CN108650546A - Barrage processing method, computer readable storage medium and electronic equipment - Google Patents
Barrage processing method, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108650546A CN108650546A CN201810453525.9A CN201810453525A CN108650546A CN 108650546 A CN108650546 A CN 108650546A CN 201810453525 A CN201810453525 A CN 201810453525A CN 108650546 A CN108650546 A CN 108650546A
- Authority
- CN
- China
- Prior art keywords
- barrage
- processing
- data
- content
- analysis
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
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]
- H04N21/40—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
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of barrage processing methods comprising following steps S1 collects original barrage data, and the original barrage data include the barrage content that user sends;S2 carries out processing in real time to the original barrage data and processed offline is analyzed, wherein the processed offline analysis includes that the barrage content is analyzed in processing;And S3, according to carrying out after processing analysis to the barrage content in step S2 as a result, carrying out state analysis to user.The invention further relates to relevant computer readable storage medium and relevant electronic equipments.
Description
Technical field
The present invention relates to data fields, and in particular to a kind of barrage processing method, relevant computer readable storage medium
And electronic equipment.
Background technology
Currently, with the fast development of live streaming industry, audient is broadcast live also in constantly expanding, in various types of live streamings
Hold also more and more abundant.Spectators can participate in comment and interaction watching the while of being broadcast live by way of sending barrage, to
It is greatly improved the participation of user, enriches live content.
For barrage message as one of live streaming main amusement exchange way of platform, development and dimension must be focused on by being entire platform
The object of shield, and effective, rational management is carried out to it will the advantageous enthusiasm for transferring participant.Webcast website makees
For an open platform, the spin of big flow how is effectively controlled, is obtained from the barrage data of magnanimity useful
Information, shield uncultivated speech, this has prodigious challenge for live streaming company.
Tradition is usually to carry out sensitive word in client according to dictionary comparative analysis for the analysis and shielding of barrage content
Filtering.However only can not be fully effective by the analysis of simple dictionary control barrage content, and for live streaming,
When carrying out large-scale game or amusement live streaming, barrage item number is very huge, it is easy to take entire screen, human eye can not be timely and effective
The barrage from rolling in determine whether that user has sent bad speech.
Therefore, it is necessary to propose a kind of new barrage processing method.
Invention content
In view of this, in order to overcome at least one aspect of the above problem, the embodiment of the present invention is provided at a kind of barrage
Reason method, includes the following steps:
S1, collects original barrage data, and the original barrage data include the barrage content that user sends;
S2 carries out processing in real time to the original barrage data and processed offline is analyzed, wherein
The processed offline analysis includes that the barrage content is analyzed in processing;And
S3, according to carrying out after processing analysis to the barrage content in step S2 as a result, carrying out state analysis to user.
Further, real-time handle includes:
The original barrage data are stored into database, and are divided the initial data according to the first preset time period
In the different subdata bases for not storing database.
Further, real-time handle further includes:According to the barrage expansion of content corpus.
For example, in step s 2, the step of barrage content is analyzed in the processing, includes:
S21 carries out word segmentation processing to the barrage content;And
S22, will be including in the storage to data warehouse of the barrage data of the barrage content after word segmentation processing.
Further, before step S21, the step of barrage content is analyzed in the processing, further includes:
S20 pre-processes the barrage content, and the pretreatment includes that removal is influential on word segmentation processing special
Character;
Further, barrage content is analyzed in the data warehouse, judges whether the barrage content is rubbish
Rubbish barrage, and will be in analysis result storage to result set database.
Further, in the result set database, the bullet that is sent in the second preset time period according to target user
Rubbish barrage proportion in curtain content, judges whether the target user is passive states.
Further, processed offline analysis further include using database service interface inquiry processed offline analysis into
Degree.
According to another aspect of the present invention, a kind of computer readable storage medium is provided, executable instruction is stored thereon with,
The executable instruction when executed by the processor, the step of realizing any barrage processing method as described above.
According to another aspect of the present invention, a kind of electronic equipment is provided, including:
Memory, for storing executable instruction;And
Processor realizes any barrage as described above for executing the executable instruction stored in the memory
The step of processing method.
