CN108519991A - A kind of method and apparatus of main broadcaster's account recommendation - Google Patents
A kind of method and apparatus of main broadcaster's account recommendation Download PDFInfo
- Publication number
- CN108519991A CN108519991A CN201810168145.0A CN201810168145A CN108519991A CN 108519991 A CN108519991 A CN 108519991A CN 201810168145 A CN201810168145 A CN 201810168145A CN 108519991 A CN108519991 A CN 108519991A
- Authority
- CN
- China
- Prior art keywords
- label
- main broadcaster
- account
- expectation
- message
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/40—Support for services or applications
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
An embodiment of the present invention provides a kind of method and apparatus of main broadcaster's account recommendation, the method includes:The first history message that user issues in direct broadcasting room where acquiring each main broadcaster's account respectively;Based on first history message, the corresponding main broadcaster's label of each main broadcaster's account is generated;Obtain the corresponding expectation label of target user;It determines the matching degree of expectation label main broadcaster's label corresponding with each main broadcaster's account, and recommends the matching degree to meet main broadcaster's account of preset condition to the target user.Through the embodiment of the present invention, the personalized recommendation to main broadcaster's account is realized, the accuracy of recommendation is improved.
Description
Technical field
The present invention relates to Internet technical fields, a kind of method more particularly to main broadcaster's account recommendation and a kind of main broadcaster's account
The device that family is recommended.
Background technology
With the development of Internet technology, the application program of various live streaming classes is more and more, and user can be set using terminal
Then the standby application program for logging in live streaming class can enter interested direct broadcasting room, watch the programme televised live of main broadcaster.
In the prior art, each main broadcaster can be itself setting label, such as " singing ", " making laughs ", to realize to master
The classification broadcast, user can also filter out interested main broadcaster by selecting label, however, main broadcaster is the label of itself setting
With great subjective colo(u)r, the live streaming style of main broadcaster can not be accurately reflected, when user sieves main broadcaster using label
When selecting, meet desired main broadcaster it is difficult to find.
Invention content
In view of the above problems, it is proposed that the embodiment of the present invention is in order to provide overcoming the above problem or solve at least partly
A kind of method and apparatus of main broadcaster's account recommendation of the above problem.
To solve the above-mentioned problems, the embodiment of the invention discloses a kind of method of main broadcaster's account recommendation, the method packets
It includes:
The first history message that user issues in direct broadcasting room where acquiring each main broadcaster's account respectively;
Based on first history message, the corresponding main broadcaster's label of each main broadcaster's account is generated;
Obtain the corresponding expectation label of target user;
Determine the matching degree of expectation label main broadcaster's label corresponding with each main broadcaster's account, and to the target
User recommends the matching degree to meet main broadcaster's account of preset condition.
Optionally, described to be based on first history message, generate the corresponding main broadcaster's label of each main broadcaster's account
Step includes:
From first history message, the first critical message is determined;
First critical message is segmented, one or more first words are obtained;
One or more of first words are matched in the first preset tag database respectively, and will matching
Successful first words is determined as candidate main broadcaster's label;
From candidate main broadcaster's label, the corresponding main broadcaster's label of main broadcaster's account is determined;Wherein, main broadcaster's label
It is more than candidate main broadcaster's label of the first predetermined threshold value for the frequency of occurrences.
Optionally, the corresponding expectation label of the target user generates in the following way:
Acquire the second history message that the target user issues in the process in viewing live streaming;
Based on second history message, the corresponding expectation label of the target user is determined.
Optionally, described the step of being based on second history message, determining the target user corresponding expectation label
Including:
From second history message, the second critical message is determined;
Second critical message is segmented, one or more second words are obtained;
One or more of second words are matched in the second preset tag database respectively, and will matching
Successful second words is determined as candidate expectation label;
From the candidate expectation label, the corresponding expectation label of the target user is determined;Wherein, the expectation label
It is more than the candidate of the second predetermined threshold value for the frequency of occurrences and it is expected label.
Optionally, the step for acquiring the first history message that user issues in the direct broadcasting room of each main broadcaster's account place respectively
Suddenly include:
The liveness of direct broadcasting room where detecting each main broadcaster's account respectively;
For each main broadcaster's account, when the liveness is in the first preset range, acquisition is used in the direct broadcasting room
First history message of family publication.
Optionally, the determination matching degree for it is expected label main broadcaster's label corresponding with each main broadcaster's account,
And the step of recommending the matching degree to meet main broadcaster's account of preset condition to the target user, includes:
Determine the same label in expectation label main broadcaster's label corresponding with each main broadcaster's account;
Accounting of the same label in the expectation label is calculated, the expectation label and each main broadcaster are obtained
The matching degree of the corresponding main broadcaster's label of account;
For each main broadcaster's account, when the matching degree is in the second preset range, recommend institute to the target user
State main broadcaster's account.
