WO2023045939A1 - 一种直播处理方法、直播平台、存储介质及电子设备 - Google Patents

一种直播处理方法、直播平台、存储介质及电子设备 Download PDF

Info

Publication number
WO2023045939A1
WO2023045939A1 PCT/CN2022/120070 CN2022120070W WO2023045939A1 WO 2023045939 A1 WO2023045939 A1 WO 2023045939A1 CN 2022120070 W CN2022120070 W CN 2022120070W WO 2023045939 A1 WO2023045939 A1 WO 2023045939A1
Authority
WO
WIPO (PCT)
Prior art keywords
keyword
information
prompt information
prompt
live broadcast
Prior art date
Application number
PCT/CN2022/120070
Other languages
English (en)
French (fr)
Inventor
刘伟科
郐洪楠
韩卫召
沈俊杰
邵京平
Original Assignee
北京沃东天骏信息技术有限公司
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 北京沃东天骏信息技术有限公司 filed Critical 北京沃东天骏信息技术有限公司
Publication of WO2023045939A1 publication Critical patent/WO2023045939A1/zh

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
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • 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
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233—Processing of audio elementary streams
    • 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
    • H04N21/43—Processing 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
    • H04N21/439—Processing of audio elementary streams
    • 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
    • H04N21/462—Content or additional data management, e.g. creating a master electronic program guide from data received from the Internet and a Head-end, controlling the complexity of a video stream by scaling the resolution or bit-rate based on the client capabilities
    • H04N21/4627—Rights management associated to the content
    • 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
    • H04N21/47—End-user applications
    • H04N21/488—Data services, e.g. news ticker
    • H04N21/4882—Data services, e.g. news ticker for displaying messages, e.g. warnings, reminders