Compared with prior art, the present invention has the following advantages:
(1) it is handled by carrying out a point library to barrage data, can effectively cope with Data Migration business, it is also ensured that bullet
Curtain content can be retrieved in time;
(2) it is handled with off-line analysis by handling in real time, can effectively help administrator to close bad speech;
(3) carrying out affective state analysis to user can effectively help administrator to reduce concern range according to User Status,
So that it is more quick to prohibit speech in real time.
Description of the drawings
By the description made for the present invention of below with reference to attached drawing, other objects and advantages of the present invention will be aobvious and easy
See, and can help that complete understanding of the invention will be obtained.
Fig. 1 is the flow chart of the implementation steps of the method for barrage provided in an embodiment of the present invention processing;
Fig. 2 is the structural schematic diagram of computer readable storage medium provided in an embodiment of the present invention;
Fig. 3 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific implementation mode
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with the attached drawing of the embodiment of the present invention,
Technical scheme of the present invention is clearly and completely described.Obviously, described embodiment is the implementation of the present invention
Example, instead of all the embodiments.Based on described the embodiment of the present invention, those of ordinary skill in the art are without creating
Property labour under the premise of the every other embodiment that is obtained, shall fall within the protection scope of the present invention.
Unless otherwise defined, the technical term or scientific terminology that the present invention uses should be tool in fields of the present invention
There is the ordinary meaning that the personage of general technical ability is understood.
According to an aspect of the invention, there is provided a kind of method of barrage processing, specific implementation thinking are as follows:
After being collected to barrage data, then by analyzing the real-time processing of barrage data and processed offline, close not
User Status can be obtained while good speech, administrator can reduce concern range according to User Status in real-time taboo speech,
It is quickly found out and sends bad speech theorist.
More specifically, the method for barrage of the present invention processing is described in detail below in conjunction with the accompanying drawings.
Refering to what is shown in Fig. 1, the method for the barrage processing that the embodiment of the present invention provides, may include steps of:
S1, collects original barrage data, and original barrage data include the barrage content that user sends;
Barrage data information is mainly that word, expression that user delivers when watching live content etc. express oneself mood
Information, barrage data information may include:User id, user's pet name, device type, user gradation, equipment id, barrage content,
Sending time etc..
In specific implementation process, the mode of text box may be used to obtain barrage data information, for example, by using text
Frame control TextBox come obtain user transmission barrage data.After original barrage data collection, preliminary sensitivity is first carried out
Word filters, such as filters out or filter other bad speeches by some dirty words.
Currently, the client of mainstream is generally Web, Android, iOS etc., therefore, preliminary sensitive word mistake can carried out
When filter by the way of being compared with sensitive dictionary, the filtering sensitive words that user sends are fallen, these sensitive words being filtered will
It will not be stored in database, will not be displayed on the screen, but the hair of these sensitive words can be alerted in a manner of pop-up
The taboo speech time can be according to circumstances arranged after same user is by continual warnings in the person of sending by administrator, and situation severe patient can set
It sets the user and permanently prohibits speech.
Specifically, can be by following logics by filtering sensitive words:
By judging that the barrage content (content) that user sends whether there is in sensitive dictionary (dictionary),
If in the presence of filtering this out, uploading onto the server if there is no if, storage is in the database.
It should be noted that the preliminary filtering of sensitive word is only to filter out a part of bad speech, some
Bad speech can not be judged by way of comparing sensitive word dictionary, and subsequent step is needed to carry out analyzing processing.
That is all sensitive words for being not intended as bad speech are stored in sensitive word dictionary.Certainly, sensitive word dictionary can be with
It is updated according to business experience.
S2 carries out processing in real time to original barrage data and processed offline is analyzed.
In the present embodiment, processing in real time may include by the storage of original barrage data in database, and according to first
Initial data is respectively stored into the different subdata bases of database by preset time period.
In specific implementation process, since live streaming platform often faces barrage increasing number and barrage content-length
Uncontrollable scene, for example when star's participation living broadcast interactive or new popular main broadcaster addition, this requires storage barrage contents
Server is capable of the such scene of reply of retractility, using the difference stored the barrage data in different time sections to database
Mode in subdata base can effectively cope with Data Migration business, while barrage content can be retrieved in time.