The embodiment of the invention also discloses a kind of device of main broadcaster's account recommendation, described device includes:
First history message acquisition module, for acquiring user's publication in direct broadcasting room where each main broadcaster's account respectively
First history message;
It is corresponding to generate each main broadcaster's account for being based on first history message for main broadcaster's tag generation module
Main broadcaster's label;
It is expected that label acquisition module, for obtaining the corresponding expectation label of target user;
Main broadcaster's account recommendation module, for determining expectation label main broadcaster's label corresponding with each main broadcaster's account
Matching degree, and recommend the matching degree to meet main broadcaster's account of preset condition to the target user.
Optionally, main broadcaster's tag generation module includes:
First critical message determination sub-module, for from first history message, determining the first critical message;
First words obtains submodule, for being segmented to first critical message, obtains one or more first
Words;
Candidate main broadcaster's label determination sub-module, for respectively by one or more of first words in the first preset mark
It is matched in label database, and the first words of successful match is determined as candidate main broadcaster's label;
Main broadcaster's label chooses submodule, for from candidate main broadcaster's label, determining the corresponding master of main broadcaster's account
Broadcast label;Wherein, main broadcaster's label is candidate main broadcaster's label that the frequency of occurrences is more than the first predetermined threshold value.
Optionally, further include:
Second history message acquisition module second is gone through for acquiring the target user what viewing live streaming was issued in the process
History message;
It is expected that label determining module determines the corresponding expectation of the target user for being based on second history message
Label.
Optionally, the expectation label determining module includes:
Second critical message determination sub-module, for from second history message, determining the second critical message;
Second words obtains submodule, for being segmented to second critical message, obtains one or more second
Words;
Candidate it is expected label determination sub-module, for respectively by one or more of second words in the second preset mark
It is matched in label database, and the second words of successful match is determined as candidate expectation label;
It is expected that label chooses submodule, for from the candidate expectation label, determining the target user corresponding phase
Hope label;Wherein, described it is expected that label is the candidate expectation label that the frequency of occurrences is more than the second predetermined threshold value.
Optionally, the first history message acquisition module includes:
Liveness detection sub-module, the liveness for direct broadcasting room where detecting each main broadcaster's account respectively;
The first history message acquisition submodule is matched, for being directed to each main broadcaster's account, when the liveness is pre- first
If when in range, acquiring the first history message that user issues in the direct broadcasting room.
Optionally, main broadcaster's account recommendation module includes:
Same label determination sub-module, for determining that expectation label main broadcaster corresponding with each main broadcaster's account marks
Same label in label;
Matching degree obtains submodule, for calculating accounting of the same label in the expectation label, obtains described
It is expected that the matching degree of label main broadcaster's label corresponding with each main broadcaster's account;
Main broadcaster's account recommendation submodule is matched, for being directed to each main broadcaster's account, when the matching degree is in the second default model
When enclosing interior, recommend main broadcaster's account to the target user.
The embodiment of the present invention includes following advantages:
In embodiments of the present invention, it is gone through by first of user's publication in direct broadcasting room where acquiring each main broadcaster's account respectively
History message is based on the first history message, generates the corresponding main broadcaster's label of each main broadcaster's account, and obtain target user's corresponding phase
It hopes label, then determines the matching degree for it is expected label main broadcaster's label corresponding with each main broadcaster's account, and recommend to target user
Matching degree meets main broadcaster's account of preset condition, realizes the personalized recommendation to main broadcaster's account, improves the accuracy of recommendation.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of step flow chart of the method for main broadcaster's account recommendation of the embodiment of the present invention;
Fig. 2 is a kind of structure diagram of the device of main broadcaster's account recommendation of the embodiment of the present invention.
Specific implementation mode
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.Obviously, described embodiments are some of the embodiments of the present invention, without
It is whole embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
The every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Referring to Fig.1, the step flow chart for showing a kind of method of main broadcaster's account recommendation of the embodiment of the present invention, specifically may be used
To include the following steps:
Step 101, the first history message that user issues in direct broadcasting room where acquiring each main broadcaster's account respectively;
As an example, the first history message can be word message, can also other kinds of message, be such as broadcast live
Between in based on broadcast the message of object of giving a present.
During main broadcaster is broadcast live, user can enter the corresponding direct broadcasting room viewing live streaming of main broadcaster's account, be broadcast live in viewing
During, each user can give out information in direct broadcasting room, and server can record the message of publication, this hair
Bright embodiment can obtain the first history message from the message of record.
In a kind of preferred embodiment of the present invention, step 101 may include following sub-step:
Sub-step 11, the liveness of direct broadcasting room where detecting each main broadcaster's account respectively;
Wherein, liveness can be the quantity that gives out information in direct broadcasting room in preset time interval.
For each direct broadcasting room, quantity that user gives out information in different time sections is different, and different quantity
Corresponding different liveness, the embodiment of the present invention can by calculating the quantity to give out information in direct broadcasting room in time interval,
To detect direct broadcasting room in liveness in different time periods.
Sub-step 12, for each main broadcaster's account, when the liveness is in the first preset range, acquisition is described straight
First history message of multiple user's publications between broadcasting.
When detecting direct broadcasting room when the liveness of some period is in the first preset range, then direct broadcasting room is in the period
In preferable states, the embodiment of the present invention can acquire within the period, and what multiple users issued in direct broadcasting room first goes through
History message.
Assuming that time interval be 10s, in 10s, if the quantity to give out information in direct broadcasting room between 20-50 items,
The liveness of direct broadcasting room is normal, carries out message collection, and if it is less than 20, then direct broadcasting room popularity is insufficient, without message collection,
If being more than 50, message rolls too fast, it is understood that there may be a large amount of invalid speeches, such as " 666 ", without message collection.
Step 102, it is based on first history message, generates the corresponding main broadcaster's label of each main broadcaster's account;
After obtaining the first history message, the first history message of the embodiment of the present invention pair parses, and such as carries out participle behaviour
Make, and then can therefrom extract multiple keywords, then can determine main broadcaster from preset multiple labels according to keyword
The corresponding expectation label of account.
In a kind of preferred embodiment of the present invention, step 102 may include following sub-step:
Sub-step 21 determines the first critical message from first history message;
In the first history message, it is understood that there may be invalid message, such as " 666 ", the embodiment of the present invention can pre-set nothing
The feature phrase of effect message can then remove the message when detecting feature phrase in the first history message, with to the
One history message is filtered, and determines the first critical message.
Sub-step 22 segments first critical message, obtains one or more first words;
After determining the first critical message, the embodiment of the present invention can carry out word segmentation processing to the first critical message, obtain
One or more first words.
Sub-step 23, respectively carries out one or more of first words in the first preset tag database
Match, and the first words of successful match is determined as candidate main broadcaster's label;
In embodiments of the present invention, the first tag database is pre-set, can be stored in the first tag database multiple
Main broadcaster's label can respectively carry out each first keyword after determining the first keyword in the first tag database
Match, obtain the first words of one or more of successful match, as the corresponding candidate main broadcaster's label of main broadcaster's account.
For example, reverse matching the first words of segmentation methods pair, which may be used, carries out word segmentation processing, it is long to set maximum segmenting word
For n, to the cutting from right to left of the first words, m character of each cutting, by m character being syncopated as in the first tag database
In matched, if matching, as candidate main broadcaster's label, if mismatching, cutting can be further carried out, until going out
Existing word.
In a kind of preferable example, it can be identified in conjunction with the first words of context of co-text pair, and then will be after identification
First words is matched in the first tag database, promotes matched accuracy.
Sub-step 24 determines the corresponding main broadcaster's label of main broadcaster's account from candidate main broadcaster's label;
Wherein, main broadcaster's label can be candidate main broadcaster's label that the frequency of occurrences is more than the first predetermined threshold value.
As an example, the first predetermined threshold value is the threshold value that staff is rule of thumb arranged, and is more than the first default threshold
Candidate main broadcaster's label of value can preferably characterize the live streaming style of main broadcaster.
After determining candidate main broadcaster's label, the embodiment of the present invention can calculate each candidate main broadcaster's label and disappear in the first history
The frequency of occurrences in breath, and then candidate main broadcaster's label that the frequency of occurrences is more than the first predetermined threshold value is chosen, as main broadcaster's account pair
The main broadcaster's label answered.
In embodiments of the present invention, by obtaining the first history message issued in direct broadcasting room, disappeared based on the first history
Breath generates the corresponding main broadcaster's label of main broadcaster's account, realizes and is automatically generated to main broadcaster's label, improves the standard classified to main broadcaster
True property.
Step 103, the corresponding expectation label of target user is obtained;
For each user, the embodiment of the present invention can the user in the message issued in the process of viewing live streaming, Jin Eryi
The corresponding expectation label of the user is generated according to the message, user can also select from preset multiple labels, to obtain
Label must it is expected, to characterize preference of the user to main broadcaster.
In a kind of preferred embodiment of the present invention, the corresponding expectation label of target user may be used under type such as and generate:
Acquire the second history message that the target user issues in the process in viewing live streaming;Disappeared based on second history
Breath, determines the corresponding expectation label of the target user.
As an example, the second history message can be word message, can also other kinds of message, be such as broadcast live
Between in based on broadcast the message of object of giving a present.