Definitions

  • the embodiments of the present application relate to the technical field of live broadcast, for example, to a live broadcast processing method, a live broadcast platform, a storage medium, and electronic equipment.
  • live broadcast industry With the development of Internet technology and the improvement of social civilization, the live broadcast industry is becoming more and more mature. Unlike the short video field, which is reviewed first and released later, live broadcasts have real-time characteristics. Therefore, the influence of live broadcast is huge.
  • the current supervision methods for live broadcasting include: 1. Laws and regulations.
  • the country has general laws and regulations for live broadcasting to curb illegal live broadcasting, but the law is the bottom line and can only prevent violations of laws and regulations
  • Embodiments of the present application provide a live broadcast processing method, a live broadcast platform, a storage medium, and electronic equipment, so as to improve the standardization of live broadcast.
  • the embodiment of the present application provides a live broadcast processing method, including:
  • Obtain the audio stream in the live media stream carry out keyword recognition to the audio stream based on the current keyword library, and determine whether there is at least one keyword in the keyword library in the audio stream;
  • the prompt information is sent to the live broadcast terminal for display, and the prompt information is added to the live media stream.
  • the embodiment of the present application also provides a live broadcast platform, including:
  • the keyword recognition module is configured to obtain the audio stream in the live media stream, carry out keyword recognition to the audio stream based on the current keyword library, and determine whether there is at least one key in the keyword library in the audio stream word;
  • the reminder information extraction module is configured to extract corresponding reminder information from a preset reminder content library based on the identified keywords if the keywords identified in the audio stream meet the information extraction trigger conditions, wherein the
  • the prompt content database includes prompt information corresponding to any keyword in the keyword database;
  • the prompt information display module is configured to send the prompt information to the live broadcast terminal for display, and add the prompt information to the live media stream.
  • the embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the processor executes the program, it implements the The live broadcast processing method provided by any embodiment.
  • the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the live broadcast processing method provided in any embodiment of the present application is implemented.
  • FIG. 1 is a schematic flowchart of a live broadcast processing method provided in Embodiment 1 of the present application;
  • FIG. 2 is a schematic diagram of a live broadcast scene provided by an embodiment of the present application.
  • Fig. 3 is a schematic diagram of displaying prompt information on a live broadcast terminal provided by an embodiment of the present application
  • FIG. 4 is a schematic flowchart of a live broadcast processing method provided in Embodiment 2 of the present application.
  • FIG. 5 is a schematic structural diagram of a live broadcast platform provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 1 is a schematic flow diagram of a live broadcast processing method provided by Embodiment 1 of the present application. This embodiment is applicable to the situation of prompting the broadcaster's non-standard live broadcast content during the live broadcast process.
  • This method can be implemented by the embodiment of the present application.
  • Provided live broadcast platform to perform, the live broadcast platform can be implemented by software and/or hardware, the live broadcast platform can be configured on electronic computing devices, including the following steps:
  • the keyword identified in the audio stream satisfies the information extraction trigger condition, extract corresponding prompt information from the preset prompt content library based on the identified keyword, wherein the prompt content library contains It includes prompt information corresponding to any keyword in the keyword library.
  • FIG. 2 is a schematic diagram of a live broadcast scene provided by an embodiment of the present application.
  • the live broadcast terminal and the client are respectively connected to the live broadcast platform.
  • the live broadcast end and the client end can also be the same electronic device, and the distinction between different user rights can be realized through different display interfaces, or by logging in to different APPs differentiate, or by verifying different role identities.
  • the live broadcast terminal and the client can be terminal devices such as mobile phones and tablet computers, which have different permissions.
  • the live broadcast terminal is used to provide live broadcast data, and has the live background management authority and the live broadcast object setting authority.
  • the client can watch the live broadcast, and only has the right to watch the live broadcast and the transaction right to the live broadcast objects in the live broadcast.
  • the live broadcast terminal needs to be registered, and the live broadcast platform is equipped with a registration module, which receives the user's registration request and user information, registers the user's live broadcast identity, and has corresponding permissions after successful registration.
  • a registration module which receives the user's registration request and user information, registers the user's live broadcast identity, and has corresponding permissions after successful registration.
  • the authority of the device is determined, that is, the device is determined to be one of the live broadcast terminal and the client.
  • you can set up a live broadcast set the live broadcast object (such as the item or game to be introduced), generate the live media stream, and transmit the generated live media stream to the live broadcast platform in real time, so that the client can obtain the live media stream from the live broadcast platform.
  • the live broadcast end includes local live broadcast collection equipment, for example, live broadcast collection equipment includes but is not limited to cameras, microphones, mobile phones and other terminal equipment.
  • the live broadcast application on the terminal device calls the local live broadcast acquisition device to collect audio streams and video streams to form a live media stream, and sends the live media stream to a live broadcast platform (such as a live server) through the live broadcast application on the terminal device.
  • the live broadcast platform conducts authority identification on the information of the live broadcast terminal. If the live broadcast terminal has the live broadcast authority, it will receive the live media stream and store it. When a stream is requested, the live media stream is sent to the client for display.
  • the live broadcast end transmits the audio stream and the video stream to the live broadcast platform respectively, and the audio stream and the video stream respectively carry timestamps, and the live broadcast platform can fuse the audio stream and the video stream through the timestamp to obtain the live media flow.
  • the live broadcast platform can directly obtain the audio stream sent by the live broadcast terminal in real time.
  • the audio stream in the live media stream can also be obtained with a delay, and the acquisition method can be import, etc., which is not limited.
  • the live broadcast terminal processes the collected audio stream and video stream to obtain a live media stream and transmits it to the live broadcast platform, and the live broadcast platform extracts the audio stream from the live media stream and performs keyword recognition on the audio stream.
  • the live broadcast platform maintains a keyword database in advance, and the keyword database includes keywords to be identified.
  • the keyword database may include but not limited to keywords of laws and regulations, sensitive words and hot words, wherein keywords of laws and regulations may be keywords extracted from laws and regulations, and sensitive words may be based on requirements It is set, sensitive words in different periods can be different, and hot words can be determined according to the popularity of discussions.
  • the type of keywords in the keyword library can be set according to the live broadcast type of the historical live broadcast terminal. For example, the live broadcast type includes online game live broadcast.
  • the keywords in the keyword library can include game-violating words.
  • the live broadcast platform regularly determines whether there is a new live broadcast type, and if there is a new live broadcast type, updates the keyword database based on the newly added live broadcast type, that is, adds keywords of the newly added live broadcast type to the keyword database.
  • the source of the keyword is set in advance, the keyword search is performed on multiple sources according to the preset time interval, and the determined new keyword is updated to the keyword library.
  • the source of the keywords of laws and regulations may be the publishing address of laws and regulations, such as national law websites, etc.
  • the source of sensitive words may be official media
  • the source of hot words may be official media.
  • the above source addresses are stored in the form of an array, which is convenient for quickly calling multiple addresses for keyword update.
  • different keyword update frequencies may be determined based on keyword types. For example, keywords of laws and regulations may be updated at a frequency of 1 week/time, and sensitive words may be updated at a frequency of 1 day/time. , hot words can be updated at a frequency of 1 hour/time.
  • the keyword update can be performed by generating a timed task, respectively calling a source address for keyword query, and updating the keyword library if a new keyword is found.
  • multiple timed tasks may be processed in parallel to improve the efficiency of keyword query and improve the real-time performance and accuracy of keywords.
  • performing keyword recognition on an audio stream may be: framing the audio stream to obtain multiple speech segments, wherein there is a preset duration overlap between adjacent speech segments, and performing keyword recognition on any speech segment identify.
  • the framing of the audio stream can be based on the preset duration, that is, multiple speech segments are speech segments of the same duration;
  • the audio stream is divided into frames to avoid the inaccurate recognition caused by the segmentation of keywords.
  • the sentence segmentation position can be a position in the audio stream where the amplitude is smaller than a preset value.
  • the keyword recognition process for each speech segment it can be to identify the phonemes in the speech segment, wherein, Chinese phonemes can use initial consonants and finals as phoneme sets, and English factors can be determined based on preset phoneme sets, and the phonemes of keywords and The phonemes in the speech segment are matched to determine the keywords included in the audio stream.
  • the hidden Markov model can be used to preset the recognition path based on keywords, and only follow the preset path for recognition during recognition, thereby avoiding the multi-frame problem. Exemplarily, "d i q i c i r en k ou p u ch a" is identified in the audio stream, and the combined result is "the seventh population census".
  • an information extraction trigger condition is set. After determining that the audio stream includes keywords, determine whether the identified keywords meet the information extraction trigger conditions, When it is determined that the identified keyword satisfies the triggering condition for information extraction, it is triggered to send prompt information to the live broadcast end, and when it is determined that the identified keyword does not meet the triggering condition for information extraction, the keyword is continuously identified. It should be noted that at least one keyword may be included in the same audio stream, and whether each keyword satisfies the information extraction trigger condition is identified separately, and at least one keyword does not interfere with each other, based on keywords that meet the information extraction trigger condition Trigger to extract prompt information.
  • the triggering condition for information extraction is the cumulative number of thresholds.
  • the cumulative number of times each keyword is recognized is recorded, that is, when any keyword is recognized, Add one to the accumulated times of the keyword.
  • the triggering condition for information extraction includes that the cumulative number of identified keywords in the audio stream exceeds a preset threshold.
  • the preset threshold may be 5 times or 10 times, which is not limited.
  • the triggering condition for information extraction includes that the cumulative number of identified keywords within a preset sliding window exceeds a preset threshold.
  • a sliding time window structure is used to manage the threshold value of keywords.
  • the sliding time window structure means that when operating at any time node, only the most recent n-time records are saved, and only the most recent n-time records are queried. And cut out the expired results.
  • the duration of n may be 30 minutes.
  • the recognition times with a duration of 30 minutes from the current time are retained.
  • different keywords may correspond to different preset thresholds.
  • the preset threshold of keyword A can be 1
  • the preset threshold of keyword B can be 10, which can be set according to the restriction requirements of keywords.
  • the information extraction trigger condition corresponding to the keyword is matched.
  • the accumulated quantity of each keyword is counted, and matched with the corresponding information extraction trigger condition. For keywords that match successfully, trigger extraction prompt information.
  • the live broadcast platform maintains a prompt content database in advance, and the prompt content database includes prompt information corresponding to each keyword in the keyword database.
  • the prompt information may be updated in real time to ensure the accuracy and effectiveness of the prompt content library.
  • the prompt content database may store the keywords in association with the corresponding prompt information, match the keywords that meet the information extraction triggering conditions in the prompt content database, and extract the prompt information corresponding to the successfully matched keywords.
  • the prompt information may be in a format such as text or a picture, which is not limited.
  • FIG. 3 is a schematic diagram of a live broadcast terminal displaying prompt information provided by an embodiment of the present application.
  • FIG. 3 is only an example, and the content, display form and display position of the prompt information are not limited, and adjustments may be made according to different prompt information and different needs of live broadcasters.
  • the display area of the prompt information is adjustable in size, and the size of the display is determined according to the data length of the display area.
  • the display area of the prompt information may be of fixed size, for example based on a fixed The screen-to-body ratio determines the size of the display area, and displays in batches according to the data length of the prompt information.
  • the position of the display area of the prompt information may be fixed, for example, in the upper left corner or upper right corner of the display interface, and the display area may be manually adjusted by the live broadcaster, as shown in FIG. 3 .
  • the position of the display area of the prompt information can be determined according to the display content of the current display interface, for example, the display area is set in a blank position of the display interface to avoid blocking the existing display content, and at the same time, there is no need for a live broadcaster manual adjustment.
  • the display duration of the prompt information is fixed, for example, after a display duration N, it will be automatically closed.
  • the display time of the prompt information may be closed manually after the display time exceeds the preset time length, wherein the preset time length may be less than the time length N.
  • the display duration of the prompt information may be determined according to the data length of the prompt information, and is positively correlated with the data length.
  • sending the prompt information to the live broadcast terminal for display includes: calling the display code of the preset interactive interface, filling the prompt information into the corresponding position of the display code, and displaying the filled The code is sent to the live broadcast terminal, so that the live broadcast terminal displays an interactive interface including prompt information.
  • the live broadcast platform presets multiple interactive interfaces (for example, different styles of interactive interfaces), which can be randomly called in multiple display interfaces, or call the corresponding display interface according to the type of live broadcast, or call the display interface specified by the live broadcast terminal .
  • the display code of the interactive interface can be source code or Html code, for example, APP corresponds to source code, and webpage corresponds to Html code, and the code in the corresponding format can be called according to the type of live broadcast software on the live broadcast terminal.
  • the prompt information when the prompt information is displayed to the live broadcast terminal, the prompt information is added to the live media stream and displayed to the watching client, so that the user can watch the prompt information and avoid the user being misled by irregular remarks .
  • keyword identification is performed on the audio stream in the live media stream by setting the keyword library, so as to determine whether there are speeches including keywords on the live broadcast terminal.
  • the corresponding prompt information is called from the prompt content library, and the prompt information is displayed to the live broadcaster and viewers.
  • the prompt information in the prompt content library is a specification with credibility Information, by displaying prompt information to show correct information to live broadcasters and viewers, to prevent live broadcasters from conveying irregular information to users when they do not understand the correct information, and to prevent users from being misled by irregular speeches, providing the standardization of live broadcast.