In the present embodiment, nosql databases may be used.Nosql databases, which have, to be possessed under mass data
Excellent readwrite performance, data model are irrelevant flexibly and between data, the advantages that being easy to extension, are very suitable in the present embodiment
The storage of magnanimity barrage.
Mongodb databases specifically may be used, divide barrage data in the specific format according to the first preset time period
It does not store in different subdata bases.For the inquiry of barrage it is general all can having time limitation, span is substantially all in 1 year
Within, it is advantageous to preset time periods as unit of day, such as can be one day or two days etc., when the barrage for inquiring same user
When need to be traversed for all subdata bases in span, find the barrage data of corresponding user id.
If specifically, by daily barrage data storage to different subdata bases, mongo_danmu_ may be used
20180312 this forms, expression is in the barrage storage a to subdata base by March 12nd, 2018.
In other preferred embodiments, processing can also include according to barrage expansion of content corpus in real time.
Corpus refers to the extensive e-text library through scientific sampling and processing, and ChnSentiCorp specifically may be used
Corpus, but only with ChnSentiCorp corpus, effect is not good enough, is much carried because barrage content aggregation has
It is broadcast live the proprietary vocabulary of platform characteristic, such as " 666 ", its not just numerical value represents cheer in live scene;Also
" naked wolf " is the proprietary term that werewolf kills game.Therefore it needs to combine the barrage characteristic that platform is broadcast live, corpus is extended.
Extension corpus in follow-up word segmentation processing, can effectively reduce the value number of feature extraction, for example will be " naked
Corpus is added in a wolf " word, can be a word by " naked wolf " cutting during follow-up participle, without being divided into " naked " and " wolf "
Two words.The personalized word that some high frequencies can also occur is added in corpus, and personalized word is different from conventional
Word, corpus can daily all can timed increase update, to improve the accuracy of corpus.
Specifically, can on corpus expansion platform, by using the mode of training and the self study of neural network, according to
Barrage expansion of content corpus.
Processed offline analysis includes processing analysis barrage content.
Barrage content is analyzed in specific processing:
S21 carries out word segmentation processing to barrage content.
Word segmentation processing is exactly the set by every barrage Content Transformation at word one by one according to bag of words, and can be with
Some are influenced small or without influence word to be filtered, finally obtains effective word in this way, it can be in transfer process
Segmented according to corpus, for example, there is " naked wolf " word in corpus, to barrage " today the naked wolf of main broadcaster play it is so good
" carry out word segmentation processing when, will " today ", " " and " " filter out, remaining word be exactly " main broadcaster ", " naked wolf ",
" object for appreciation " and " so good ", then the bag of words of the barrage content are exactly [" main broadcaster ", " naked wolf ", " object for appreciation ", " so good "].
In other better embodiments, barrage content can be pre-processed before being segmented to barrage content.
Pretreatment refers to removing on some influential spcial characters of participle, such as space, if between a word
There are spaces, the case where being divided into a word it is possible that being actually needed, but be divided into two words because of the presence in space.
For example, carrying space in " if naked wolf " this word, returns when participle and " a naked wolf " is divided into " naked " and " wolf ", this
Sample just affects the accuracy rate of follow-up barrage identification, is empty therefore, it is necessary to when pretreated, remove in barrage content
Data, punctuation mark and barrage type are the data of sky.
S22, will be including in the storage to data warehouse of the barrage data of the barrage content after word segmentation processing.
In the present embodiment, hive may be used in data warehouse, and hive is built upon the basis of the data warehouse on Hadoop
Framework.It provides a series of tool, can be used for carry out data extraction conversion load (ETL), this be one kind can store,
Inquiry and analysis are stored in the mechanism of the large-scale data in Hadoop.Hive defines simple class SQL query language, referred to as
HQL, it allows the user for being familiar with SQL to inquire data.Meanwhile this language also allows the developer's exploitation for being familiar with MapReduce
Customized mapper and reducer handles the analysis work of the impossible complexity of built-in mapper and reducer.
