CN109271509A - Generation method, device, computer equipment and the storage medium of direct broadcasting room topic - Google Patents
Generation method, device, computer equipment and the storage medium of direct broadcasting room topic Download PDFInfo
- Publication number
- CN109271509A CN109271509A CN201810969224.1A CN201810969224A CN109271509A CN 109271509 A CN109271509 A CN 109271509A CN 201810969224 A CN201810969224 A CN 201810969224A CN 109271509 A CN109271509 A CN 109271509A
- Authority
- CN
- China
- Prior art keywords
- topic
- direct broadcasting
- broadcasting room
- head stack
- title
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses generation method, device, computer equipment and the storage mediums of a kind of direct broadcasting room topic.The described method includes: obtaining the publishing documents for meeting attention rate condition at least one information publishing platform;Using similarity mode condition, the heading message of publishing documents is collected in corresponding head stack;It determines title keyword corresponding with head stack, and according to title keyword, constructs direct broadcasting room topic.It is time-consuming and laborious that the technical solution of the embodiment of the present invention solves existing topic library building mode, cost of labor is higher and has the technological deficiency of certain information delay, direct broadcasting room topic is constructed by the publishing documents of information platform, realize artificial topic building method, this method is not only not necessarily to manually participate in, and quick, convenient, real-time highland construction topic may be implemented, the timeliness of the topic constructed is higher.
Description
Technical field
The present embodiments relate to data mining technology field more particularly to a kind of generation methods of direct broadcasting room topic, dress
It sets, computer equipment and storage medium.
Background technique
Class software is broadcast live as a kind of converter tools and provides a kind of entertainment way of participatory for user, since it has
Real-time is good, interactive strong feature, it is made to have obtained liking and pursuing for users rapidly.It is main during live streaming at present
Broadcasting the exchange and interdynamic between spectators is typically all using a certain topic as main line.
The interaction topic of direct broadcasting room, either what main broadcaster was set when starting broadcasting by interactive voice, it is also possible to main broadcaster
It is chosen from topic library.So correspondingly, it is necessary to before direct broadcasting room starts broadcasting, be provided with a topic library.The prior art
In, topic library is typically all to be manually entered by staff.
In the implementation of the present invention, the discovery prior art has following defects that when establishing topic library inventor, talks about
Content in exam pool is manually entered by staff, and human cost is high, and its selected topic has certain information
Hysteresis quality.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of generation method of direct broadcasting room topic, device, computer equipment and
Storage medium, to optimize existing direct broadcasting room topic generation method.
In a first aspect, the embodiment of the invention provides a kind of generation methods of direct broadcasting room topic, comprising:
In at least one information publishing platform, the publishing documents for meeting attention rate condition are obtained;
Using similarity mode condition, the heading message of the publishing documents is collected in corresponding head stack;
It determines title keyword corresponding with the head stack, and according to the title keyword, constructs direct broadcasting room words
Topic.
In the above-mentioned methods, optionally, the attention rate condition includes at least one of following:
Amount of reading is more than or equal to reading number threshold value, comment amount is more than or equal to comment number threshold value and the amount of thumbing up is greater than etc.
In thumbing up number threshold value.
In the above-mentioned methods, optionally, title keyword corresponding with the head stack is determined, comprising:
Word segmentation processing is carried out at least one heading message for including in the head stack, obtains at least two participles;
Calculate the word frequency of each participle;
Each participle is ranked up according to word frequency, and obtains institute corresponding with the head stack according to ranking results
State title keyword.
In the above-mentioned methods, optionally, before the word frequency for calculating each participle, further includes:
Everyday words filtering is carried out to each participle according to everyday words dictionary.
In the above-mentioned methods, optionally, according to the title keyword, direct broadcasting room topic is constructed, comprising:
The title keyword is sent to label and determines platform, the label is obtained and determines platform feedback, and it is described
The corresponding Words ' Attributes label of title keyword;
Obtain standard topic clause corresponding with the Words ' Attributes label, wherein include in the standard topic clause
For filling the void item of title keyword;
The title keyword and the standard topic clause are combined, the direct broadcasting room topic is obtained.
In the above-mentioned methods, optionally, after according to the title keyword, constructing direct broadcasting room topic, further includes:
The direct broadcasting room topic is sent to audit platform and carries out topic audit;
If receiving the audit of the audit platform feedback by response, the direct broadcasting room topic is stored in topic
In library;
Wherein, the topic stored in the topic library is selected for being supplied to main broadcaster end, so that the main broadcaster end is selected
In target topic shown in corresponding direct broadcasting room.
In second aspect, the embodiment of the invention provides a kind of generating means of direct broadcasting room topic, comprising:
Document obtains module, at least one information publishing platform, obtaining the publication text for meeting attention rate condition
Shelves;
Title collects module, and for using similarity mode condition, the heading message of the publishing documents is collected in right
In the head stack answered;
Direct broadcasting room topic constructing module, for determining title keyword corresponding with the head stack, and according to described
Title keyword constructs direct broadcasting room topic.