  • the prompt information after sending the prompt information to the live broadcast terminal for display, it also includes: continuing to identify the keyword for the audio stream, and accumulating the number of times of identification; When the number of times meets the alert threshold, an alert alert is generated.
  • the reminder thresholds corresponding to different keywords may be different, for example, they may be N times the preset threshold in the information extraction trigger condition, where N is a positive number greater than 1.
  • the alert reminder may be a violation reminder.
  • the reminder threshold can be thresholds of multiple levels. When the cumulative recognition times of keywords meet the low-level thresholds, prompt information is generated. When the cumulative recognition times of keywords meet the high-level thresholds, violation penalties or manual intervention are triggered. , such as closing the live room, etc.
  • FIG. 4 is a schematic flow chart of a live broadcast processing method provided in Embodiment 2 of the present application.
  • the method for determining the prompt information in the prompt content library includes: for any keyword in the keyword library, querying multiple queries in the address library based on preset information The address periodically acquires prompt information, and updates the prompt content library based on the acquired prompt information.
  • the method of the embodiment of the present application includes the following steps:
  • S240 Send the prompt information to the live broadcast terminal for display, and add the prompt information to the live media stream.
  • step S210 and steps S220-S240 may be executed synchronously.
  • Step S210 is executed cyclically to update the prompt content database in real time to ensure the accuracy and timeliness of the prompt content database.
  • the prompt content library called in step S230 is the prompt content library at the current moment.
  • the live broadcast platform is pre-set with an information query address database, and for each keyword in the keyword database, periodically query prompt information in multiple information query locations, and update the prompt content database.
  • periodically obtaining prompt information based on a plurality of query addresses in the preset information query address library includes: determining a query cycle based on the type and popularity status of keywords, and generating query tasks based on the query cycle, wherein, The query task is used to query multiple query addresses in the address library based on preset information to obtain prompt information.
  • keywords include but are not limited to legal and regulatory keywords, sensitive words, and hot words.
  • the frequency of changes in the reminder information for legal and regulatory keywords, sensitive words, and hot words Increases in turn, correspondingly, the query cycle decreases in turn.
  • the query period of laws and regulations keywords may be 1 week/time
  • the query period of sensitive words may be 1 day/time
  • the query period of hot words may be 1 hour/time.
  • a web service framework such as using java-web services
  • a timing scheduling function include job, quartz, etc.
  • Any timing scheduling function can perform cyclic scheduling of functions at specified intervals.
  • parallel information query tasks are performed on multiple keywords in the keyword library, so as to improve the efficiency of information query. Wherein, when any keyword calling information query task is not finished, the same keyword is not called repeatedly.
  • periodically obtain prompt information based on a plurality of query addresses in the preset information query address library including: in any query cycle, generate a keyword query task based on the information query address performing the query, and execute the key
  • the word query task is to determine tag address information including the keyword, and extract prompt information including the keyword based on the tag address information.
  • any information query address is called to generate a keyword query task, and keyword query is performed on the data corresponding to the information query address.
  • the information query address is the official address of the media, and a large amount of information is correspondingly stored in this address.
  • the keyword query task is used to carry out date cycle and page cycle keyword query on the information query address
  • the query instruction of the keyword query task includes a date field and a layout field, and the keyword query of the date cycle and the layout cycle is realized by updating the information of the date field and the layout field.
  • the same date in A newspaper The data includes eight pages. By traversing each page, the keyword query of the page cycle is realized.
  • the keyword query of the date cycle is realized, so as to avoid information omission and improve the comprehensiveness of information query through double cycles.
  • incremental query can be performed.
  • the first execution of the keyword query task can be to traverse all published dates and all layout data.
  • the keyword query task can be performed by traversing the data of the newly added date or the newly added layout, so as to improve the efficiency of information query.
  • the keyword query task may be to query tags in the information query address to obtain tag address information, and extract prompt information including keywords from data corresponding to the tag address information.
  • the tags can be article titles, subtitles, etc.
  • the keyword can be split, for example, the keyword is the seventh census, and the keyword can be split into "population", “seventh census” or " “Census” and so on, query tags based on split words to avoid missing problems caused by different words used in different articles. For example, tags including "population” can be used to extract prompt information to improve the comprehensiveness of prompt information extraction.
  • each keyword in the prompt content library may correspond to a prompt information.
  • the prompt information in the prompt content library may be the latest release, and/or , the information released by the most authoritative organization.
  • multiple information query addresses in the information query address database are respectively set with weights, and correspondingly, the prompt information queried from each information query address has a corresponding weight.
  • Multiple information query addresses in the information query address database include laws and regulations and official media, and their weights decrease in order.
  • the official media includes multiple information query addresses, and the multiple information query addresses of the official media may have the same weight or different weights, which can be set according to requirements.
  • updating the prompt content database based on the obtained prompt information includes: if the prompt content database does not include the prompt information of the keyword, adding the obtained prompt information and the corresponding keyword to the prompt content database. If the prompt content database includes the prompt information of the keyword, and the weight corresponding to the obtained prompt information is higher than the weight of the existing prompt information in the prompt content database, then update the prompt content database based on the obtained prompt information.
  • the prompt information queried by the high-weight information query address covers the prompt information queried by the low-weight information query address, so as to improve the authority and accuracy of the prompt information in the prompt content library.
  • the editorial of newspaper B is crawled for the first time, and entered into the prompt content library, and the data example is: the seventh census: ⁇ source: newspaper B, content:" ⁇ html>xxxxxB newspaper editorial xxxxxx ⁇ /html>” ⁇ , crawled to the editorial of A newspaper the next day, according to the weighting rules, the weight of A newspaper is higher than that of B newspaper, so the data becomes:
  • the prompt content library is updated based on the acquired prompt information.
  • the timeliness of the prompt information in the prompt content library is improved by overwriting the prompt information released earlier by the prompt information released later.
  • the reminder information queried by the high-weight information query address within a certain period of time can cover the reminder information queried by the low-weight information query address.
  • the release time is within the time period
  • the prompt information queried by the high-weight information query address cannot cover the prompt information queried by the low-weight information query address.
  • the obtained prompt information is discarded; if the weight of the obtained prompt information is lower than the weight of the prompt content library If the weight of the prompt information already in the content library exceeds a certain period of time, the existing prompt information in the prompt content library can be overwritten.
  • periodic information query is performed for each keyword to update the prompt information database, so as to ensure the timeliness of the prompt information database.
  • the prompt information is updated according to the weight of the information publishing organization, which ensures the authority and correctness of the prompt information.
  • the live broadcaster and the viewer are displayed, which improves the The standardization of live broadcast.
  • Fig. 5 is a schematic structural diagram of a live broadcast platform provided by an embodiment of the present application, the live broadcast platform includes:
  • the keyword identification module 310 is configured to obtain the audio stream in the live media stream, perform keyword identification on the audio stream based on the current keyword library, and determine whether there is at least one of the keyword library in the audio stream Key words;
  • the reminder information extraction module 320 is configured to extract corresponding reminder information from a preset reminder content library based on the identified keywords if the keywords identified in the audio stream meet the information extraction trigger conditions, wherein,
  • the prompt content library includes prompt information corresponding to any keyword in the keyword library;
  • the prompt information display module 330 is configured to send the prompt information to the live broadcast terminal for display, and add the prompt information to the live media stream.
  • the device also includes:
  • the prompt information obtaining module is configured to periodically obtain prompt information based on a plurality of query addresses in the preset information query address library for any keyword in the keyword database;
  • the prompt content library updating module is configured to update the prompt content library based on the obtained prompt information.
  • multiple information query addresses in the information query address library are respectively set with weights
  • Prompt content library update module is set to:
  • the update module of the prompt content library is also set to:
  • the prompt content library is updated based on the acquired prompt information.
  • the prompt information acquisition module is set to:
  • Keyword types include laws and regulations keywords, sensitive words and hot words
  • a query task is generated based on the query period, wherein the query task is used to query multiple query addresses in the address library based on preset information to obtain prompt information.
  • the prompt information acquisition module is set to:
  • a keyword query task is generated based on the information query address for query, and the keyword query task is executed to determine the tag address information including the keyword, wherein the keyword query task is used to query all Use the above information query address to perform date cycle and page cycle keyword query;
  • Prompt information including the keyword is extracted based on the tag address information.
  • the information extraction trigger condition includes that the cumulative number of recognized keywords in the audio stream exceeds a preset threshold, or the cumulative number of recognized keywords within a sliding window of a preset duration exceeded the preset threshold.
  • the prompt information display module 330 is set to:
  • the device also includes:
  • the module for accumulating the number of times of identification is configured to continue to identify the keyword for the audio stream after sending the prompt information to the live broadcast terminal for display, and accumulate the number of times of identification;
  • the reminder module is configured to generate an alarm reminder when the accumulated recognition times meet the reminder threshold.
  • the live broadcast platform provided in the embodiment of the present application can execute the live broadcast processing method provided in any embodiment of the present application, and has corresponding functional modules for executing the method.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application.
  • FIG. 6 shows a block diagram of an electronic device 12 suitable for implementing embodiments of the present application.
  • the electronic device 12 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiment of the present application.
  • Device 12 is typically an electronic device undertaking image classification functions.
  • electronic device 12 takes the form of a general-purpose computing device.
  • Components of the electronic device 12 may include, but are not limited to: at least one processor 16, a storage device 28, and a bus 18 connecting various system components (including the storage device 28 and the processor 16).
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to Industry Standard Architecture (Industry Standard Architecture, ISA) bus, Micro Channel Architecture (Micro Channel Architecture, MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards Association, VESA) local bus and peripheral component interconnect (Peripheral Component Interconnect, PCI) bus.
  • Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.
  • Storage device 28 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory, RAM) 30 and/or cache memory 32 .
  • Electronic device 12 may include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive").
  • a disk drive for reading and writing to a removable nonvolatile disk may be provided, as well as a removable nonvolatile disk (such as a Compact Disc- Read Only Memory, CD-ROM), Digital Video Disc (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical media) CD-ROM drive.
  • each drive may be connected to bus 18 via at least one data medium interface.
  • the storage device 28 may include at least one program product having a set (for example, at least one) of program modules configured to perform the functions of the various embodiments of the present application.
  • Program modules 26 generally perform functions and/or methods in the embodiments described herein.
  • the electronic device 12 can also communicate with at least one external device 14 (such as a keyboard, pointing device, camera, display 24, etc.), and can also communicate with at least one device that enables the user to interact with the electronic device 12, and/or communicate with the device that enables the user to interact with the electronic device 12.
  • Electronic device 12 is capable of communicating with any device (eg, network card, modem, etc.) that communicates with at least one other computing device. This communication can be performed through an input/output (Input/Output, I/O) interface 22 .
  • I/O input/output
  • the electronic device 12 can also communicate with at least one gateway (such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public gateway, such as the Internet) through the gateway adapter 20.
  • gateway adapter 20 communicates with other modules of electronic device 12 via bus 18 .
  • other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays) of Independent Disks, RAID) systems, tape drives, and data backup storage systems.
  • the processor 16 executes various functional applications and data processing by running the programs stored in the storage device 28 , for example, realizing the live broadcast processing method provided by the above-mentioned embodiments of the present application.
  • Embodiment 5 of the present application provides a computer-readable storage medium on which a computer program is stored.
  • the live broadcast processing method provided in the embodiment of the present application is implemented.
  • the method includes: obtaining a live media stream audio stream in the audio stream, carry out keyword recognition on the audio stream based on the current keyword library, and determine whether there is at least one keyword in the keyword library in the audio stream; in response to identifying the audio stream in the audio stream The keyword meets the information extraction trigger condition, and based on the identified keyword, the corresponding prompt information is extracted from the preset prompt content library, wherein the prompt content library includes any keyword in the keyword library Corresponding prompt information; sending the prompt information to the live broadcast terminal for display, and adding the prompt information to the live media stream.
  • the computer-readable storage medium provided by the embodiment of the present application is not limited to the method operation described above, and can also execute the live broadcast processing method provided by any embodiment of the present application.
  • the computer storage medium in the embodiments of the present application may use any combination of at least one computer-readable medium.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer readable signal medium may include a data signal carrying computer readable source code in baseband or as part of a carrier wave traveling as a data signal. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .
  • Source code embodied on a computer readable medium may be transmitted using any appropriate medium, including - but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • any appropriate medium including - but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • Computer source code for carrying out the operations of this application may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language.
  • the Source Code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user computer through any kind of gateway, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (such as through an Internet Service Provider). Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.