Data format unspecial hive.Hive can be very good to be operated on Thrift, control separator, also user be allowed to refer to
Determine data format.
In further preferred embodiment, barrage content is analyzed in data warehouse, whether judges barrage content
For rubbish barrage, and will be in analysis result storage to result set database.
In specific implementation process, the neural network model that the RNN training of bluebeard compound vector sum may be used judges in barrage
Whether appearance is rubbish barrage, and since hive analysis times are long and inquiry required time is longer, can be deposited analysis result
It stores up in result set database, result set database can be mysq1 or ElasticSearch etc..If barrage is rubbish barrage,
Then when watching playback, which will not be displayed on the screen user.Meanwhile to sending by way of warning letter in dispatching station
Rubbish barrage person sounds a warning, and in the case of necessary, can make and prohibit speech processing, after reaching certain number, can make permanent taboo
Speech processing.
In further preferred embodiment, it is that current results collection can be marked in Redis for which day processing analysis
As a result, label can be that FLAG_danmu_yyyyMMdd can be on the day of in this way when carrying out query processing analysis result
In the case that the also non-analyzing processing of barrage data is completed, then the last time is obtained by accessing FLAG_danmu_yyyyMMdd
Analysis and processing result achievees the purpose that High Availabitity.
In specific implementation process, the progress of database service interface inquiry processed offline analysis can be utilized.
Database service interface mainly uses the HTTP interface that springBoot is provided, requesting party to need to transmit user id or close
The information such as title, Query Dates, it is necessary first to access FLAG_danmu_yyyyMMdd to obtain newest data set SET_
YyyyMMdd, then provides data query result, and main process is as follows:
S3, according to carrying out after processing analysis to barrage content in step S2 as a result, carrying out state analysis to user.
In the present embodiment, rubbish in the barrage content that a certain specific user sends in the second preset time period can be analyzed
Thus rubbish barrage proportion judges whether target user is passive states.
For example, a certain user can be analyzed in the nearest 7 days barrage total numbers sent out, daily barrage number, daily barrage
Content and most nearby rubbish barrage proportion in 100 barrages, when rubbish barrage proportion is more than 50%, it is believed that
The user is in passive states, at this moment can be sounded a warning to the user by way of warning letter in dispatching station, and warning is multiple
After the taboo speech time can be set or permanent prohibit speech.Moreover, when judging that a certain user is in passive states, if the user is not in
Prohibit speech state, then whether the barrage content that can pay close attention to user transmission has bad speech, it is possible thereby to help administrator
Concern range is reduced according to User Status, more quickly finds bad speech.
In this way, the method provided through this embodiment, is handled by carrying out a point library to barrage data, can effectively be coped with
Data Migration business, it is also ensured that barrage content can be retrieved in time;It is handled with off-line analysis by handling in real time,
Administrator can be effectively helped to close bad speech;To user carry out affective state analysis can effectively help administrator according to
User Status reduces concern range, so that it is more quick to prohibit speech in real time.
Based on same inventive concept, refering to what is shown in Fig. 2, the embodiment of the present invention also provides a kind of computer-readable storage medium
Matter 201, is stored thereon with executable instruction 202, and executable instruction 202 when executed by one or more processors, is realized such as
On any barrage processing method the step of.
Based on same inventive concept, refering to what is shown in Fig. 3, the embodiment of the present invention additionally provides a kind of electronic equipment 301, the electricity
Sub- equipment 301 may include:
Memory 310 is used to store executable instruction 311;And
Processor 320 is used to execute the executable instruction 311 stored in memory 310, realizes any bullet as above
The step of method of curtain processing.
For the embodiment of the present invention, it is also necessary to explanation, in the absence of conflict, the embodiment of the present invention and reality
The feature in example is applied to can be combined with each other to obtain new embodiment.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, it will be understood by those of ordinary skill in the art that, it can be to the present invention's
Technical solution is modified or equivalent replacement, without departing from the spirit of the technical scheme of the invention and range.