In above-mentioned apparatus, optionally, the attention rate condition includes at least one of following:
Amount of reading is more than or equal to reading number threshold value, comment amount is more than or equal to comment number threshold value and the amount of thumbing up is greater than etc.
In thumbing up number threshold value.
In the third aspect, the embodiment of the invention provides a kind of computer equipment, the computer equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes method described in any embodiment of the present invention.
It is described the embodiment of the invention provides a kind of storage medium comprising computer executable instructions in fourth aspect
Computer executable instructions as computer processor when being executed for executing method described in any embodiment of the present invention.
The embodiment of the invention provides generation method, device, computer equipment and the storage medium of a kind of direct broadcasting room topic,
By first collecting the heading message for meeting the publishing documents of attention rate condition into head stack, then according to head stack
Corresponding keyword constructs direct broadcasting room topic, and it is time-consuming and laborious to solve existing topic library building mode, cost of labor it is higher and
Technological deficiency with certain information delay constructs direct broadcasting room topic by the publishing documents of information platform, realizes
Artificial topic building method, this method are not only not necessarily to manually participate in, and quick, convenient, real-time highland structure may be implemented
Topic is made, the timeliness of the topic constructed is higher.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the generation method for direct broadcasting room topic that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow chart of the generation method of direct broadcasting room topic provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of flow chart of the generation method for direct broadcasting room topic that the embodiment of the present invention three provides;
Fig. 4 is a kind of structure chart of the generating means for direct broadcasting room topic that the embodiment of the present invention four provides;
Fig. 5 is a kind of structure chart for computer equipment that the embodiment of the present invention five provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawing to of the invention specific real
Example is applied to be described in further detail.It is understood that specific embodiment described herein is used only for explaining the present invention,
Rather than limitation of the invention.
It also should be noted that only the parts related to the present invention are shown for ease of description, in attached drawing rather than
Full content.It should be mentioned that some exemplary embodiments are described before exemplary embodiment is discussed in greater detail
At the processing or method described as flow chart.Although operations (or step) are described as the processing of sequence by flow chart,
It is that many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be by again
It arranges.The processing can be terminated when its operations are completed, it is also possible to have the additional step being not included in attached drawing.
The processing can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 is a kind of flow chart of the generation method for direct broadcasting room topic that the embodiment of the present invention one provides, the present embodiment
Method can be executed with the generating means of direct broadcasting room topic, which can be realized by way of hardware and/or software, and general
It can be integrated in the equipment such as server and intelligent mobile terminal.The method of the present embodiment specifically includes:
S101, at least one information publishing platform, obtain and meet the publishing documents of attention rate condition.
In the present embodiment, information publishing platform specifically can be news website, news category application program, microblog,
Wechat application program etc..What the data that attention rate condition specifically refers to user's attention rate for embodying publishing documents should meet
Condition.Illustratively, attention rate condition specifically can be the frequency of reading of publishing documents, number of reviews, hop count, thumb up number
The condition that amount or collection number are met, naturally it is also possible to be multiple data (such as frequency of reading and number of reviews) while meet
Condition.
It is understood that information publishing platform generally all can be in time to newest, most popular and social influence
The higher document of power is issued, and these are newest, the higher document of most popular and social effectiveness also will receive
The highest attention of user.Therefore, the publishing documents for meeting attention rate condition acquired from information publishing platform should be worked as
Lower hot topic degree and the higher document of popularity, it is possible thereby to make the direct broadcasting room topic according to determined by the publishing documents of acquisition
Temperature and popularity are all higher, can preferably be matched with live streaming class application, and for being used as direct broadcasting room (especially voice broadcast
Between) in discuss topic.
S102, using similarity mode condition, the heading message of publishing documents is collected in corresponding head stack.
In the present embodiment, from information publishing platform obtain meet the publishing documents of attention rate condition after, first
Meeting carries out similarity mode to the heading message of acquired each publishing documents, then according to matching result and similarity mode
Condition carries out the heading message of acquired publishing documents to collect division, is divided in one or more head stack.
In the present embodiment, Europe can specifically be passed through by carrying out similarity mode to the heading message of acquired publishing documents
The calculation methods such as distance, Euclidean distance, cosine similarity, Minkowski distance and manhatton distance are obtained in several determines two
Similarity between heading message.The text that similarity mode condition specifically can be the heading message of two publishing documents is similar
Degree is greater than given threshold etc..
It is understood that above-mentioned given threshold is arranged higher, then all heading messages in a head stack
Similarity it is higher, and then the quantity of the different title keywords that are included of all heading messages in the head stack is just
It can be fewer.
It will be further understood that in order to reduce the correlation of direct broadcasting room topic (that is different direct broadcasting rooms words
Similarity between topic is answered lower), for two higher title keywords of similarity, it is crucial that one of title can be abandoned
Word constructs direct broadcasting room topic just for another keyword.Therefore, above-mentioned given threshold is not easy to be arranged excessively high, otherwise,
The similarity of the title keyword determined according to different head stacks is possible to excessively high, and then leads to the correlation of direct broadcasting room topic
Property is excessively high.
