CN108076354A - Direct broadcasting room recommends method and apparatus - Google Patents
Direct broadcasting room recommends method and apparatus Download PDFInfo
- Publication number
- CN108076354A CN108076354A CN201711387616.9A CN201711387616A CN108076354A CN 108076354 A CN108076354 A CN 108076354A CN 201711387616 A CN201711387616 A CN 201711387616A CN 108076354 A CN108076354 A CN 108076354A
- Authority
- CN
- China
- Prior art keywords
- room
- direct broadcasting
- broadcasting room
- user
- sectional drawing
- 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
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Abstract
The embodiment of the present application provides a kind of direct broadcasting room and recommends method and apparatus, wherein, method includes：Obtain the corresponding live scene sectional drawing of direct broadcasting room；The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；The direct broadcasting room is recommended and the matched user of the room property.Technical solution provided by the embodiments of the present application can accurately classify to direct broadcasting room, improve the precision that live streaming platform recommends direct broadcasting room to user.
Description
Technical field
This application involves Internet technical fields more particularly to a kind of direct broadcasting room to recommend method and apparatus.
Background technology
The development of internet technique at any time, network direct broadcasting gradually have new expansion.User can by network direct broadcasting,
The online various types of programs watched competitive sports, amusement variety, news and main broadcaster and provided.
In general, when user is using live streaming platform viewing live streaming, live streaming platform can recommend it according to the hobby of user for user
The direct broadcasting room that may be liked.In the prior art, can be that the direct broadcasting room sets room property, the room when main broadcaster opens direct broadcasting room
Between the attribute characterization type of direct broadcasting room and other characteristic of division.Platform is broadcast live when recommending direct broadcasting room to user, according to room
Matching degree between attribute and the hobby of user is recommended.
However, in some cases, the content that direct broadcasting room is being broadcast live exists with the room property that main broadcaster is set to be mismatched
The phenomenon that, and then cause the precision that platform to user's recommendation direct broadcasting room is broadcast live relatively low.
The content of the invention
The many aspects of the embodiment of the present application provide a kind of direct broadcasting room and recommend method and apparatus, to accurately to direct broadcasting room into
Row classification improves the precision that live streaming platform recommends direct broadcasting room to user.
The embodiment of the present application provides a kind of direct broadcasting room and recommends method, including：
Obtain the corresponding live scene sectional drawing of direct broadcasting room；
The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；
The direct broadcasting room is recommended and the matched user of the room property.
Still optionally further, the corresponding live scene sectional drawing of direct broadcasting room is obtained, including：The live streaming is captured to set the cycle
Between room surface plot；Using the room surface plot as the live scene sectional drawing of the direct broadcasting room.
Still optionally further, the live scene sectional drawing is identified, to determine the room property of the direct broadcasting room, bag
It includes：Extract the key feature that the live scene sectional drawing includes；According to direct broadcasting room feature recognition model trained in advance, to described
Key feature is identified；According to the identification as a result, the corresponding room features label of the direct broadcasting room is determined, as described
The room property of direct broadcasting room.
Still optionally further, according to the identification as a result, determine the corresponding room features label of the direct broadcasting room, as
The room property of the direct broadcasting room, including：According to the recognition result, the broadcasting content of the direct broadcasting room is determined；According to described
The broadcasting content of direct broadcasting room, inquiry broadcasting content and the correspondence of room features label, to determine that the direct broadcasting room is corresponding
Room features label；By the corresponding room features label of the direct broadcasting room, the room property as the direct broadcasting room.
Still optionally further, by the direct broadcasting room recommend with the matched user of the room property, including：Described in calculating
Similarity between the corresponding room features label of direct broadcasting room feature tag corresponding with the interest of user；When the similarity is big
When default similarity threshold, the direct broadcasting room is recommended into the user.
Still optionally further, the corresponding feature tag of the interest of the user, including：The user sets according to own interests
The feature tag put；And/or it is obtained according to the history of user viewing recording gauge matched with the interest of the user
Feature tag.
The embodiment of the present application also provides a kind of direct broadcasting room recommendation apparatus, including：Memory and processor；
Wherein, the memory is for one or more computer instruction of storage；
The processor is used for：Perform one or more computer instruction for：
Obtain the corresponding live scene sectional drawing of direct broadcasting room；
The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；
The direct broadcasting room is recommended and the matched user of the room property.
Still optionally further, the processor is specifically used for：To set the room surface plot that the cycle captures the direct broadcasting room；
Using the room surface plot as the live scene sectional drawing of the direct broadcasting room.
Still optionally further, the processor is specifically used for：Extract the key feature that the live scene sectional drawing includes；Root
According to direct broadcasting room feature recognition model trained in advance, the key feature is identified；According to the identification as a result, determining
The corresponding room features label of the direct broadcasting room, the room property as the direct broadcasting room.
Still optionally further, the processor is specifically used for：The corresponding room features label of the direct broadcasting room is calculated with using
Similarity between the corresponding feature tag of interest at family；When the similarity is more than default similarity threshold, by described in
Direct broadcasting room recommends the user.
In the embodiment of the present application, before direct broadcasting room is recommended to user, the corresponding live scene of direct broadcasting room is obtained in advance
Sectional drawing, and the live scene sectional drawing is identified.Based on recognition result, the room property of direct broadcasting room is determined, and by direct broadcasting room
It recommends and the matched user of its room property.The embodiment of the present application, can be accurately to direct broadcasting room by above-mentioned this mode
Classify, and then improve the precision that live streaming platform recommends direct broadcasting room to user.