Claims (10)
1. a kind of barrage processing method, includes the following steps:
S1, collects original barrage data, and the original barrage data include the barrage content that user sends;
S2 carries out processing in real time to the original barrage data and processed offline is analyzed, wherein
The processed offline analysis includes that the barrage content is analyzed in processing;And
S3, according to carrying out after processing analysis to the barrage content in step S2 as a result, carrying out state analysis to user.
2. the method as described in claim 1, which is characterized in that it is described it is real-time processing include:
The original barrage data are stored into database, and are deposited the initial data respectively according to the first preset time period
In the different subdata bases for storing up database.
3. method as claimed in claim 1 or 2, which is characterized in that it is described it is real-time processing further include:According to the barrage content
Extend corpus.
4. method as claimed in claim 3, which is characterized in that in step s 2, the barrage content is analyzed in the processing
Step includes:
S21 carries out word segmentation processing to the barrage content;And
S22, will be including in the storage to data warehouse of the barrage data of the barrage content after word segmentation processing.
5. method as claimed in claim 4, which is characterized in that before step S21, the barrage content is analyzed in the processing
The step of further include:
S20 pre-processes the barrage content, and the pretreatment includes removal special word influential on word segmentation processing
Symbol.
6. method as claimed in claim 4, which is characterized in that carry out processing point to barrage content in the data warehouse
Analysis, judges whether the barrage content is rubbish barrage, and will be in analysis result storage to result set database.
7. method as claimed in claim 6, which is characterized in that in the result set database, according to target user
Rubbish barrage proportion in the barrage content sent in two preset time periods, judges whether the target user is passive shape
State.
8. the method as described in claim 1, which is characterized in that the processed offline analysis further includes utilizing database service interface
Inquire the progress of processed offline analysis.
9. a kind of computer readable storage medium, is stored thereon with executable instruction, which is characterized in that described instruction is by handling
When device executes, the step of realizing barrage processing method as described in any one of claim 1-8.
10. a kind of electronic equipment, including:
Memory, for storing executable instruction;And
Processor, for executing the executable instruction stored in the memory, to realize such as any one of claim 1-8
The step of described barrage processing method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810453525.9A CN108650546B (en) | 2018-05-11 | 2018-05-11 | Barrage processing method, computer-readable storage medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810453525.9A CN108650546B (en) | 2018-05-11 | 2018-05-11 | Barrage processing method, computer-readable storage medium and electronic device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108650546A true CN108650546A (en) | 2018-10-12 |
CN108650546B CN108650546B (en) | 2021-07-23 |
Family
ID=63755023
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810453525.9A Active CN108650546B (en) | 2018-05-11 | 2018-05-11 | Barrage processing method, computer-readable storage medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108650546B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111263195A (en) * | 2020-01-08 | 2020-06-09 | 上海米哈游天命科技有限公司 | Barrage processing method and device, server equipment and storage medium |
CN111294661A (en) * | 2020-01-21 | 2020-06-16 | 上海米哈游天命科技有限公司 | Bullet screen display method and device, bullet screen server equipment and storage medium |
CN112507164A (en) * | 2020-12-07 | 2021-03-16 | 重庆邮电大学 | Bullet screen filtering method and device based on content and user identification and storage medium |
CN114257563A (en) * | 2021-12-20 | 2022-03-29 | 创盛视联数码科技(北京)有限公司 | Method for filtering chat content callback in live broadcast room |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140172989A1 (en) * | 2012-12-14 | 2014-06-19 | Yigal Dan Rubinstein | Spam detection and prevention in a social networking system |
CN104123328A (en) * | 2013-04-28 | 2014-10-29 | 北京千橡网景科技发展有限公司 | Method and device used for inhibiting spam comments in website |
CN106341703A (en) * | 2016-08-30 | 2017-01-18 | 乐视控股(北京)有限公司 | Bullet screen processing method and device |