In the present embodiment, the collecting method of the heading message of publishing documents specifically can be one heading message of selection and make
For information to be matched, the similarity with the heading message is met to all heading messages and the mark of similarity mode condition
Topic information is collected into a heading message set.
S103, determination title keyword corresponding with head stack, and according to title keyword, construct direct broadcasting room topic.
In the present embodiment, after the heading message of publishing documents is divided into head stack, it can determine whether each mark
The corresponding title keyword of topic set.One head stack can correspond to a title keyword, can also correspond to multiple marks
Inscribe keyword.Wherein, it is most specifically to can be frequency of occurrence in all heading messages in the head stack for title keyword
Or frequency of occurrence be greater than given threshold word.
Further, after determining title keyword, so that it may be talked about according to the composition of content direct broadcasting room of title keyword
Topic, a title keyword can specifically construct one or more direct broadcasting room topics.Illustratively, if title keyword is
" clothes ", then specifically can be according to the direct broadcasting room topic of " clothes " construction, " you like the clothes of what style ", " you are frequent
Apparel brand of purchase " etc..
The embodiment of the invention provides a kind of generation methods of direct broadcasting room topic, by will meet attention rate condition first
The heading message of publishing documents is collected into head stack, then according to the corresponding keyword construction direct broadcasting room words of head stack
Topic, solves that existing topic library building mode is time-consuming and laborious, and cost of labor is higher and skill with certain information delay
Art defect constructs direct broadcasting room topic by the publishing documents of information platform, realizes artificial topic building method, this method
It is not only participated in without artificial, and quick, convenient, real-time highland construction topic, the timeliness of the topic constructed may be implemented
Property is higher.
Embodiment two
Fig. 2 is a kind of flow chart of the generation method of direct broadcasting room topic provided by Embodiment 2 of the present invention.The present embodiment with
It is optimized based on above-described embodiment, in the present embodiment, gives a kind of materialization keyword and determine method, increase simultaneously
Everyday words filtration step, and embody the specific embodiment of direct broadcasting room topic building method.
Correspondingly, the method for the present embodiment specifically includes:
S201, at least one information publishing platform, obtain and meet the publishing documents of attention rate condition.
S202, using similarity mode condition, the heading message of publishing documents is collected in corresponding head stack.
S203, word segmentation processing is carried out at least one heading message for including in head stack, obtains at least two participles.
In the present embodiment, step 203 to step 206 embodies the determination process of title keyword.
Since the heading message in head stack meets similarity mode condition, it is known that belong to the institute in a head stack
There is the word content similarity in heading message higher, therefore, in the present embodiment, can only use in a head stack
One heading message determines the corresponding one or more title keywords of the head stack, of course for improving title keyword
Accuracy, it is preferable to use multiple or all titles information is crucial to determine the corresponding one or more titles of the head stack
Word.
Further, determine that the corresponding one or more titles of head stack are crucial if it is multiple heading messages are used
Word randomly selects multiple heading messages then specifically can be from head stack, can also be multiple according to similarity selection
Heading message etc., the present embodiment is not limited this.
Typically, word segmentation processing can be carried out to all titles information for including in head stack respectively, and then can obtained
To word segmentation result corresponding with each heading message.
S204, everyday words filtering is carried out to each participle according to everyday words dictionary.
It is understood that everyday words appear in the word frequency in heading message can be higher, it is thus possible to can miss everyday words
It is determined as title keyword.So in the present embodiment, after being segmented to heading message, being carried out first to participle normal
The filtering of word.Wherein, the everyday words dictionary specifically can be adverbial word dictionary, conjunction dictionary, preposition dictionary and auxiliary word word
One or more in library.
Typically, include in the adverbial word dictionary: " ", " ", " when " or the common adverbial word such as " most ";The conjunction
Include in dictionary: the common conjunction such as " with ", " just ", " wanting ", " use " or "and";Include in the preposition dictionary: " certainly ",
" beating ", " to " or " and " etc. common preposition;Include in the auxiliary word dictionary: " obtaining ", " only ", " to " or " " etc. is common
Auxiliary word.
S205, the filtered word frequency respectively segmented of everyday words is calculated.
In the present embodiment, title keyword is determined according to the word frequency of each participle obtained after heading message participle
, therefore, after carrying out everyday words filtering to participle, the word frequency of each participle will be counted, i.e., believed with each title
It ceases in corresponding word segmentation result, the frequency of occurrence of each participle.
S206, each participle is ranked up according to word frequency, and obtains title corresponding with head stack according to ranking results
Keyword.
In the present embodiment, from big to small or from small to large according to word frequency, each participle is ranked up, it then both can be only
It chooses the highest participle of word frequency and is used as title keyword, all participles that can also choose word frequency greater than setting word frequency threshold are made
For title keyword.
S207, it title keyword is sent to label determines platform, obtain label and determine platform feedback, with title key
The corresponding Words ' Attributes label of word.
In the present embodiment, step 207 to step 209 embodies the side that direct broadcasting room topic is constructed according to title keyword
Method.
In the present embodiment, a kind of Words ' Attributes label is corresponding with a set of standard topic clause, therefore, is determining title pass
After the corresponding Words ' Attributes label of keyword, so that it may easily construct the corresponding direct broadcasting room topic of the title keyword.Its
In, Words ' Attributes label specifically can be name, place name, apparel brand, cosmetics brand etc..
Illustratively, if Words ' Attributes label is " place name ", corresponding a set of standard topic clause may include:
" you like XXX? ", " you removed XXX? ", " you feel XXX beauty? " etc..Wherein, " XXX " this blank position is used for
Fill title keyword.
S208, acquisition standard topic clause corresponding with Words ' Attributes label, wherein include being used in standard topic clause
Fill the void item of title keyword.
S209, title keyword and standard topic clause are combined, obtain direct broadcasting room topic.
In the present embodiment, it can specifically combine title keyword with all standard topic clause, obtain title key
The corresponding all direct broadcasting room topics of word.Further, it if the limited amount system of direct broadcasting room topic, can be closed according to title
The quantity of keyword, the quantity of the corresponding standard topic clause of every one kind Words ' Attributes label, determines each title keyword institute
The quantity for the direct broadcasting room topic that need to be formed.
S210, direct broadcasting room topic is sent to audit platform progress topic audit.
In order to ensure it is flat to be sent to audit in the present embodiment by direct broadcasting room topic health for the direct broadcasting room topic of construction
Platform carries out topic audit.Wherein, the mode of topic audit specifically can be staff and audit, be also possible to by with not
Good word match is audited etc., and the present embodiment is not limited this.
If direct broadcasting room topic is stored in topic library by response by S211, the audit for receiving audit platform feedback
In, wherein the topic stored in topic library is selected for being supplied to main broadcaster end, so that the target topic that main broadcaster end is chosen exists
It is shown in corresponding direct broadcasting room.
The embodiment of the invention provides a kind of generation method of direct broadcasting room topic, this method embodies the determination of keyword
Method improves the accuracy of title keyword extraction.The step of increasing everyday words filtering simultaneously, avoids everyday words to mark
The bad interference of keyword extraction is inscribed, and the method for embodying direct broadcasting room topic construction, realizes quick, easy and have
Effect ground constructs direct broadcasting room topic according to title keyword.
On the basis of the various embodiments described above, attention rate condition can specifically include at least one of following: amount of reading is greater than
It is more than or equal to equal to reading number threshold value, comment amount more than or equal to comment number threshold value and the amount of thumbing up and thumbs up number threshold value.
The benefit being arranged in this way is: can correctly, effectively filter out the higher publishing documents of attention rate.
Embodiment three
Fig. 3 is a kind of flow chart of the generation method for direct broadcasting room topic that the embodiment of the present invention three provides.The present embodiment with
Optimized based on above-described embodiment, in the present embodiment, give it is a kind of increase direct broadcasting room topic setting up procedure it is specific
Embodiment.
Correspondingly, the method for the present embodiment specifically includes:
S301, at least one information publishing platform, obtain and meet the publishing documents of attention rate condition.
S302, using similarity mode condition, the heading message of publishing documents is collected in corresponding head stack.
S303, determination title keyword corresponding with head stack, and according to title keyword, construct direct broadcasting room topic.
S304, all direct broadcasting room topics are stored to setting storage region, constitutes topic library.
The topic setting instruction for the direct broadcasting room that S305, server are sent according to main broadcaster end, obtains alternative words from topic library
Topic collective feedback gives main broadcaster end.
In the present embodiment, main broadcaster end specifically can be intelligent mobile terminal, the tablet computer that the main broadcaster of direct broadcasting room uses
Equal terminal devices.Direct broadcasting room specifically refers to what main broadcaster was established by using live streaming class application program, (sees for direct broadcasting room user
It is many) virtual room that enters, it typically can be between voice broadcast or between net cast etc..It include multiple be used in topic library
The legal topic discussed in direct broadcasting room.
In the present embodiment, topic setting instruction specifically can be the topic setting instruction for adding topic, can be with
It is that instruction etc. is set for replacing the topic of topic.Specifically, the main broadcaster of direct broadcasting room can pass through selection topic when starting broadcasting
Setting control makes main broadcaster end send the topic setting instruction of addition topic to server, can also pass through choosing during live streaming
Select the topic setting instruction that replacement topic control makes main broadcaster end send replacement topic to server.
It is understood that user is when using being broadcast live class application program and entering direct broadcasting room, most of situation is all straight
It has started broadcasting between broadcasting a period of time, therefore user can not know the topic of direct broadcasting room currently exchanged when just entering direct broadcasting room,
So that user is difficult to rapidly incorporate.Therefore, in the present embodiment, main broadcaster can pass through main broadcaster end to service when direct broadcasting room starts broadcasting
Device sends topic setting instruction, and then server passes through direct broadcasting room topic setting method composed by step 305 to step 307,
Enable main broadcaster's displaying target topic in direct broadcasting room.
In the present embodiment, server obtained from topic library alternative topic set mode either server from words
A certain number of alternative topics are randomly selected in exam pool and form alternative topic set, are also possible to server according to the number of topic
Or the generation time of topic, according to sequence from big to small or from small to large, the alternative topic composition for obtaining setting quantity is standby
Select topic set etc..Typically, server can recorde each alternative words into the alternative topic set that same main broadcaster pushes
Topic, is repeatedly pushed to same main broadcaster to avoid same alternative topic.
Wherein, which specifically can be the fixed numbers of system setting, can also be by main broadcaster end freedom
The customized numerical value being arranged can also be according to the alternative topic display mode at different main broadcaster ends and the variation of position and dynamically become
The numerical value etc. of change, the present embodiment comparison are not limited.
Further, alternative topic included in topic library is either be broadcast live the preparatory typing of staff of platform
, it is also possible to can also be and screened from network hot word by multiple main broadcasters (for example, main broadcaster with certain permission) offer
Etc., naturally it is also possible to it is to be obtained by any two ways in above-mentioned three kinds alternative topic acquisition modes or all three mode
Alternative topic is taken, the present embodiment is also not limited this.
S306, server receive the target topic that main broadcaster end is determined according to the alternative topic set of feedback.
In the present embodiment, main broadcaster end, can be by alternative topic after receiving the alternative topic set of server feedback
Set is shown, so that the main broadcaster of direct broadcasting room can therefrom choose interested topic, i.e. target topic.It is determined simultaneously in main broadcaster
After choosing target topic, the target topic selected by main broadcaster can be sent to server by main broadcaster end.
Target topic is pushed in direct broadcasting room and is shown by S307, server.
In the present embodiment, which can be pushed to direct broadcasting room after receiving target topic by server
In, so that whole direct broadcasting room corresponding with the direct broadcasting room with can check the target topic per family.It typically, can directly will be above-mentioned
Target topic push to the associated whole user terminals in main broadcaster end, to indicate user terminal setting in corresponding user side display interface
Determine display position and shows the target topic.
Further, it can also synchronize above-mentioned target topic synchronized push to main broadcaster end, to indicate main broadcaster end in correspondence
The setting display position of main broadcaster side display interface show the target topic.
It is held what needs to be explained here is that the step 301 in the present embodiment specifically can be the same server to step 307
Capable, it is also possible to different server execution.If step 301 to the step 307 in the present embodiment is that different server is held
Capable, then step 301 to step 304 is that the same server executes, step 305 to step 307 is the same server
It executes.
The embodiment of the invention provides a kind of generation methods of direct broadcasting room topic, and this method increase the settings of direct broadcasting room topic
Process solves user in the prior art and needs to take a significant amount of time the technological deficiency that can just find interested direct broadcasting room, leads to
Showing in real time to direct broadcasting room exchange theme is spent, so that user can be with the exchange of timely learning direct broadcasting room after entering direct broadcasting room
Theme greatly reduces user and is used to determine whether to be resident the required time in direct broadcasting room, and then shortens user and find and feel emerging
Time needed for the direct broadcasting room of interest.In addition, the technical solution of the present embodiment be also possible that just enter direct broadcasting room user it is quick
The topic discussed in direct broadcasting room is incorporated, the usage experience of user is improved.
Example IV
Fig. 4 is a kind of structure chart of the generating means for direct broadcasting room topic that the embodiment of the present invention four provides.As shown in figure 4,
Described device includes: that document obtains module 401, title collects module 402 and direct broadcasting room topic constructing module 403, in which:
Document obtains module 401, for obtaining the publication for meeting attention rate condition at least one information publishing platform
Document;
Title collects module 402, and for using similarity mode condition, the heading message of publishing documents is collected in correspondence
Head stack in;
Direct broadcasting room topic constructing module 403 for determining title keyword corresponding with head stack, and is closed according to title
Keyword constructs direct broadcasting room topic.
The embodiment of the invention provides a kind of generating means of direct broadcasting room topic, which passes through document first and obtains module
In at least one information publishing platform, the publishing documents for meeting attention rate condition are obtained, module is then collected by title and is adopted
With similarity mode condition, the heading message of publishing documents is collected in corresponding head stack, is talked about finally by direct broadcasting room
It inscribes constructing module and determines title keyword corresponding with head stack, and according to title keyword, construct direct broadcasting room topic.
Which solves existing topic library building mode is time-consuming and laborious, cost of labor is higher and has certain information
The technological deficiency of hysteresis quality constructs direct broadcasting room topic by the publishing documents of information platform, realizes artificial topic construction
Method, this method are not only not necessarily to manually participate in, and quick, convenient, real-time highland construction topic may be implemented, and are constructed
The timeliness of topic is higher.
On the basis of the various embodiments described above, attention rate condition may include at least one of following:
Amount of reading is more than or equal to reading number threshold value, comment amount is more than or equal to comment number threshold value and the amount of thumbing up is greater than etc.
In thumbing up number threshold value.
On the basis of the various embodiments described above, direct broadcasting room topic constructing module 403 may include:
Participle unit obtains at least for carrying out word segmentation processing at least one heading message for including in head stack
Two participles;
Word frequency computing unit, for calculating the word frequency of each participle;
Title keyword acquiring unit, for according to word frequency to it is each participle be ranked up, and according to ranking results obtain with
The corresponding title keyword of head stack.
On the basis of the various embodiments described above, can also include:
Everyday words filter element, for being carried out according to everyday words dictionary to each participle before the word frequency for calculating each participle
Everyday words filtering.
On the basis of the various embodiments described above, direct broadcasting room topic constructing module 403 can also include:
Words ' Attributes label acquiring unit determines platform for title keyword to be sent to label, obtains label and determine
Platform feedback, Words ' Attributes label corresponding with title keyword;
Standard topic clause acquiring unit, for obtaining standard topic clause corresponding with Words ' Attributes label, wherein mark
It include the void item for filling title keyword in definite message topic clause;
Direct broadcasting room topic determination unit obtains direct broadcasting room for title keyword and standard topic clause to be combined
Topic.
On the basis of the various embodiments described above, can also include:
Topic sending module, for being sent direct broadcasting room topic after constructing direct broadcasting room topic according to title keyword
Topic audit is carried out to audit platform;
Topic memory module, if the audit for receiving audit platform feedback passes through response, by direct broadcasting room topic
It is stored in topic library;
Wherein, the topic stored in topic library is selected for being supplied to main broadcaster end, so that the target that main broadcaster end is chosen
Topic is shown in corresponding direct broadcasting room.
The generating means of direct broadcasting room topic provided by the embodiment of the present invention can be used for executing any embodiment of that present invention and mention
The generation method of the direct broadcasting room topic of confession, has corresponding functional module, realizes identical beneficial effect.
Embodiment five
Fig. 5 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention five provides.Fig. 5, which is shown, to be suitable for being used to
Realize the block diagram of the exemplary computer device 12 of embodiment of the present invention.The computer equipment 12 that Fig. 5 is shown is only one
Example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Computer equipment 12 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing not
Movably, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").It, can be with although being not shown in Fig. 5
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") is provided, and non-volatile to moving
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform of the invention each
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, can also be enabled a user to one or more equipment interact with the computer equipment 12 communicate, and/or with make
The computer equipment 12 any equipment (such as network interface card, the modulatedemodulate that can be communicated with one or more of the other calculating equipment
Adjust device etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, computer equipment 12 may be used also
To pass through network adapter 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network
Network, such as internet) communication.As shown, network adapter 20 is logical by other modules of bus 18 and computer equipment 12
Letter.It should be understood that although not shown in the drawings, can in conjunction with computer equipment 12 use other hardware and/or software module, including
But it is not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive
And data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the method for building up in direct broadcasting room topic library provided by the embodiment of the present invention.Namely: at least one letter
It ceases in distribution platform, obtains the publishing documents for meeting attention rate condition;Using similarity mode condition, by the publishing documents
Heading message collects in corresponding head stack;Determine title keyword corresponding with the head stack, and according to described
Title keyword constructs direct broadcasting room topic.
Embodiment six
The embodiment of the present invention six additionally provides a kind of storage medium comprising computer executable instructions, and the computer can
It executes instruction when being executed as computer processor for realizing the foundation in direct broadcasting room topic library provided by the embodiment of the present invention
Method.Namely: at least one information publishing platform, obtain the publishing documents for meeting attention rate condition;Using similarity
With condition, the heading message of the publishing documents is collected in corresponding head stack;Determination is corresponding with the head stack
Title keyword construct direct broadcasting room topic and according to the title keyword.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of generation method of direct broadcasting room topic characterized by comprising
In at least one information publishing platform, the publishing documents for meeting attention rate condition are obtained;
Using similarity mode condition, the heading message of the publishing documents is collected in corresponding head stack;
It determines title keyword corresponding with the head stack, and according to the title keyword, constructs direct broadcasting room topic.
2. the method according to claim 1, wherein the attention rate condition includes at least one of following:
Amount of reading is more than or equal to reading number threshold value, comment amount is more than or equal to comment number threshold value and the amount of thumbing up is more than or equal to point
Praise number threshold value.
3. the method according to claim 1, wherein determine corresponding with head stack title keyword,
Include:
Word segmentation processing is carried out at least one heading message for including in the head stack, obtains at least two participles;
Calculate the word frequency of each participle;
Each participle is ranked up according to word frequency, and obtains the mark corresponding with the head stack according to ranking results
Inscribe keyword.
4. according to the method described in claim 3, it is characterized in that, before the word frequency for calculating each participle, further includes:
Everyday words filtering is carried out to each participle according to everyday words dictionary.
5. method according to claim 1-4, which is characterized in that according to the title keyword, construction live streaming
Between topic, comprising:
The title keyword is sent to label and determines platform, the label is obtained and determines platform feedback, with the title
The corresponding Words ' Attributes label of keyword;
Obtain standard topic clause corresponding with the Words ' Attributes label, wherein include being used in the standard topic clause
Fill the void item of title keyword;
The title keyword and the standard topic clause are combined, the direct broadcasting room topic is obtained.
6. method according to claim 1-4, which is characterized in that according to the title keyword, construction is straight
After broadcasting a topic, further includes:
The direct broadcasting room topic is sent to audit platform and carries out topic audit;
If receiving the audit of the audit platform feedback by response, the direct broadcasting room topic is stored in topic library
In;
Wherein, the topic stored in the topic library is selected for being supplied to main broadcaster end, so that the main broadcaster end was chosen
Target topic is shown in corresponding direct broadcasting room.
7. a kind of generating means of direct broadcasting room topic characterized by comprising
Document obtains module, for obtaining the publishing documents for meeting attention rate condition at least one information publishing platform;
Title collects module, and for using similarity mode condition, the heading message of the publishing documents is collected in corresponding
In head stack;
Direct broadcasting room topic constructing module, for determining title keyword corresponding with the head stack, and according to the title
Keyword constructs direct broadcasting room topic.
8. device according to claim 7, which is characterized in that the attention rate condition includes at least one of following:
Amount of reading is more than or equal to reading number threshold value, comment amount is more than or equal to comment number threshold value and the amount of thumbing up is more than or equal to point
Praise number threshold value.
9. a kind of computer equipment, which is characterized in that the computer equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method of any of claims 1-6.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
For executing such as method of any of claims 1-6 when device executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810969224.1A CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810969224.1A CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109271509A true CN109271509A (en) | 2019-01-25 |
CN109271509B CN109271509B (en) | 2021-05-28 |
Family
ID=65154193
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810969224.1A Active CN109271509B (en) | 2018-08-23 | 2018-08-23 | Live broadcast room topic generation method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109271509B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769270A (en) * | 2019-11-08 | 2020-02-07 | 网易(杭州)网络有限公司 | Live broadcast interaction method and device, electronic equipment and storage medium |
CN112199578A (en) * | 2020-08-28 | 2021-01-08 | 贝壳技术有限公司 | Information processing method and apparatus, electronic device, and storage medium |
CN113099253A (en) * | 2021-03-30 | 2021-07-09 | 北京达佳互联信息技术有限公司 | Data generation method and device and electronic equipment |
CN113411618A (en) * | 2020-11-26 | 2021-09-17 | 腾讯科技(深圳)有限公司 | Data processing method and device based on social application and computer storage medium |
CN113691825A (en) * | 2021-08-20 | 2021-11-23 | 上海哔哩哔哩科技有限公司 | Service processing method and device |
CN114125492A (en) * | 2022-01-24 | 2022-03-01 | 阿里巴巴(中国)有限公司 | Live content generation method and device |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103617169A (en) * | 2013-10-23 | 2014-03-05 | 杭州电子科技大学 | Microblog hot topic extracting method based on Hadoop |
CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
CN105488196A (en) * | 2015-12-07 | 2016-04-13 | 中国人民大学 | Automatic hot topic mining system based on internet corpora |
CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
US9646057B1 (en) * | 2013-08-05 | 2017-05-09 | Hrl Laboratories, Llc | System for discovering important elements that drive an online discussion of a topic using network analysis |
CN106874448A (en) * | 2017-02-10 | 2017-06-20 | 中国农业大学 | A kind of method and apparatus that earthquake descriptor is excavated from microblogging |
CN107276985A (en) * | 2017-05-16 | 2017-10-20 | 德基网络科技南京有限公司 | One kind is based on e-commerce platform Online Video management method |
CN107526819A (en) * | 2017-08-29 | 2017-12-29 | 江苏飞搏软件股份有限公司 | A kind of big data the analysis of public opinion method towards short text topic model |
CN107562843A (en) * | 2017-08-25 | 2018-01-09 | 贵州耕云科技有限公司 | A kind of hot news Phrase extraction method based on title high frequency cutting |
CN107894994A (en) * | 2017-10-18 | 2018-04-10 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for detecting much-talked-about topic classification |
CN108009149A (en) * | 2017-11-23 | 2018-05-08 | 东软集团股份有限公司 | A kind of keyword extracting method, extraction element, medium and electronic equipment |
-
2018
- 2018-08-23 CN CN201810969224.1A patent/CN109271509B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9646057B1 (en) * | 2013-08-05 | 2017-05-09 | Hrl Laboratories, Llc | System for discovering important elements that drive an online discussion of a topic using network analysis |