During watching live streaming, user can carry out information input in the input frame at live streaming interface, and such as input " be sung
Listen ", " transmission " button is can then click on, the message of input is sent to direct broadcasting room.
For each user, server can record the message that user issues in the process in viewing live streaming, and the present invention is implemented
Example the second history message of target user within a preset period of time can be obtained from server, by the second history message into
Row parsing, obtains the corresponding expectation label of target user.
Specifically, described be based on second history message, the step of determining the target user corresponding expectation label
It may include following sub-step:
Sub-step 31 determines the second critical message from second history message;
In the second history message, it is understood that there may be invalid message, such as " 666 ", the embodiment of the present invention can pre-set nothing
The feature phrase of effect message can then remove the message when detecting feature phrase in the second history message, with to the
Two history messages are filtered, and determine the second critical message.
Sub-step 32 segments second critical message, obtains one or more second words;
After determining the second critical message, the embodiment of the present invention can carry out word segmentation processing to the second critical message, obtain
One or more second words.
Sub-step 33, respectively carries out one or more of second words in the second preset tag database
Match, and the second words of successful match is determined as candidate expectation label;
In embodiments of the present invention, the second tag database is pre-set, can be stored in the second tag database multiple
It is expected that label, after determining the second keyword, each second keyword can be carried out in the second tag database respectively
Match, obtain the second words of one or more of successful match, as the corresponding candidate expectation label of target user.
In a kind of preferable example, it can be identified in conjunction with the second words of context of co-text pair, and then will be after identification
Second words is matched in the second tag database, promotes matched accuracy.
Sub-step 34 determines the corresponding expectation label of the target user from the candidate expectation label;
Wherein, it is expected that label can be the frequency of occurrences it is expected label more than the candidate of the second predetermined threshold value.
As an example, the second predetermined threshold value is the threshold value that staff is rule of thumb arranged, and is more than the second default threshold
The candidate of value it is expected that label can preferably characterize user's expectation.
After determining candidate expectation label, the embodiment of the present invention can calculate each candidate expectation label and disappear in the second history
The frequency of occurrences in breath, and then the candidate expectation label that the frequency of occurrences is more than the second predetermined threshold value is chosen, as target user couple
The expectation label answered.
Step 104, the matching degree of expectation label main broadcaster's label corresponding with each main broadcaster's account is determined, and to
The target user recommends the matching degree to meet main broadcaster's account of preset condition.
Label it is expected with after main broadcaster's label determining, the embodiment of the present invention can calculate of desired label and main broadcaster's label
With degree, and then when detecting matching degree and whether meeting preset condition, if meeting preset condition, the master can be recommended to target user
Broadcast account.
For example, preset condition can be " being more than 80% ", then when desired label main broadcaster's mark corresponding with some main broadcaster's account
The matching degree of label is more than 80%, then can recommend main broadcaster's label to target user.
In a kind of preferred embodiment of the present invention, step 104 may include following sub-step:
Sub-step 41 determines the identical mark in expectation label main broadcaster's label corresponding with each main broadcaster's account
Label;
Due to it is expected that label and main broadcaster's label can have multiple labels, the embodiment of the present invention, which determines, it is expected label and master
Broadcast the same label in label.
Sub-step 42 calculates accounting of the same label in the expectation label, obtains the expectation label and institute
State the matching degree of the corresponding main broadcaster's label of each main broadcaster's account;
After determining same label, the first quantity of same label can be calculated, and can determine label in desired label
The second quantity, then can calculate the ratio of the first quantity and the second quantity, obtain it is expected label and main broadcaster's label matching
Degree.
Sub-step 43, when the matching degree is in the second preset range, is used for each main broadcaster's account to the target
Recommend main broadcaster's account in family.
After obtaining matching degree, the embodiment of the present invention can detect matching degree whether in the second preset range, and such as second
Preset range is 80%-100%, if so, recommending main broadcaster's account to target user.
In a kind of preferable example, the corresponding expectation label of target user master corresponding with multiple main broadcaster's accounts can be calculated
The matching degree of label is broadcast, then multiple main broadcaster's accounts are ranked up according to matching degree, main broadcaster's account after sequence is pushed to user
Family.
In embodiments of the present invention, it is gone through by first of user's publication in direct broadcasting room where acquiring each main broadcaster's account respectively
History message is based on the first history message, generates the corresponding main broadcaster's label of each main broadcaster's account, and obtain target user's corresponding phase
It hopes label, then determines the matching degree for it is expected label main broadcaster's label corresponding with each main broadcaster's account, and recommend to target user
Matching degree meets main broadcaster's account of preset condition, realizes the personalized recommendation to main broadcaster's account, improves the accuracy of recommendation.
It should be noted that for embodiment of the method, for simple description, therefore it is all expressed as a series of action group
It closes, but those skilled in the art should understand that, the embodiment of the present invention is not limited by the described action sequence, because according to
According to the embodiment of the present invention, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, and the involved action not necessarily present invention is implemented
Necessary to example.
With reference to Fig. 2, a kind of structure diagram of the device of main broadcaster's account recommendation of the embodiment of the present invention is shown, it specifically can be with
Including following module:
First history message acquisition module 201 is issued for user in direct broadcasting room where acquiring each main broadcaster's account respectively
The first history message;
Main broadcaster's tag generation module 202 generates each main broadcaster's account and corresponds to for being based on first history message
Main broadcaster's label;
It is expected that label acquisition module 203, for obtaining the corresponding expectation label of target user;
Main broadcaster's account recommendation module 204, for determining expectation label main broadcaster corresponding with each main broadcaster's account
The matching degree of label, and recommend the matching degree to meet main broadcaster's account of preset condition to the target user.
In a kind of preferred embodiment of the present invention, main broadcaster's tag generation module 202 includes:
First critical message determination sub-module, for from first history message, determining the first critical message;
First words obtains submodule, for being segmented to first critical message, obtains one or more first
Words;
Candidate main broadcaster's label determination sub-module, for respectively by one or more of first words in the first preset mark
It is matched in label database, and the first words of successful match is determined as candidate main broadcaster's label;
Main broadcaster's label chooses submodule, for from candidate main broadcaster's label, determining the corresponding master of main broadcaster's account
Broadcast label;Wherein, main broadcaster's label is candidate main broadcaster's label that the frequency of occurrences is more than the first predetermined threshold value.
In a kind of preferred embodiment of the present invention, further include:
Second history message acquisition module second is gone through for acquiring the target user what viewing live streaming was issued in the process
History message;
It is expected that label determining module determines the corresponding expectation of the target user for being based on second history message
Label.
In a kind of preferred embodiment of the present invention, the expectation label determining module includes:
Second critical message determination sub-module, for from second history message, determining the second critical message;
Second words obtains submodule, for being segmented to second critical message, obtains one or more second
Words;
Candidate it is expected label determination sub-module, for respectively by one or more of second words in the second preset mark
It is matched in label database, and the second words of successful match is determined as candidate expectation label;
It is expected that label chooses submodule, for from the candidate expectation label, determining the target user corresponding phase
Hope label;Wherein, described it is expected that label is the candidate expectation label that the frequency of occurrences is more than the second predetermined threshold value.
In a kind of preferred embodiment of the present invention, the first history message acquisition module 201 includes:
Liveness detection sub-module, the liveness for direct broadcasting room where detecting each main broadcaster's account respectively;
The first history message acquisition submodule is matched, for being directed to each main broadcaster's account, when the liveness is pre- first
If when in range, acquiring the first history message that user issues in the direct broadcasting room.
In a kind of preferred embodiment of the present invention, main broadcaster's account recommendation module 204 includes:
Same label determination sub-module, for determining that expectation label main broadcaster corresponding with each main broadcaster's account marks
Same label in label;
Matching degree obtains submodule, for calculating accounting of the same label in the expectation label, obtains described
It is expected that the matching degree of label main broadcaster's label corresponding with each main broadcaster's account;
Main broadcaster's account recommendation submodule is matched, for being directed to each main broadcaster's account, when the matching degree is in the second default model
When enclosing interior, recommend main broadcaster's account to the target user.
In embodiments of the present invention, by the way that the first history message acquisition module is arranged, for being acquired respectively in each main broadcaster
The first history message that user issues in direct broadcasting room where account, and main broadcaster's tag generation module is set, it is gone through for being based on first
History message generates the corresponding main broadcaster's label of each main broadcaster's account, and label acquisition module it is expected in then setting, is used for obtaining target
The corresponding expectation label in family, and main broadcaster's account recommendation module is set, it is expected that label is corresponding with each main broadcaster's account for determining
The matching degree of main broadcaster's label, and recommend matching degree to meet main broadcaster's account of preset condition to target user, it realizes to main broadcaster's account
The personalized recommendation at family improves the accuracy of recommendation.
The embodiment of the invention also discloses a kind of mobile terminal, including processor, memory and it is stored in the memory
Computer program that is upper and can running on the processor, is realized as above when the computer program is executed by the processor
A kind of the step of method of main broadcaster's account recommendation.
The embodiment of the invention also discloses a kind of computer readable storage mediums, which is characterized in that described computer-readable
Computer program is stored on storage medium, and a kind of main broadcaster's account as described above is realized when the computer program is executed by processor
The step of method that family is recommended.
For device embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of description
Place illustrates referring to the part of embodiment of the method.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be with reference to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided
Computer program instructions are set to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction generates for realizing in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of specified function.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal equipments
In computer-readable memory operate in a specific manner so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or in one box of block diagram or multiple boxes specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device including the element.
It above to a kind of method and apparatus of main broadcaster's account recommendation provided by the present invention, is described in detail, herein
In apply specific case principle and implementation of the present invention are described, the explanation of above example is only intended to sides
Assistant solves the method and its core concept of the present invention;Meanwhile for those of ordinary skill in the art, think of according to the present invention
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
The limitation of the present invention.
Claims (12)
1. a kind of method of main broadcaster's account recommendation, which is characterized in that the method includes:
The first history message that user issues in direct broadcasting room where acquiring each main broadcaster's account respectively;
Based on first history message, the corresponding main broadcaster's label of each main broadcaster's account is generated;
Obtain the corresponding expectation label of target user;
Determine the matching degree of expectation label main broadcaster's label corresponding with each main broadcaster's account, and to the target user
The matching degree is recommended to meet main broadcaster's account of preset condition.
2. according to the method described in claim 1, it is characterized in that, described be based on first history message, generation is described every
The step of a main broadcaster's account corresponding main broadcaster's label includes:
From first history message, the first critical message is determined;
First critical message is segmented, one or more first words are obtained;
One or more of first words are matched in the first preset tag database respectively, and by successful match
The first words be determined as candidate main broadcaster's label;
From candidate main broadcaster's label, the corresponding main broadcaster's label of main broadcaster's account is determined;Wherein, main broadcaster's label is
Existing frequency is more than candidate main broadcaster's label of the first predetermined threshold value.
3. method according to claim 1 or 2, which is characterized in that the corresponding expectation label of the target user is using such as
Under type generates:
Acquire the second history message that the target user issues in the process in viewing live streaming;
Based on second history message, the corresponding expectation label of the target user is determined.
4. according to the method described in claim 3, it is characterized in that, it is described be based on second history message, determine the mesh
The step of mark user's corresponding expectation label includes:
From second history message, the second critical message is determined;
Second critical message is segmented, one or more second words are obtained;
One or more of second words are matched in the second preset tag database respectively, and by successful match
The second words be determined as candidate it is expected label;
From the candidate expectation label, the corresponding expectation label of the target user is determined;Wherein, the expectation label is
Existing frequency is more than the candidate of the second predetermined threshold value and it is expected label.
5. according to the method described in claim 1, it is characterized in that, described acquire respectively in the direct broadcasting room of each main broadcaster's account place
User publication the first history message the step of include:
The liveness of direct broadcasting room where detecting each main broadcaster's account respectively;
For each main broadcaster's account, when the liveness is in the first preset range, acquisition user in the direct broadcasting room sends out
First history message of cloth.
6. according to the method described in claim 1, it is characterized in that, the determination expectation label and each main broadcaster's account
The matching degree of the corresponding main broadcaster's label in family, and recommend the matching degree to meet main broadcaster's account of preset condition to the target user
The step of include:
Determine the same label in expectation label main broadcaster's label corresponding with each main broadcaster's account;
Accounting of the same label in the expectation label is calculated, the expectation label and each main broadcaster's account are obtained
The matching degree of corresponding main broadcaster's label;
For each main broadcaster's account, when the matching degree is in the second preset range, recommend the master to the target user
Broadcast account.
7. a kind of device of main broadcaster's account recommendation, which is characterized in that described device includes:
First history message acquisition module, first for acquiring user's publication in direct broadcasting room where each main broadcaster's account respectively
History message;
Main broadcaster's tag generation module generates the corresponding main broadcaster of each main broadcaster's account for being based on first history message
Label;
It is expected that label acquisition module, for obtaining the corresponding expectation label of target user;
Main broadcaster's account recommendation module, for determining expectation label main broadcaster's label corresponding with each main broadcaster's account
The matching degree is recommended to meet main broadcaster's account of preset condition with degree, and to the target user.
8. device according to claim 7, which is characterized in that main broadcaster's tag generation module includes:
First critical message determination sub-module, for from first history message, determining the first critical message;
First words obtains submodule, for being segmented to first critical message, obtains one or more first words;
Candidate main broadcaster's label determination sub-module, for respectively by one or more of first words in the first preset number of tags
According to being matched in library, and the first words of successful match is determined as candidate main broadcaster's label;
Main broadcaster's label chooses submodule, for from candidate main broadcaster's label, determining the corresponding main broadcaster's mark of main broadcaster's account
Label;Wherein, main broadcaster's label is candidate main broadcaster's label that the frequency of occurrences is more than the first predetermined threshold value.
9. device according to claim 7 or 8, which is characterized in that further include:
Second history message acquisition module disappears for acquiring the second history that the target user issues in the process in viewing live streaming
Breath;
It is expected that label determining module determines the corresponding expectation label of the target user for being based on second history message.