Abstract

本申请实施例公开了一种直播处理方法、直播平台、存储介质及电子设备，其中方法包括：获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别；响应于所述音频流中识别到的关键词满足信息提取触发条件，基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。

Description

一种直播处理方法、直播平台、存储介质及电子设备
本申请要求在2021年9月24日提交中国专利局、申请号为202111124006.6的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及直播技术领域，例如涉及一种直播处理方法、直播平台、存储介质及电子设备。
背景技术
随着互联网技术的发展和社会文明的提高，直播行业日趋成熟。与短视频领域先审后发不同，直播存在实时性的特征。因此，直播的影响力十分巨大。
相关技术中至少存在以下技术问题：当前对直播的监管方式包括：一、法律法规，国家有通用法律和针对直播的法规，以抑制了直播违法情况，但法律是底限，只能杜绝违法违规行为，无法杜绝灰色内容；二、上岗培训，部分机构和平台有针对主播的短暂培训，但由于直播门槛低，大量主播未经过规范的培训；三、违规检测，通过各种技术手段检测到违规行为时，提醒主播已违规和要求改正、提醒管理员介入或自动封禁，但是目前的处理方案以惩罚为主，又因惩罚不可滥用，产生了很多灰色空间。
发明内容
本申请实施例提供一种直播处理方法、直播平台、存储介质及电子设备，以实现提高直播的规范性。
第一方面，本申请实施例提供了一种直播处理方法，包括：
获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；
响应于所述音频流中识别到的关键词满足信息提取触发条件，基于所述识 别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；
将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。
第二方面，本申请实施例还提供了一种直播平台，包括：
关键词识别模块，设置为获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；
提示信息提取模块，设置为若所述音频流中识别到的关键词满足信息提取触发条件，则基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；
提示信息展示模块，设置为将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。
第三方面，本申请实施例还提供了一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如本申请任一实施例提供的直播处理方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请任一实施例提供的直播处理方法。
附图说明
图1为本申请实施例一提供的一种直播处理方法的流程示意图；
图2是本申请实施例提供的一种直播场景的示意图；
图3是本申请实施例提供的一种直播端展示提示信息的示意图；
图4为本申请实施例二提供的一种直播处理方法的流程示意图；
图5是本申请实施例提供的一种直播平台的结构示意图；
图6是本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请详细说明。
实施例一
图1为本申请实施例一提供的一种直播处理方法的流程示意图，本实施例可适用于在直播过程中，对直播者的不规范直播内容进行提示的情况，该方法可以由本申请实施例提供的直播平台来执行，该直播平台可以由软件和/或硬件来实现，该直播平台可以配置在电子计算设备上，包括如下步骤：
S110、获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词。
S120、若所述音频流中识别到的关键词满足信息提取触发条件，则基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息。
S130、将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。
示例性的，参见图2，图2是本申请实施例提供的一种直播场景的示意图，直播端和客户端分别与直播平台通信连接，在一些实施例中，直播端和客户端可以是分别的两端，即两个不同的电子设备；在另一些实施例中，还可以是直播端和客户端是同一电子设备，通过不同的展示界面实现不同用户权限的区分，或者通过登录不同的APP进行区分，或者通过验证不同的角色身份进行区分。直播端和客户端可以是诸如手机、平板电脑等的终端设备，分别具有不同的权限，直播端用于提供直播数据，具有直播后台管理权限、直播对象设置权限。客户端可观看直播，仅具有直播观看权限和对直播中直播对象的交易权限。
直播端需要进行注册，直播平台配置有注册模块，接收用户的注册请求以 及用户信息，对用户的直播身份进行注册，注册成功后具备相应的权限。对于任一设备向直播平台发起请求时，判断该设备是否登录，登录成功后，确定该设备的权限，即确定该设备为直播端和客户端中的一项。对于直播端可开设直播，设置直播对象(例如进行介绍的物品或者游戏等)，生成直播媒体流，将生成的直播媒体流实时传输至直播平台，便于客户端从直播平台获取直播媒体流。
直播端包括本地直播采集设备，例如直播采集设备包括但不限于摄像头、麦克风以及手机等终端设备。通过终端设备上的直播应用调用本地直播采集设备采集音频流和视频流，形成直播媒体流，并通过终端设备上的直播应用将直播媒体流发送至直播平台(例如直播服务器)。直播平台对直播端信息进行权限鉴定，若该直播端具有直播权限，则接收直播媒体流并存储，直播平台在外层封装一个主播服务层用于对外服务，便于在接收到客户端发送的直播媒体流的请求时，将该直播媒体流发送至客户端进行展示。
在一些实施例中，直播端将音频流和视频流分别传输到直播平台，该音频流和视频流中分别携带有时间戳，直播平台可通过时间戳将音频流和视频流融合处理得到直播媒体流。相应的，直播平台可直接实时获取直播端发送的音频流，在一些实施例中，直播媒体流中的音频流还可以是延时获取的，其获取方式可以是导入等，对此不作限定。
在一些实施例中，直播端将采集的音频流和视频流处理得到直播媒体流传输到直播平台，直播平台从直播媒体流中提取音频流，并对音频流进行关键词识别。
本实施例中，直播平台预先维持一关键词库，该关键词库中包括待识别的关键词。在一些实施例中，关键词库中可以是包括但不限于法律法规关键词、敏感词和热点词，其中，法律法规关键词可以是从法律法规中提取的关键词，敏感词可以是根据需求设置的，不同时期的敏感词可以不同，热点词可以是根据讨论热度确定。关键词库中的关键词的类型可根据历史直播端的直播类型设置，例如，直播类型包括网络游戏直播，相应的，关键词库中的关键词可以是 包括游戏违规词。可选的，直播平台定期确定是否存在新增直播类型，在存在新增直播类型的情况下，基于新增直播类型更新关键词库，即在关键词库中增加新增直播类型的关键词。
预先设置关键词的来源，根据预设时间间隔对多个来源进行关键词搜索，将确定的新关键词更新至关键词库中。示例性的，法律法规关键词的来源可以是法律法规的发布地址，例如国家法律网站等，敏感词的来源可以是官方媒体，热点词的来源可以是官方媒体等。将上述来源地址以数组的形式进行存储，便于快速调用多个地址进行关键词更新。在一些实施例中，可以是基于关键词类型确定不同的关键词更新频率，例如法律法规关键词可以是以1周/次的频率进行更新，敏感词可以是以1天/次的频率进行更新，热点词可以是以1小时/次的频率进行更新。关键词更新可以是通过生成定时任务，分别调用一来源地址进行关键词查询，若查询到新增关键词，则更新关键词库。其中，可以是通过多个定时任务并行处理，提高关键词查询的效率，提高关键词的实时性和准确性。
基于关键词库中的关键词对直播媒体流中的音频流进行语音识别，确定该音频流中包括的关键词。示例性的，对音频流进行关键词识别可以是：对音频流进行分帧，得到多个语音段，其中，相邻语音段之间存在预设时长的重叠，对于任一语音段进行关键词识别。其中，对音频流进行分帧可以是基于预设时长进行分帧，即多个语音段为相同时长的语音段；对音频流进行分帧还可以是识别音频流的断句位置，基于断句位置对音频流进行分帧，避免关键词被分割导致识别不准确的情况，其中，断句位置可以是音频流中振幅小于预设值的位置。
对于每一语音段进行关键词识别过程中，可以是识别语音段中的音素，其中，中文音素可以用声母和韵母作为音素集，英文因素可以基于预设音素集确定，将关键词的音素与语音段中的音素进行匹配，确定音频流中包括的关键词。为避免语音段划分导致的识别错误，在一些实施例中，可以是利用隐马尔可夫模型，基于关键词预设识别路径，在识别时只按照预设路径进行识别，从而规 避多帧问题。示例性的，在音频流中识别出“d i q i c i r en k ou p u ch a”，组合结果为“第七次人口普查”。
本实施例中，为避免向直播端频繁发送提示信息对直播者的干扰，设置了信息提取触发条件，在确定音频流中包括关键词后，确定识别到的关键词是否满足信息提取触发条件，在确定识别到的关键词满足信息提取触发条件的情况下，触发对直播端发送提示信息，在确定识别到的关键词不满足信息提取触发条件的情况下，持续识别关键词。需要说明的是，同一音频流中可以是包括至少一个关键词，分别对每一个关键词识别是否满足信息提取触发条件，至少一个关键词之间互不干扰，基于满足信息提取触发条件的关键词触发提取提示信息。
在一些实施例中，信息提取触发条件为累计次数阈值，相应的，在对音频流进行关键词识别的同时，记录每个关键词被识别的累计次数，即在识别到任一关键词时，对该关键词的累计次数加一。可选的，信息提取触发条件包括所述音频流中已识别到关键词的累计次数超过预设阈值，示例性的，预设阈值可以是5次或10次，对此不作限定。