CN107239440A (en) * | 2017-04-21 | 2017-10-10 | 同盾科技有限公司 | A kind of rubbish text recognition methods and device |
CN107633077A (en) * | 2017-09-25 | 2018-01-26 | 南京安链数据科技有限公司 | A kind of system and method for more strategy cleaning social media text datas |
-
2018
- 2018-05-11 CN CN201810453525.9A patent/CN108650546B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140172989A1 (en) * | 2012-12-14 | 2014-06-19 | Yigal Dan Rubinstein | Spam detection and prevention in a social networking system |
CN104123328A (en) * | 2013-04-28 | 2014-10-29 | 北京千橡网景科技发展有限公司 | Method and device used for inhibiting spam comments in website |
CN106341703A (en) * | 2016-08-30 | 2017-01-18 | 乐视控股(北京)有限公司 | Bullet screen processing method and device |
CN107239440A (en) * | 2017-04-21 | 2017-10-10 | 同盾科技有限公司 | A kind of rubbish text recognition methods and device |
CN107633077A (en) * | 2017-09-25 | 2018-01-26 | 南京安链数据科技有限公司 | A kind of system and method for more strategy cleaning social media text datas |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111263195A (en) * | 2020-01-08 | 2020-06-09 | 上海米哈游天命科技有限公司 | Barrage processing method and device, server equipment and storage medium |
CN111263195B (en) * | 2020-01-08 | 2022-04-15 | 上海米哈游天命科技有限公司 | Barrage processing method and device, server equipment and storage medium |
CN111294661A (en) * | 2020-01-21 | 2020-06-16 | 上海米哈游天命科技有限公司 | Bullet screen display method and device, bullet screen server equipment and storage medium |
CN112507164A (en) * | 2020-12-07 | 2021-03-16 | 重庆邮电大学 | Bullet screen filtering method and device based on content and user identification and storage medium |
CN112507164B (en) * | 2020-12-07 | 2022-04-12 | 重庆邮电大学 | Bullet screen filtering method and device based on content and user identification and storage medium |
CN114257563A (en) * | 2021-12-20 | 2022-03-29 | 创盛视联数码科技(北京)有限公司 | Method for filtering chat content callback in live broadcast room |
CN114257563B (en) * | 2021-12-20 | 2023-10-24 | 创盛视联数码科技(北京)有限公司 | Filtering method for chat content callback in live broadcasting room |
Also Published As
Publication number | Publication date |
---|---|
CN108650546B (en) | 2021-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106874378B (en) | Method for constructing knowledge graph based on entity extraction and relation mining of rule model | |
US20210097089A1 (en) | Knowledge graph building method, electronic apparatus and non-transitory computer readable storage medium | |
CN107766371B (en) | Text information classification method and device | |
CN105447184B (en) | Information extraction method and device | |
US20200301954A1 (en) | Reply information obtaining method and apparatus | |
CN105956082B (en) | Real time data processing and storage system | |
CN108650546A (en) | Barrage processing method, computer readable storage medium and electronic equipment | |
CN105138652B (en) | A kind of enterprise's incidence relation recognition methods and system | |
US11036768B2 (en) | Scalable capturing, modeling and reasoning over complex types of data for high level analysis applications | |
CN110717049A (en) | Text data-oriented threat information knowledge graph construction method | |
CN110275935A (en) | Processing method, device and storage medium, the electronic device of policy information | |
CN111581376B (en) | Automatic knowledge graph construction system and method | |
CN106030571A (en) | Dynamically modifying elements of user interface based on knowledge graph | |
CN109543067A (en) | Enterprise's production status based on artificial intelligence monitors analysis system in real time | |
CN107092639A (en) | A kind of search engine system | |
CN110019616A (en) | A kind of POI trend of the times state acquiring method and its equipment, storage medium, server | |
CN106354860A (en) | Method for automatically labelling and pushing information resource based on label sets | |
CN108073625A (en) | For the system and method for metadata information management | |
CN109271428A (en) | Data pick-up method and method for exhibiting data based on geography information | |
CN111523324A (en) | Training method and device for named entity recognition model | |
CN111858728A (en) | Data extraction method, device and equipment for different data sources and storage medium | |
CN109150585A (en) | A kind of network O&M failure solution, system, device and storage medium | |
CN105518644A (en) | Method for processing and displaying real-time social data on map | |
CN108287889B (en) | A kind of multi-source heterogeneous date storage method and system based on elastic table model | |
CN108959664A (en) | Distributed file system based on picture processor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |