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件914还可以包括光传感器，如互补性氧化金属半导体(Complementary Metal-Oxide Semiconductor，CMOS)或电荷藕合器件(Charge Coupled Device，CCD)图像传 感器，用于在成像应用中使用。在一些实施例中，该传感器组件914还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件916被配置为便于设备900和其他设备之间有线或无线方式的通信。设备900可以接入基于通信标准的无线网络，如无线保真(Wireless-Fidelity，WiFi)，运营商网络(如2G、3G、4G或5G)，或它们的组合。在一个实施例中，通信组件916经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个实施例中，通信组件916还包括近场通信(Near Field Communication，NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别((Radio Frequency Identification，RFID)技术，红外数据协会(Infrared Data Association，IrDA)技术，超宽带(Ultra Wide Band，UWB)技术，蓝牙(Bluetooth，BT)技术和其他技术来实现。
在一些实施例中，设备900可以被一个或多个应用专用集成电路(Application Specific Integrated Circuit，ASIC)、数字信号处理器(Digital Signal Processor，DSP)、数字信号处理设备(Digital Signal Processor Device，DSPD)、可编程逻辑器件(Programmable Logic Device，PLD)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在一些实施例中，还提供了一种包括指令的存储介质，例如包括指令的存储器904，上述指令可由设备900的处理器920执行以完成上述方法。在一些实施例中，存储介质可以是非临时性计算机可读存储介质，例如，非临时性计算机可读存储介质可以是ROM、随机存取存储器(Random Access Memory，RAM)、光盘只读存储器(Compact Disk Read Only Memory，CD-ROM)、磁带、软盘和光数据存储设备等。
图10是根据一实施例示出的一种用于直播辅助的装置1000的框图。例如，装置1000可以被提供为一服务器。参照图10，装置1000包括处理组件1022，其进一步包括一个或多个处理器，以及由存储器1032所代表的存储器资源，用于存储可由处理组件1022的执行的指令，例如应用程序。存储器1032中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1022被配置为执行指令，以执行上述直播辅助方法。
装置1000还可以包括一个电源组件1026被配置为执行装置1000的电源管理，一个有线或无线网络接口1050被配置为将装置1000连接到网络，和一个输入输出(I/O)接口1058。装置1000可以操作基于存储在存储器1032的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
本领域技术人员在考虑说明书及实践这里公开的内容后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权 利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (22)