可选的，信息提取触发条件包括预设时长的滑动窗口内已识别到关键词的累计次数超过预设阈值。示例性的，采用滑动时窗式结构来进行关键词的阈值管理，滑动时窗式结构是指在任意时间节点操作时，都只保存最近n时长的记录，也只查询最近n时长的记录，并将已过期结果裁剪掉。其中，n时长可以是30分钟，相应的，对每个关键词的识别次数的累计，仅保留距当前时刻时长30分钟的识别次数。可选的，通过redis-zset方案存储音频流的识别结果，其数据结构为key-value-score式，其中key为直播唯一标识(如直播id)，value为识别到的关键词，score为识别时的时间戳，示例性的，{id＝5，value＝“七普”，score＝16523123132}。
在一些实施例中，不同的关键词可以是对应不同的预设阈值。示例性的，关键词A的预设阈值可以是1，关键词B的预设阈值可以是10，可根据关键词 的限制需求设置。可选的，在任一关键词的累计数量发生变化时，与该关键词对应的信息提取触发条件进行匹配。可选的，根据固定时间间隔(例如30秒)，统计每个关键词的累计数量，与对应的信息提取触发条件进行匹配。对于匹配成功的关键词，触发提取提示信息。
本实施例中，直播平台预先维持一提示内容库，该提示内容库中包括关键词库中每个关键词对应的提示信息。该提示信息可以是实时更新的，以保证提示内容库的准确性和实效性。
提示内容库中可以是将关键词与对应的提示信息关联存储，对于满足信息提取触发条件的关键词，在提示内容库中进行匹配，提取匹配成功的关键词对应的提示信息。该提示信息可以是文本、图片等格式，对此不作限定。
将提取的提示信息发送至直播端，以使主播端在显示界面显示该提示信息，示例性的，参见图3，图3是本申请实施例提供的一种直播端展示提示信息的示意图。其中，图3仅为一种示例，对提示信息的内容、提示信息的展示形式和展示位置不作限定，可根据提示信息的不同、直播者的需求不同进行调整。在一些实施例中，提示信息的展示区域是尺寸可调的，根据展示区域的数据长度确定展示的大小，在另一些实施例中，提示信息的展示区域可以是尺寸固定的，例如基于固定的屏占比确定展示区域的尺寸，根据提示信息的数据长度进行分批次展示。在一些实施例中，提示信息的展示区域的位置可以是固定的，例如在显示界面的左上角或右上角等，该展示区域可由直播者手动调节，参见图3。在另一些实施例中，提示信息的展示区域的位置可以是根据当前显示界面的显示内容确定，例如将展示区域设置在显示界面的空白位置，避免对已有显示内容的遮挡，同时无需直播者手动调节。在一些实施例中，提示信息的展示时长固定，例如显示时长N后，自动关闭。其中，提示信息的展示时长超过预设时长后可通过手动关闭，其中，预设时长可以是小于时长N。在另一实施例中，提示信息的展示时长可以是根据提示信息的数据长度确定，与数据长度正相关。
可选的，将所述提示信息发送至所述直播端进行展示，包括：调用预设的 交互界面的显示代码，将所述提示信息填充至所述显示代码的对应位置，将填充后的显示代码发送至直播端，以使所述直播端显示包括提示信息的交互界面。其中，直播平台预先设置多个交互界面(例如不同风格的交互界面)，可在多个显示界面中随机调用，或者，根据直播类型调用对应的显示界面，或者，根据调用直播端指定的显示界面。交互界面的显示代码可以是源生代码或者Html代码，例如APP对应源生代码，网页对应Html代码，可根据直播端直播软件类型调用对应格式的代码。
本实施例中，将提示信息展示给直播端的同时，将提示信息添加到直播媒体流中，展示给正在观看的客户端，以使用户可观看到该提示信息，避免用户被不规范言论所误导。
本实施例的技术方案，通过设置关键词库，对直播媒体流中的音频流进行关键词识别，以确定直播端是否存在包括关键词的言论。在识别到的关键词满足信息提取触发条件时，从提示内容库中调用对应的提示信息，将提示信息展示给直播者和观看者，其中，提示内容库中的提示信息为具有公信度的规范信息，通过展示提示信息向直播者和观看者展示正确信息，避免直播者在不了解正确信息时，向用户传达不规范信息，也避免用户被不规范言论所误导，提供了直播的规范性。
在上述实施例的基础上，在将所述提示信息发送至所述直播端进行展示之后，还包括：对所述音频流继续进行所述关键词的识别，并累计识别次数；在累计的识别次数满足提醒阈值时，生成警报提醒。
为了避免提示信息展示后，直播者继续传输不规范言论的情况，在展示提示信息后，继续对音频流进行所述关键词的识别，在已展示提示信息的关键词的累计识别次数满足提醒阈值时，生成警报提醒。其中，不同的关键词对应的提醒阈值可以不同，例如可以是信息提取触发条件中预设阈值的N倍，该N为大于1的正数。
该警报提醒可以是违规提醒。在一些实施例中，提醒阈值可以是多个级别 的阈值，关键词的累计识别次数满足低级别阈值时，生成提示信息，关键词的累计识别次数满足高级别阈值时，触发违规惩罚或人工介入，例如关闭直播间等。
实施例二
图4为本申请实施例二提供的一种直播处理方法的流程示意图，本申请实施例与上述实施例中各个可选方案可以结合。在本申请实施例中，可选地，所述提示内容库中提示信息的确定方法包括：对于所述关键词库中的任一关键词，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，并基于获取的提示信息更新所述提示内容库。
如图4所示，本申请实施例的方法包括如下步骤：
S210、对于所述关键词库中的任一关键词，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，并基于获取的提示信息更新所述提示内容库。
S220、获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词。
S230、若所述音频流中识别到的关键词满足信息提取触发条件，则基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息。
S240、将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。
需要说明的是，步骤S210和步骤S220-S240可以是同步执行。步骤S210循环执行，以实时更新提示内容库，保证提示内容库的准确性和时效性。步骤S230调用的提示内容库为当前时刻的提示内容库。
本实施例中，直播平台预先设置有信息查询地址库，对于关键词库中每个关键词，周期性的在多个信息查询地中进行提示信息的查询，并更新提示内容 库。可选的，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，包括：基于关键词的类型和热度状态确定查询周期，基于所述查询周期生成查询任务，其中，所述查询任务用于基于预设的信息查询地址库中的多个查询地址获取提示信息。不同类型的关键词的相关提示信息的变更频率不同，例如关键词类型包括但不限于法律法规关键词、敏感词和热点词，其中，法律法规关键词、敏感词和热点词的提示信息变更频率依次增大，相应的，其查询周期依次减小。示例性的，法律法规关键词的查询周期可以是以1周/次，敏感词的查询周期可以是以1天/次，热点词的查询周期可以是以1小时/次。
示例性的，可以是搭建web服务框架，例如使用java-web服务，并增加定时调度功能，常见的调度功能包括job、quartz等，任意定时调度功能均可以以指定间隔进行功能的循环调度。基于上述循环调度，以及对应的查询周期对关键词库中的多个关键词执行并行的信息查询任务，以提高信息查询效率。其中，在任意关键字调用信息查询任务未结束时，同一关键词不重复调用。
可选的，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，包括：在任一查询周期，基于进行查询的信息查询地址生成关键词查询任务，并执行所述关键词查询任务，确定包括所述关键词的标签地址信息，基于所述标签地址信息提取包括所述关键词的提示信息。
示例性的，调用任一信息查询地址生成关键词查询任务，对该信息查询地址对应的数据进行关键词查询。需要说明的是，该信息查询地址为媒体的官方地址，该地址对应存储有大量信息，本实施例中，关键词查询任务用于对所述信息查询地址进行日期循环和版面循环的关键词查询，相应的，该关键词查询任务的查询指令中包括日期字段和版面字段，通过更新日期字段和版面字段的信息实现日期循环和版面循环的关键词查询，示例性的，A报纸中同一日期的数据中包括八个版面，通过遍历各个版面实现版面循环的关键词查询，同时，通过遍历各个发布日期，实现日期循环的关键词查询，避免信息遗漏，通过双重循环提高信息查询的全面性。在一些实施例中，可以是进行增量查询，例如 对于同一关键词在同一信息查询地址进行查询过程中，首次执行关键词查询任务可以是遍历已发布的全部日期和全部版面数据，在非首次执行关键词查询任务可以是遍历新增日期或新增版面的数据，以提高信息查询效率。
在一些实施例中，关键词查询任务可以是对信息查询地址中的标签进行查询，得到标签地址信息，在标签地址信息对应的数据中提取包括关键词的提示信息。其中，标签可以是文章标题、副标题等，通过对标签进行首次查询，对关键词进行快速筛查，并对包含关键词的标签对应的内容进行信息提取，提高提示信息的提取效率和针对性，避免大量无效查询导致的时间浪费和内存消耗。
在一些实施例中，由于关键词长度较大，可以是将关键词进行拆分，例如关键词为第七次人口普查，可以是将该关键词拆分为“人口”“七普”或者“普查”等，基于拆分的词进行标签的查询，避免不同文章用词不同导致遗漏的问题，例如对于包括“人口”的标签可以是进行提示信息的提取，提高提示信息提取的全面性。
本实施例中，提示内容库中每一个关键词可以是对应一个提示信息，为了避免提示信息变化等导致的不同信息之间的偏差，提示内容库的提示信息可以是最新发布的，和/或，最具有权威的机构发布的信息。
其中，信息查询地址库中多个信息查询地址分别设置有权重，相应的，从每个信息查询地址查询到的提示信息具有对应的权重。信息查询地址库中多个信息查询地址包括法律法规、官方媒体，其权重依次下降。示例性的，官方媒体包括多个信息查询地址，对于官方媒体的多个信息查询地址可以是具有相同权重，还可以是具有不同权重，可根据需求设置。