10. device according to claim 9, which is characterized in that the expectation label determining module includes:
Second critical message determination sub-module, for from second history message, determining the second critical message;
Second words obtains submodule, for being segmented to second critical message, obtains one or more second words;
Candidate it is expected label determination sub-module, for respectively by one or more of second words in the second preset number of tags
According to being matched in library, and the second words of successful match is determined as candidate it is expected label;
It is expected that label chooses submodule, for from the candidate expectation label, determining the corresponding expectation mark of the target user
Label;Wherein, described it is expected that label is the candidate expectation label that the frequency of occurrences is more than the second predetermined threshold value.
11. device according to claim 7, which is characterized in that the first history message acquisition module includes:
Liveness detection sub-module, the liveness for direct broadcasting room where detecting each main broadcaster's account respectively;
The first history message acquisition submodule is matched, for being directed to each main broadcaster's account, when the liveness is in the first default model
When enclosing interior, the first history message that user issues in the direct broadcasting room is acquired.
12. device according to claim 7, which is characterized in that main broadcaster's account recommendation module includes:
Same label determination sub-module, for determining in expectation label main broadcaster's label corresponding with each main broadcaster's account
Same label;
Matching degree obtains submodule, for calculating accounting of the same label in the expectation label, obtains the expectation
The matching degree of label main broadcaster's label corresponding with each main broadcaster's account;
Main broadcaster's account recommendation submodule is matched, for being directed to each main broadcaster's account, when the matching degree is in the second preset range
When, recommend main broadcaster's account to the target user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810168145.0A CN108519991A (en) | 2018-02-28 | 2018-02-28 | A kind of method and apparatus of main broadcaster's account recommendation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810168145.0A CN108519991A (en) | 2018-02-28 | 2018-02-28 | A kind of method and apparatus of main broadcaster's account recommendation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108519991A true CN108519991A (en) | 2018-09-11 |
Family
ID=63433313
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810168145.0A Pending CN108519991A (en) | 2018-02-28 | 2018-02-28 | A kind of method and apparatus of main broadcaster's account recommendation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108519991A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110737859A (en) * | 2019-09-09 | 2020-01-31 | 苏宁云计算有限公司 | UP main matching method and device |
CN111104605A (en) * | 2019-12-02 | 2020-05-05 | 北京达佳互联信息技术有限公司 | Content recommendation method and device, electronic equipment and storage medium |
CN111263179A (en) * | 2020-02-20 | 2020-06-09 | 广州虎牙科技有限公司 | Live broadcast room drainage method, device, system, server and storage medium |
CN111526253A (en) * | 2020-03-09 | 2020-08-11 | 深圳追一科技有限公司 | Call control method, device, computer equipment and storage medium |
CN112423000A (en) * | 2020-10-27 | 2021-02-26 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and medium |
CN112672188A (en) * | 2019-10-15 | 2021-04-16 | 阿里巴巴集团控股有限公司 | Anchor recommendation method, device and storage medium |
CN113032542A (en) * | 2021-04-12 | 2021-06-25 | 腾讯科技(深圳)有限公司 | Live data processing method, device and equipment and readable storage medium |
CN113315988A (en) * | 2021-05-28 | 2021-08-27 | 北京中指讯博数据信息技术有限公司 | Live video recommendation method and device |
CN113382272A (en) * | 2021-05-31 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Data playing method and device, electronic equipment and storage medium |
CN113763004A (en) * | 2020-09-07 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information matching method and device |
CN113923529A (en) * | 2021-10-08 | 2022-01-11 | 北京百度网讯科技有限公司 | Live broadcast wheat connecting method, device, equipment and storage medium |
CN115336281A (en) * | 2020-09-29 | 2022-11-11 | 多玩国株式会社 | Moving picture distribution device, moving picture distribution method, and recording medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110010673A1 (en) * | 2009-07-07 | 2011-01-13 | Kabushiki Kaisha Toshiba | Mobile communication terminal and method for recommending content item |
CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
CN106560811A (en) * | 2016-09-23 | 2017-04-12 | 武汉斗鱼网络科技有限公司 | Direct broadcasting room recommending method and system based on broadcaster style |
CN107483982A (en) * | 2017-07-11 | 2017-12-15 | 北京潘达互娱科技有限公司 | A kind of main broadcaster recommends method and apparatus |
-
2018