  1. 一种直播辅助方法，包括：
    获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
    根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
    根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  2. 根据权利要求1所述的直播辅助方法，所述根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型，包括：
    根据所述第一属性信息对所述初始主播画像模型进行训练，辅助所述目标直播间对应的主播进行直播活动，得到第二属性信息；其中，所述第二属性信息为进行直播活动的实时属性信息；
    基于所述第二属性信息更新所述第一属性信息，迭代训练所述主播画像模型。
  3. 根据权利要求1所述的直播辅助方法，所述根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型，包括：
    获取预设的第三属性信息；其中，所述第三属性信息为所述目标直播间对应的直播活动相关的属性信息；
    根据所述第一属性信息和所述第三属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  4. 根据权利要求1所述的直播辅助方法，所述根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型，包括：
    获取与所述第一属性信息相关的第四属性信息；其中，所述第四属性信息为与所述目标直播间关联的直播间的属性信息；
    根据所述第一属性信息和所述第四属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  5. 根据权利要求4所述的直播辅助方法，所述获取与所述第一属性信息相关的第四属性信息，包括：
    获取直播间属性数据集；
    对所述直播间属性数据集与所述第一属性信息进行相关性分析，将相关性满足预设条件的直播间属性数据集确定为所述第四属性信息。
  6. 根据权利要求1所述的直播辅助方法，所述根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动，包括：
    对所述目标直播间的指令信息进行检测；
    当检测到所述目标直播间发起指令时，响应于所述指令，并根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  7. 根据权利要求1所述的直播辅助方法，所述根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动，包括：
    对所述第一属性信息进行检测；
    当所述第一属性信息满足预设的轮询规则时，根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  8. 一种直播辅助装置，包括：
    信息获取单元，被配置为执行获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
    模型确定单元，被配置为执行根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
    辅助直播单元，被配置为执行根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  9. 根据权利要求8所述的直播辅助装置，所述模型确定单元具体被配置为执行：
    根据所述第一属性信息对所述初始主播画像模型进行训练，辅助所述目标直播间对应的主播进行直播活动，得到第二属性信息；其中，所述第二属性信息为进行直播活动的实时属性信息；
    基于所述第二属性信息更新所述第一属性信息，迭代训练所述主播画像模型。
  10. 根据权利要求8所述的直播辅助装置，
    所述信息获取单元，还被配置为执行获取预设的第三属性信息；其中，所述第三属性信息为所述目标直播间对应的直播活动相关的属性信息；
    所述模型确定单元，还被配置为执行根据所述第一属性信息和所述第三属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  11. 根据权利要求8所述的直播辅助装置，
    所述信息获取单元，还被配置为执行获取与所述第一属性信息相关的第四属性信息；其中，所述第四属性信息为与所述目标直播间关联的直播间的属性信息；
    所述模型确定单元，还被配置为执行根据所述第一属性信息和所述第四属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  12. 根据权利要求11所述的直播辅助装置，所述信息获取单元具体被配置为执行：
    获取直播间属性数据集；
    对所述直播间属性数据集与所述第一属性信息进行相关性分析，将相关性满足预设条件的直播间属性数据集确定为所述第四属性信息。
  13. 根据权利要求8所述的直播辅助装置，所述辅助直播单元具体被配置为执行：
    对所述目标直播间的指令信息进行检测；
    当检测到所述目标直播间发起指令时，响应于所述指令，并根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  14. 根据权利要求8所述的直播辅助装置，所述辅助直播单元具体被配置为执行：
    对所述第一属性信息进行检测；
    当所述第一属性信息满足预设的轮询规则时，根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  15. 一种电子设备，包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令时，
    获取目标直播间的第一属性信息；其中，所述第一属性信息为所述目标直播间的历史直播活动相关的属性信息；
    根据所述第一属性信息，训练预设的初始主播画像模型，得到主播画像模型；
    根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  16. 根据权利要求15所述的电子设备，所述处理器具体被配置为执行：
    根据所述第一属性信息对所述初始主播画像模型进行训练，辅助所述目标直播间对应的主播进行直播活动，得到第二属性信息；其中，所述第二属性信息为进行直播活动的实时属性信息；
    基于所述第二属性信息更新所述第一属性信息，迭代训练所述主播画像模型。
  17. 根据权利要求15所述的电子设备，所述处理器还被配置为执行：
    获取预设的第三属性信息；其中，所述第三属性信息为所述目标直播间对应的直播活动相关的属性信息；
    根据所述第一属性信息和所述第三属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  18. 根据权利要求15所述的电子设备，所述处理器还被配置为执行：
    获取与所述第一属性信息相关的第四属性信息；其中，所述第四属性信息为与所述目标直播间关联的直播间的属性信息；
    根据所述第一属性信息和所述第四属性信息，训练预设的初始主播画像模型，得到所述主播画像模型。
  19. 根据权利要求18所述的电子设备，所述处理器具体被配置为执行：
    获取直播间属性数据集；
    对所述直播间属性数据集与所述第一属性信息进行相关性分析，将相关性满足预设条件的直播间属性数据集确定为所述第四属性信息。
  20. 根据权利要求15所述的电子设备，所述处理器具体被配置为执行：
    对所述目标直播间的指令信息进行检测；
    当检测到所述目标直播间发起指令时，响应于所述指令，并根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  21. 根据权利要求15所述的电子设备，所述处理器具体被配置为执行：
    对所述第一属性信息进行检测；
    当所述第一属性信息满足预设的轮询规则时，根据所述主播画像模型，辅助所述目标直播间对应的主播进行直播活动。
  22. 一种存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得电子设备能够执行如权利要求1至7中任一项所述的直播辅助方法。
PCT/CN2020/128677 2020-01-22 2020-11-13 直播辅助方法及电子设备 WO2021147480A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20916077.9A EP4096222A4 (en) 2020-01-22 2020-11-13 LIVE BROADCASTING SUPPORT PROCEDURE AND ELECTRONIC DEVICE
US17/407,495 US20210385506A1 (en) 2020-01-22 2021-08-20 Method and electronic device for assisting live streaming