可选的，基于获取的提示信息更新所述提示内容库，包括：若提示内容库中不包括该关键词的提示信息，则将获取的提示信息和对应的关键词添加至提示内容库。若提示内容库中包括该关键词的提示信息，且获取的提示信息对应的权重高于所述提示内容库中已有提示信息的权重，则基于获取的提示信息更新所述提示内容库。通过高权重的信息查询地址查询到提示信息覆盖低权重的 信息查询地址查询到提示信息，提高提示内容库中提示信息的权威性和准确性。示例性的，对于关键词“第七次人口普查”，首次爬取到B报纸的社论，录入了提示内容库，其数据示例为：第七次人口普查:{source:B报纸，content:”<html>xxxxxB报纸社论xxxxxx</html>”}，第二天爬取到A报纸的社论，根据权重规则，A报纸权重高于B报纸，因此数据变为：第七次人口普查:{source:A报纸，content:”<html>xxxxxA报纸社论xxxxxx</html>”}。
在上述实施例的基础上，若获取的提示信息对应的权重与所述提示内容库中已有提示信息的权重相同，且所述获取的提示信息的发布时间晚于所述提示内容库中已有提示信息的发布时间，则基于获取的提示信息更新所述提示内容库。通过发布时间晚的提示信息覆盖发布时间早的提示信息，提高提示内容库中提示信息的时效性。
在一些实施例中，高权重的信息查询地址查询到的一定时间段内(如半年内)的提示信息，可以覆盖低权重信息查询地址查询到的提示信息，相应的，若发布时间在时间段外，例如超过半年，则该高权重的信息查询地址查询到的提示信息无法覆盖低权重信息查询地址查询到的提示信息。同理，若获取的提示信息的权重低于提示内容库中已有提示信息的权重，且在一定时间段内，则丢弃该获取的提示信息；若获取的提示信息的权重低于提示内容库中已有提示信息的权重，且超过一定时间段，则可覆盖提示内容库中已有提示信息。
本实施例的技术方案，通过针对每一个关键词进行周期性的信息查询，以更新提示信息库，保证提示信息库中的时效性。对于获取的提示信息，通过信息发布机构的权重，对提示信息进行更新，保证了提示信息的权威性和正确性，基于该提示内容库中的提示信息对直播者和观看者进行展示，提高了直播的规范性。
实施例三
图5是本申请实施例提供的一种直播平台的结构示意图，该直播平台包括：
关键词识别模块310，设置为获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；
提示信息提取模块320，设置为若所述音频流中识别到的关键词满足信息提取触发条件，则基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；
提示信息展示模块330，设置为将所述提示信息发送至所述直播端进行展示，并将所述提示信息添加至直播媒体流中。
在上述实施例的基础上，该装置还包括：
提示信息获取模块，设置为对于所述关键词库中的任一关键词，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息；
提示内容库更新模块，设置为基于获取的提示信息更新所述提示内容库。
在上述实施例的基础上，所述信息查询地址库中多个信息查询地址分别设置有权重；
提示内容库更新模块设置为：
若获取的提示信息对应的权重高于所述提示内容库中已有提示信息的权重，则基于获取的提示信息更新所述提示内容库
在上述实施例的基础上，提示内容库更新模块还设置为：
若获取的提示信息对应的权重与所述提示内容库中已有提示信息的权重相同，且所述获取的提示信息的发布时间晚于所述提示内容库中已有提示信息的发布时间，则基于获取的提示信息更新所述提示内容库。
在上述实施例的基础上，提示信息获取模块设置为：
基于关键词的类型和热度状态确定查询周期，其中，所述关键词类型包括法律法规关键词、敏感词和热点词；
基于所述查询周期生成查询任务，其中，所述查询任务用于基于预设的信 息查询地址库中的多个查询地址获取提示信息。
在上述实施例的基础上，提示信息获取模块设置为：
在任一查询周期，基于进行查询的信息查询地址生成关键词查询任务，并执行所述关键词查询任务，确定包括所述关键词的标签地址信息，其中，所述关键词查询任务用于对所述信息查询地址进行日期循环和版面循环的关键词查询；
基于所述标签地址信息提取包括所述关键词的提示信息。
在上述实施例的基础上，所述信息提取触发条件包括所述音频流中已识别到关键词的累计次数超过预设阈值，或者，预设时长的滑动窗口内已识别到关键词的累计次数超过预设阈值。
在上述实施例的基础上，提示信息展示模块330设置为：
调用预设的交互界面的显示代码，将所述提示信息填充至所述显示代码的对应位置，将填充后的显示代码发送至直播端，以使所述直播端显示包括提示信息的交互界面。
在上述实施例的基础上，该装置还包括：
识别次数累计模块，设置为在将所述提示信息发送至所述直播端进行展示之后，对所述音频流继续进行所述关键词的识别，并累计识别次数；
提醒模块，设置为在累计的识别次数满足提醒阈值时，生成警报提醒。
本申请实施例所提供的直播平台可执行本申请任意实施例所提供的直播处理方法，具备执行方法相应的功能模块。
实施例四
图6为本申请实施例四提供的一种电子设备的结构示意图。图6示出了适于用来实现本申请实施方式的电子设备12的框图。图6显示的电子设备12仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。设备12典型的是承担图像分类功能的电子设备。
如图6所示，电子设备12以通用计算设备的形式表现。电子设备12的组件可以包括但不限于：至少一个处理器16，存储装置28，连接不同系统组件(包括存储装置28和处理器16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture，ISA)总线，微通道体系结构(Micro Channel Architecture，MCA)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
电子设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
存储装置28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)30和/或高速缓存存储器32。电子设备12可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以用于读写不可移动的、非易失性磁介质(图6未显示，通常称为“硬盘驱动器”)。尽管图6中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如只读光盘(Compact Disc-Read Only Memory，CD-ROM)、数字视盘(Digital Video Disc-Read Only Memory，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过至少一个数据介质接口与总线18相连。存储装置28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请各实施例的功能。
具有一组(至少一个)程序模块26的程序36，可以存储在例如存储装置28中，这样的程序模块26包括但不限于操作系统、至少一个应用程序、其它程 序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网关环境的实现。程序模块26通常执行本申请所描述的实施例中的功能和/或方法。
电子设备12也可以与至少一个外部设备14(例如键盘、指向设备、摄像头、显示器24等)通信，还可与至少一个使得用户能与该电子设备12交互的设备通信，和/或与使得该电子设备12能与至少一个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(Input/Output，I/O)接口22进行。并且，电子设备12还可以通过网关适配器20与至少一个网关(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网关，例如因特网)通信。如图所示，网关适配器20通过总线18与电子设备12的其它模块通信。应当明白，尽管图中未示出，可以结合电子设备12使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理器16通过运行存储在存储装置28中的程序，从而执行各种功能应用以及数据处理，例如实现本申请上述实施例所提供的直播处理方法。
实施例五
本申请实施例五提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请实施例所提供的直播处理方法，该方法包括：获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；响应于所述音频流中识别到的关键词满足信息提取触发条件，基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；将所述提示信息发送至直播端进行展示，并将所述提示信息添加至直播媒体流中。
当然，本申请实施例所提供的一种计算机可读存储介质，其上存储的计算机程序不限于如上所述的方法操作，还可以执行本申请任意实施例所提供的直播处理方法。
本申请实施例的计算机存储介质，可以采用至少一个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器((Erasable Programmable Read-Only Memory，EPROM)或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的源代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的源代码可以用任何适当的介质传输，包括——但不限于无线、电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机源代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的 程序设计语言。源代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网关——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。