- 2018-02-28 CN CN201810168145.0A patent/CN108519991A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110010673A1 (en) * | 2009-07-07 | 2011-01-13 | Kabushiki Kaisha Toshiba | Mobile communication terminal and method for recommending content item |
CN105824923A (en) * | 2016-03-17 | 2016-08-03 | 海信集团有限公司 | Movie and video resource recommendation method and device |
CN106560811A (en) * | 2016-09-23 | 2017-04-12 | 武汉斗鱼网络科技有限公司 | Direct broadcasting room recommending method and system based on broadcaster style |
CN107483982A (en) * | 2017-07-11 | 2017-12-15 | 北京潘达互娱科技有限公司 | A kind of main broadcaster recommends method and apparatus |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110737859A (en) * | 2019-09-09 | 2020-01-31 | 苏宁云计算有限公司 | UP main matching method and device |
CN110737859B (en) * | 2019-09-09 | 2022-09-27 | 苏宁云计算有限公司 | UP master matching method and device |
CN112672188A (en) * | 2019-10-15 | 2021-04-16 | 阿里巴巴集团控股有限公司 | Anchor recommendation method, device and storage medium |
CN111104605A (en) * | 2019-12-02 | 2020-05-05 | 北京达佳互联信息技术有限公司 | Content recommendation method and device, electronic equipment and storage medium |
CN111263179A (en) * | 2020-02-20 | 2020-06-09 | 广州虎牙科技有限公司 | Live broadcast room drainage method, device, system, server and storage medium |
CN111526253A (en) * | 2020-03-09 | 2020-08-11 | 深圳追一科技有限公司 | Call control method, device, computer equipment and storage medium |
CN113763004A (en) * | 2020-09-07 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information matching method and device |
CN115336281A (en) * | 2020-09-29 | 2022-11-11 | 多玩国株式会社 | Moving picture distribution device, moving picture distribution method, and recording medium |
CN112423000A (en) * | 2020-10-27 | 2021-02-26 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and medium |
CN113032542A (en) * | 2021-04-12 | 2021-06-25 | 腾讯科技(深圳)有限公司 | Live data processing method, device and equipment and readable storage medium |
CN113032542B (en) * | 2021-04-12 | 2024-04-09 | 腾讯科技(深圳)有限公司 | Live broadcast data processing method, device, equipment and readable storage medium |
CN113315988A (en) * | 2021-05-28 | 2021-08-27 | 北京中指讯博数据信息技术有限公司 | Live video recommendation method and device |
CN113315988B (en) * | 2021-05-28 | 2023-04-07 | 北京中指讯博数据信息技术有限公司 | Live video recommendation method and device |
CN113382272A (en) * | 2021-05-31 | 2021-09-10 | 北京达佳互联信息技术有限公司 | Data playing method and device, electronic equipment and storage medium |
CN113382272B (en) * | 2021-05-31 | 2022-08-26 | 北京达佳互联信息技术有限公司 | Data playing method and device, electronic equipment and storage medium |
US11819761B2 (en) | 2021-05-31 | 2023-11-21 | Beijing Dajia Internet Information Technology Co., Ltd. | Data play method and terminal |
CN113923529A (en) * | 2021-10-08 | 2022-01-11 | 北京百度网讯科技有限公司 | Live broadcast wheat connecting method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108519991A (en) | A kind of method and apparatus of main broadcaster's account recommendation | |
CN105095508B (en) | A kind of multimedia content recommended method and multimedia content recommendation apparatus | |
CN105915956A (en) | Video content recommendation method, device, server and system | |
CN108471544B (en) | Method and device for constructing video user portrait | |
WO2015176652A1 (en) | Network service recommendation method and apparatus | |
CN110287375B (en) | Method and device for determining video tag and server | |
CN112333547A (en) | Method and device for recommending favorite preference of short video user at television end and smart television | |
CN110837581A (en) | Method, device and storage medium for video public opinion analysis | |
US11184682B2 (en) | Obtaining viewer demographics through advertisement selections | |
CN104572969A (en) | Cross-application related resource information acquisition method and device | |
CN113407773A (en) | Short video intelligent recommendation method and system, electronic device and storage medium | |
CN112287165A (en) | File processing method and device | |
CN113989476A (en) | Object identification method and electronic equipment | |
CN104731938A (en) | Video searching method and device | |
CN114461920A (en) | Data processing method, device, medium and equipment for list information recommendation | |
CN104077713B (en) | Access need assessment, advertisement sending method and the system of the user of website | |
CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
CN113297416A (en) | Video data storage method and device, electronic equipment and readable storage medium | |
CN111782850B (en) | Object searching method and device based on hand drawing | |
CN110442789A (en) | Method, apparatus and electronic equipment are determined based on the association results of user behavior | |
CN115190357A (en) | Video abstract generation method and device | |
CN113709507B (en) | Video recommendation method and device, electronic equipment and storage medium | |
CN111859221B (en) | Project recommendation method and device | |
CN107666518B (en) | Information pushing method and device, terminal equipment and computer readable storage medium | |
CN113973234A (en) | Video recommendation method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180911 |