CN103617169A (en) * | 2013-10-23 | 2014-03-05 | 杭州电子科技大学 | Microblog hot topic extracting method based on Hadoop |
CN104915447A (en) * | 2015-06-30 | 2015-09-16 | 北京奇艺世纪科技有限公司 | Method and device for tracing hot topics and confirming keywords |
CN106503030A (en) * | 2015-09-03 | 2017-03-15 | 卡西欧计算机株式会社 | Session control, dialog control method |
CN105488196A (en) * | 2015-12-07 | 2016-04-13 | 中国人民大学 | Automatic hot topic mining system based on internet corpora |
CN106874448A (en) * | 2017-02-10 | 2017-06-20 | 中国农业大学 | A kind of method and apparatus that earthquake descriptor is excavated from microblogging |
CN107276985A (en) * | 2017-05-16 | 2017-10-20 | 德基网络科技南京有限公司 | One kind is based on e-commerce platform Online Video management method |
CN107562843A (en) * | 2017-08-25 | 2018-01-09 | 贵州耕云科技有限公司 | A kind of hot news Phrase extraction method based on title high frequency cutting |
CN107526819A (en) * | 2017-08-29 | 2017-12-29 | 江苏飞搏软件股份有限公司 | A kind of big data the analysis of public opinion method towards short text topic model |
CN107894994A (en) * | 2017-10-18 | 2018-04-10 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for detecting much-talked-about topic classification |
CN108009149A (en) * | 2017-11-23 | 2018-05-08 | 东软集团股份有限公司 | A kind of keyword extracting method, extraction element, medium and electronic equipment |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769270A (en) * | 2019-11-08 | 2020-02-07 | 网易(杭州)网络有限公司 | Live broadcast interaction method and device, electronic equipment and storage medium |
CN112199578A (en) * | 2020-08-28 | 2021-01-08 | 贝壳技术有限公司 | Information processing method and apparatus, electronic device, and storage medium |
CN112199578B (en) * | 2020-08-28 | 2022-04-22 | 贝壳找房(北京)科技有限公司 | Information processing method and apparatus, electronic device, and storage medium |
CN113411618A (en) * | 2020-11-26 | 2021-09-17 | 腾讯科技(深圳)有限公司 | Data processing method and device based on social application and computer storage medium |
CN113411618B (en) * | 2020-11-26 | 2024-03-22 | 腾讯科技(深圳)有限公司 | Data processing method and device based on social application and computer storage medium |
CN113099253A (en) * | 2021-03-30 | 2021-07-09 | 北京达佳互联信息技术有限公司 | Data generation method and device and electronic equipment |
CN113691825A (en) * | 2021-08-20 | 2021-11-23 | 上海哔哩哔哩科技有限公司 | Service processing method and device |
CN114125492A (en) * | 2022-01-24 | 2022-03-01 | 阿里巴巴(中国)有限公司 | Live content generation method and device |
CN114125492B (en) * | 2022-01-24 | 2022-07-15 | 阿里巴巴(中国)有限公司 | Live content generation method and device |
Also Published As
Publication number | Publication date |
---|---|
CN109271509B (en) | 2021-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109271509A (en) | Generation method, device, computer equipment and the storage medium of direct broadcasting room topic | |
US20190394529A1 (en) | Resource recommendation method, device, apparatus and computer readable storage medium | |
CN108228794B (en) | Information management apparatus, information processing apparatus, and automatic replying/commenting method | |
CN106933808A (en) | Article title generation method, device, equipment and medium based on artificial intelligence | |
CN109657054A (en) | Abstraction generating method, device, server and storage medium | |
CN103377262B (en) | The method and apparatus being grouped to user | |
CN102084645B (en) | Related scene addition device and related scene addition method | |
CN107832433A (en) | Information recommendation method, device, server and storage medium based on dialogue interaction | |
CN109348302A (en) | Connect wheat user recommended method, device, server and storage medium in live streaming | |
CN106789543A (en) | The method and apparatus that facial expression image sends are realized in session | |
CN109257656A (en) | A kind of voice connects wheat method, apparatus, server and storage medium | |
CN109151598A (en) | The determination method of direct broadcasting room topic, device, computer equipment and storage medium | |
CN109213954A (en) | Direct broadcasting room topic setting method, device, computer equipment and storage medium | |
CN109286821A (en) | A kind of direct broadcasting room recommended method, device, server and storage medium | |
TW201208353A (en) | System and method for television search assistant | |
WO2014117490A1 (en) | Method and device for recommending video from video library | |
US20130125008A1 (en) | Systems And Methods For Providing Content Streams | |
CN103384883A (en) | Semantic enrichment by exploiting Top-K processing | |
CN107657024A (en) | A kind of search result methods of exhibiting, device, equipment and storage medium | |
CN108108419A (en) | A kind of information recommendation method, device, equipment and medium | |
CN103942247B (en) | The information providing method and device of multimedia resource | |
CN109561212A (en) | A kind of merging method of release information, device, equipment and storage medium | |
CN110276009A (en) | A kind of recommended method of associational word, device, electronic equipment and storage medium | |
CN109815482A (en) | A kind of method, apparatus, equipment and the computer storage medium of news interaction | |
EP2869546B1 (en) | Method and system for providing access to auxiliary information |
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 |