Claims (12)

  1. 一种直播处理方法，包括：
    获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；
    响应于所述音频流中识别到的关键词满足信息提取触发条件，基于所述识别到的关键词从预设的提示内容库中提取对应的提示信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；
    将所述提示信息发送至直播端进行展示，并将所述提示信息添加至直播媒体流中。
  2. 根据权利要求1所述的方法，其中，所述提示内容库中提示信息的确定方法包括：
    对于所述关键词库中的任一关键词，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，并基于获取的提示信息更新所述提示内容库。
  3. 根据权利要求2所述的方法，其中，所述信息查询地址库中多个信息查询地址分别设置有权重；
    所述基于获取的提示信息更新所述提示内容库，包括：
    响应于获取的提示信息对应的权重高于所述提示内容库中已有提示信息的权重，基于获取的提示信息更新所述提示内容库。
  4. 根据权利要求3所述的方法，还包括：
    响应于获取的提示信息对应的权重与所述提示内容库中已有提示信息的权重相同，且所述获取的提示信息的发布时间晚于所述提示内容库中已有提示信息的发布时间，基于获取的提示信息更新所述提示内容库。
  5. 根据权利要求2所述的方法，其中，基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，包括：
    基于关键词的类型和热度状态确定查询周期，其中，所述关键词类型包括法律法规关键词、敏感词和热点词；
    基于所述查询周期生成查询任务，其中，所述查询任务用于基于预设的信 息查询地址库中的多个查询地址获取提示信息。
  6. 根据权利要求2所述的方法，其中，所述基于预设的信息查询地址库中的多个查询地址周期性地获取提示信息，包括：
    在任一查询周期，基于进行查询的信息查询地址生成关键词查询任务，并执行所述关键词查询任务，确定包括所述关键词的标签地址信息，其中，所述关键词查询任务用于对所述信息查询地址进行日期循环和版面循环的关键词查询；
    基于所述标签地址信息提取包括所述关键词的提示信息。
  7. 根据权利要求1所述的方法，其中，所述信息提取触发条件包括所述音频流中已识别到关键词的累计次数超过预设阈值，或者，预设时长的滑动窗口内已识别到关键词的累计次数超过预设阈值。
  8. 根据权利要求1所述的方法，其中，所述将所述提示信息发送至所述直播端进行展示，包括：
    调用预设的交互界面的显示代码，将所述提示信息填充至所述显示代码的对应位置，将填充后的显示代码发送至直播端，以使所述直播端显示包括提示信息的交互界面。
  9. 根据权利要求1所述的方法，在将所述提示信息发送至所述直播端进行展示之后，还包括：
    对所述音频流继续进行所述关键词的识别，并累计识别次数；
    响应于累计的识别次数满足提醒阈值，生成警报提醒。
  10. 一种直播平台，包括：
    关键词识别模块，设置为获取直播媒体流中的音频流，基于当前的关键词库对所述音频流进行关键词识别，确定所述音频流中是否存在所述关键词库中的至少一个关键词；
    提示信息提取模块，设置为若所述音频流中识别到的关键词满足信息提取触发条件，则基于所述识别到的关键词从预设的提示内容库中提取对应的提示 信息，其中，所述提示内容库中包括所述关键词库中任一关键词对应的提示信息；
    提示信息展示模块，设置为将所述提示信息发送至直播端进行展示，并将所述提示信息添加至直播媒体流中。
  11. 一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1-9中任一所述的直播处理方法。
  12. 一种计算机可读存储介质，所述计算机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1-9中任一所述的直播处理方法。
PCT/CN2022/120070 2021-09-24 2022-09-21 一种直播处理方法、直播平台、存储介质及电子设备 WO2023045939A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111124006.6 2021-09-24
CN202111124006.6A CN113891104A (zh) 2021-09-24 2021-09-24 一种直播处理方法、直播平台、存储介质及电子设备