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010074650.6 2020-01-22
CN202010074650.6A CN111314719A (zh) 2020-01-22 2020-01-22 直播辅助方法、装置、电子设备及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/407,495 Continuation US20210385506A1 (en) 2020-01-22 2021-08-20 Method and electronic device for assisting live streaming

Publications (1)

Publication Number Publication Date
WO2021147480A1 true WO2021147480A1 (zh) 2021-07-29

Family

ID=71146941

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/128677 WO2021147480A1 (zh) 2020-01-22 2020-11-13 直播辅助方法及电子设备

Country Status (4)

Country Link
US (1) US20210385506A1 (zh)
EP (1) EP4096222A4 (zh)
CN (1) CN111314719A (zh)
WO (1) WO2021147480A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111314719A (zh) * 2020-01-22 2020-06-19 北京达佳互联信息技术有限公司 直播辅助方法、装置、电子设备及存储介质
CN111986301A (zh) * 2020-09-04 2020-11-24 网易（杭州）网络有限公司 直播中数据处理的方法及装置、电子设备、存储介质
CN114697688A (zh) * 2020-12-29 2022-07-01 阿里巴巴集团控股有限公司 直播策略推荐方法、互动方法、装置、设备和存储介质
CN114727123B (zh) * 2021-02-03 2023-03-17 北京城市网邻信息技术有限公司 一种直播间的数据处理方法和装置
CN113784155A (zh) * 2021-08-12 2021-12-10 阿里巴巴达摩院(杭州)科技有限公司 基于直播间的数据处理方法及装置
CN114268839A (zh) * 2021-12-17 2022-04-01 北京达佳互联信息技术有限公司 视频发布账户筛选方法、装置、电子设备及存储介质
CN114339282A (zh) * 2021-12-27 2022-04-12 上海哔哩哔哩科技有限公司 直播互动中主播形象图片的传输方法及装置
CN115065834A (zh) * 2022-05-16 2022-09-16 杭州网易云音乐科技有限公司 流量扶持方法、装置、介质和计算设备
CN117319758B (zh) * 2023-10-13 2024-03-12 南京霍巴信息科技有限公司 一种基于云平台的直播方法及直播系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106878820A (zh) * 2016-12-09 2017-06-20 北京小米移动软件有限公司 直播互动方法及装置
US20180091832A1 (en) * 2016-09-27 2018-03-29 Clarifai, Inc. Prediction model training via live stream concept association
CN109491564A (zh) * 2018-10-18 2019-03-19 深圳前海达闼云端智能科技有限公司 虚拟机器人的互动方法，装置，存储介质及电子设备
CN109936774A (zh) * 2019-03-29 2019-06-25 广州虎牙信息科技有限公司 虚拟形象控制方法、装置及电子设备
CN110035325A (zh) * 2019-04-19 2019-07-19 广州虎牙信息科技有限公司 弹幕回复方法、弹幕回复装置和直播设备
CN111314719A (zh) * 2020-01-22 2020-06-19 北京达佳互联信息技术有限公司 直播辅助方法、装置、电子设备及存储介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10129251B1 (en) * 2014-02-11 2018-11-13 Morphotrust Usa, Llc System and method for verifying liveliness
US20170111418A1 (en) * 2015-10-16 2017-04-20 Microsoft Technology Licensing, Llc Two-way interactive streaming media
CN108073671A (zh) * 2017-04-12 2018-05-25 北京市商汤科技开发有限公司 业务对象推荐方法、装置和电子设备
CN108076353A (zh) * 2017-05-18 2018-05-25 北京市商汤科技开发有限公司 业务对象推荐方法、装置、存储介质和电子设备
CN108769772B (zh) * 2018-05-28 2019-06-14 广州虎牙信息科技有限公司 直播间显示方法、装置、设备及存储介质
CN108900923B (zh) * 2018-07-20 2021-03-09 广州方硅信息技术有限公司 推荐直播模板的方法和装置
CN109241242B (zh) * 2018-08-23 2021-02-02 武汉斗鱼网络科技有限公司 一种直播间话题推荐方法、装置、服务器及存储介质
CN110401844A (zh) * 2019-08-22 2019-11-01 北京字节跳动网络技术有限公司 视频直播策略的生成方法、装置、设备及可读介质
CN110446057B (zh) * 2019-08-30 2022-05-17 北京字节跳动网络技术有限公司 直播辅助数据的提供方法、装置、设备及可读介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180091832A1 (en) * 2016-09-27 2018-03-29 Clarifai, Inc. Prediction model training via live stream concept association
CN106878820A (zh) * 2016-12-09 2017-06-20 北京小米移动软件有限公司 直播互动方法及装置
CN109491564A (zh) * 2018-10-18 2019-03-19 深圳前海达闼云端智能科技有限公司 虚拟机器人的互动方法，装置，存储介质及电子设备
CN109936774A (zh) * 2019-03-29 2019-06-25 广州虎牙信息科技有限公司 虚拟形象控制方法、装置及电子设备
CN110035325A (zh) * 2019-04-19 2019-07-19 广州虎牙信息科技有限公司 弹幕回复方法、弹幕回复装置和直播设备
CN111314719A (zh) * 2020-01-22 2020-06-19 北京达佳互联信息技术有限公司 直播辅助方法、装置、电子设备及存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4096222A4