Publications (1)

Publication Number Publication Date
WO2023045939A1 true WO2023045939A1 (zh) 2023-03-30

Family

ID=79006484

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/120070 WO2023045939A1 (zh) 2021-09-24 2022-09-21 一种直播处理方法、直播平台、存储介质及电子设备

Country Status (2)

Country Link
CN (1) CN113891104A (zh)
WO (1) WO2023045939A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113891104A (zh) * 2021-09-24 2022-01-04 北京沃东天骏信息技术有限公司 一种直播处理方法、直播平台、存储介质及电子设备
CN114845127A (zh) * 2022-04-13 2022-08-02 广州方硅信息技术有限公司 直播间词条展示方法、系统、装置、设备及存储介质
CN117319750A (zh) * 2023-08-16 2023-12-29 浙江印象软件有限公司 直播信息的实时显示方法及装置

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106303557A (zh) * 2016-08-16 2017-01-04 广州华多网络科技有限公司 网络直播的直播内容展示方法和装置
JP2018029325A (ja) * 2016-08-19 2018-02-22 バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド ライブ配信に応用する対話型方法及び装置
WO2019169766A1 (zh) * 2018-03-06 2019-09-12 平安科技（深圳）有限公司 电子装置、系统敏感内容的预警方法、系统及存储介质
CN110784751A (zh) * 2019-08-21 2020-02-11 腾讯科技（深圳）有限公司 信息显示方法及装置
CN111355781A (zh) * 2020-02-18 2020-06-30 腾讯科技（深圳）有限公司 一种语音信息交流的管理方法、装置和存储介质
CN111541904A (zh) * 2020-04-15 2020-08-14 腾讯科技（深圳）有限公司 直播过程中的信息提示方法、装置、设备及存储介质
CN112511855A (zh) * 2020-11-28 2021-03-16 南京雄雉电子商务有限公司 一种基于云计算的电子商务平台视频直播智能管理系统
CN112995696A (zh) * 2021-04-20 2021-06-18 共道网络科技有限公司 一种直播间违规检测方法及装置
WO2021136363A1 (zh) * 2019-12-31 2021-07-08 阿里巴巴集团控股有限公司 视频数据的处理、显示方法、装置、电子设备及存储介质
CN113315994A (zh) * 2021-04-23 2021-08-27 北京达佳互联信息技术有限公司 直播数据处理方法、装置、电子设备及存储介质
CN113891104A (zh) * 2021-09-24 2022-01-04 北京沃东天骏信息技术有限公司 一种直播处理方法、直播平台、存储介质及电子设备

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106303557A (zh) * 2016-08-16 2017-01-04 广州华多网络科技有限公司 网络直播的直播内容展示方法和装置
JP2018029325A (ja) * 2016-08-19 2018-02-22 バイドゥ オンライン ネットワーク テクノロジー （ベイジン） カンパニー リミテッド ライブ配信に応用する対話型方法及び装置
WO2019169766A1 (zh) * 2018-03-06 2019-09-12 平安科技（深圳）有限公司 电子装置、系统敏感内容的预警方法、系统及存储介质
CN110784751A (zh) * 2019-08-21 2020-02-11 腾讯科技（深圳）有限公司 信息显示方法及装置
WO2021136363A1 (zh) * 2019-12-31 2021-07-08 阿里巴巴集团控股有限公司 视频数据的处理、显示方法、装置、电子设备及存储介质
CN111355781A (zh) * 2020-02-18 2020-06-30 腾讯科技（深圳）有限公司 一种语音信息交流的管理方法、装置和存储介质
CN111541904A (zh) * 2020-04-15 2020-08-14 腾讯科技（深圳）有限公司 直播过程中的信息提示方法、装置、设备及存储介质
CN112511855A (zh) * 2020-11-28 2021-03-16 南京雄雉电子商务有限公司 一种基于云计算的电子商务平台视频直播智能管理系统
CN112995696A (zh) * 2021-04-20 2021-06-18 共道网络科技有限公司 一种直播间违规检测方法及装置
CN113315994A (zh) * 2021-04-23 2021-08-27 北京达佳互联信息技术有限公司 直播数据处理方法、装置、电子设备及存储介质
CN113891104A (zh) * 2021-09-24 2022-01-04 北京沃东天骏信息技术有限公司 一种直播处理方法、直播平台、存储介质及电子设备

Also Published As

Publication number Publication date
CN113891104A (zh) 2022-01-04

Similar Documents

Publication Publication Date Title
WO2023045939A1 (zh) 一种直播处理方法、直播平台、存储介质及电子设备
US20200245021A1 (en) Reception apparatus, reception method, program, and information processing system
US11562020B2 (en) Short-term and long-term memory on an edge device
US20170289619A1 (en) Method for positioning video, terminal apparatus and cloud server
EP3155822B1 (en) Systems and methods for locally recognizing viewed video content
US20150039601A1 (en) Pre-delivery of content to a user device
EP3876441B1 (en) Method for surveying broadcast ratings and ratings statistics information server
CN104853230B (zh) 一种热点视频推送方法及装置
CN104488277A (zh) 用于监测媒体呈现的方法和装置
CN111274442B (zh) 确定视频标签的方法、服务器及存储介质
US11743522B2 (en) Systems and methods that match search queries to television subtitles
WO2014052847A1 (en) Enriching broadcast media related electronic messaging
CN110941738B (zh) 推荐方法、装置、电子设备及计算机可读存储介质
US20140324858A1 (en) Information processing apparatus, keyword registration method, and program
US20150128190A1 (en) Video Program Recommendation Method and Server Thereof
CN103997662A (zh) 节目推送的方法及系统
CN106658033A (zh) 直播内容查询方法、装置和服务器
WO2022262719A1 (zh) 一种直播处理方法、装置、存储介质及电子设备
CN104881774A (zh) 一种自动建立日程的方法和装置
US8983942B2 (en) Method and apparatus for providing time machine service based on social network service
CN112035534A (zh) 一种实时大数据处理方法、装置及电子设备
US9762687B2 (en) Continuity of content
US11334575B2 (en) Integrating relational database temporal tables with a distributed programming environment
CN110719337A (zh) 业务系统、业务请求处理方法、装置及服务器
CN106156024B (zh) 一种信息处理方法及服务器

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: 22871985

Country of ref document: EP

Kind code of ref document: A1