Also Published As

Publication number Publication date
US20210385506A1 (en) 2021-12-09
EP4096222A4 (en) 2023-07-19
EP4096222A1 (en) 2022-11-30
CN111314719A (zh) 2020-06-19

Similar Documents

Publication Publication Date Title
WO2021147480A1 (zh) 直播辅助方法及电子设备
US11196930B1 (en) Display device content selection through viewer identification and affinity prediction
RU2597232C1 (ru) Способ предоставления видео в режиме реального времени и устройство для его осуществления, а также сервер и терминальное устройство
RU2667606C2 (ru) Способ и аппарат для управления устройством и терминальное устройство
KR101967658B1 (ko) 영상 통화 장치 및 영상 통화 방법
US20210375281A1 (en) Voice control method and apparatus, and computer storage medium
KR102311603B1 (ko) 단말기 및 그것의 동작 방법
RU2640632C2 (ru) Способ и устройство для доставки информации
US11244228B2 (en) Method and device for recommending video, and computer readable storage medium
TW202139140A (zh) 圖像重建方法及圖像重建裝置、電子設備和電腦可讀儲存媒體
WO2018058899A1 (zh) 一种智能终端的音量调节方法及其装置
US10334282B2 (en) Methods and devices for live broadcasting based on live broadcasting application
JP2011114591A (ja) 表示制御装置、及び、表示制御システム、並びに、遠隔制御装置
CN109660873B (zh) 基于视频的交互方法、交互装置和计算机可读存储介质
WO2022135005A1 (zh) 一种基于通话的屏幕共享方法、装置、设备及存储介质
WO2017181545A1 (zh) 对象监控方法及装置
US20230007312A1 (en) Method and apparatus for information interaction in live broadcast room
CN112153396A (zh) 页面展示方法、装置、系统和存储介质
US11553019B2 (en) Method, apparatus, electronic device and storage medium for acquiring programs in live streaming room
CN114189719B (zh) 视频信息提取方法、装置、电子设备及存储介质
US20200250708A1 (en) Method and system for providing recommended digital content item to electronic device
KR102051828B1 (ko) 영상 통화 방법 및 영상 통화 중개 장치
CN114697611B (zh) 来访对讲控制方法、对讲控制装置、系统、电子设备及存储介质
CN114726816B (zh) 一种建立关联关系的方法、装置、电子设备和存储介质
US11290530B2 (en) Customizable, pull-based asset transfer requests using object models

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: 20916077

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020916077

Country of ref document: EP

Effective date: 20220822