Description of the drawings
Attached drawing described herein is used for providing further understanding of the present application, forms the part of the application, this Shen
Schematic description and description please does not form the improper restriction to the application for explaining the application.In the accompanying drawings：
Fig. 1 is the structure diagram for the data handling system that one embodiment of the application provides；
Fig. 2 is the structure diagram for the data handling system that another embodiment of the application provides；
Fig. 3 is the structure diagram for the direct broadcasting room recommendation apparatus that the another embodiment of the application provides.
Specific embodiment
To make the purpose, technical scheme and advantage of the application clearer, below in conjunction with the application specific embodiment and
Technical scheme is clearly and completely described in corresponding attached drawing.Obviously, described embodiment is only the application one
Section Example, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not doing
Go out all other embodiments obtained under the premise of creative work, shall fall in the protection scope of this application.
Fig. 1 is the method flow diagram that the direct broadcasting room that one embodiment of the application provides recommends method.As shown in Figure 1, this method
Including：
Step 101 obtains the corresponding live scene sectional drawing of direct broadcasting room.
The live scene sectional drawing is identified in step 102, to determine the room property of the direct broadcasting room.
Step 103 recommends the direct broadcasting room and the matched user of the room property.
In a step 101, direct broadcasting room refers to the virtual place that live streaming platform provides, and in the direct broadcasting room, main broadcaster can be with
Show live content, user can enter direct broadcasting room viewing live content simultaneously can carry out interaction with main broadcaster.
Live scene sectional drawing, when referring to that direct broadcasting room is during live streaming, the live content shown is corresponding visual
Image.
In a step 102, the room property of direct broadcasting room can be made of multiple keyword groups, and the plurality of keyword can characterize directly
Characteristic of division between broadcasting.For example, the room property of a direct broadcasting room is：Game, sports, strategy and risk etc., another direct broadcasting room
Room property be variety, reality TV show, parent-offspring's program etc..
After the corresponding live scene sectional drawing of direct broadcasting room is obtained, can scene Recognition be carried out according to the live scene sectional drawing,
And then the room property of direct broadcasting room is determined according to recognition result.For example, the recognition result bag of the live scene sectional drawing of a direct broadcasting room
Include substantial amounts of simulated weapons and simulation personage, it may be determined that the room property of the direct broadcasting room includes：Game and strategy.
In step 103, with the matched user of the room property, referring to may be to the interested use of the direct broadcasting room
Family.Such as a certain user may like the variety show of reality TV show etc, then room property is variety, reality TV show and parent-offspring save
Purpose direct broadcasting room can be matched with the user.For another example another user may like football match, then room property is physical culture, foot
The direct broadcasting room of ball and world cup can be matched with the user.
In the present embodiment, before direct broadcasting room is recommended to user, the corresponding live scene sectional drawing of direct broadcasting room is obtained in advance,
And the live scene sectional drawing is identified.Based on recognition result, the room property of direct broadcasting room is determined, and direct broadcasting room is recommended
With the matched user of its room property.The embodiment of the present application can accurately divide direct broadcasting room by above-mentioned this mode
Class, and then improve the precision that live streaming platform recommends direct broadcasting room to user.
Above-described embodiment, which describes, is identified the live scene sectional drawing of direct broadcasting room, and this is broadcast live according to recognition result
Between recommend the method for corresponding user, following embodiment will be further elaborated the above method with reference to attached drawing.
Fig. 2 is the method flow diagram that the direct broadcasting room that another embodiment of the application provides recommends method.As shown in Fig. 2, the party
Method includes：
Step 201, the room surface plot to set cycle crawl direct broadcasting room, the live scene as the direct broadcasting room are cut
Figure.
The key feature that step 202, the extraction live scene sectional drawing include.
Step 203, basis direct broadcasting room feature recognition model trained in advance, are identified the key feature.
Step 204, according to the identification as a result, determine the direct broadcasting room room property.
Step 205, calculate the corresponding room features label of direct broadcasting room feature tag corresponding with the interest of user it
Between similarity.
Step 206, when the similarity be more than default similarity threshold when, the direct broadcasting room is recommended into the use
Family.
In step 201, optionally, live scene sectional drawing can be the room front cover sectional drawing of direct broadcasting room.In general, per always
There is a mark front cover, which can be that live streaming platform is intercepted from the content of the room current live between broadcasting.
In an optional embodiment, the room front cover of direct broadcasting room is stored in a spatial cache, and room front cover and straight
The correspondence between ID between broadcasting also is stored in the spatial cache.It, can when live streaming platform shows a direct broadcasting room in channel page
Room corresponding with the ID of direct broadcasting room front cover is determined from above-mentioned spatial cache, and the room front cover is showed in channel page
Corresponding position.Optionally, in this step, the room envelope of stored direct broadcasting room can be directly obtained from above-mentioned spatial cache
Face, as the corresponding live scene sectional drawing in the room, to promote the efficiency for obtaining live scene sectional drawing.
Under a kind of possible scene, main broadcaster in different times section carry out different content live streaming, for example, from one hour
It is interior to be switched to sports show from game live streaming.To ensure the precision and timeliness of room property differentiation, optionally, Ke Yishe
Fixed cycle captures the room surface plot of direct broadcasting room, and then constantly updates the live scene sectional drawing of direct broadcasting room.The setting cycle can
To be an empirical value, such as it can be 10 minutes or 15 minutes, the present embodiment is not limited.
In step 202, after live scene sectional drawing is obtained, key feature can be extracted from live scene sectional drawing.It can
Choosing, key feature includes color characteristic, personage's posture feature, character face's feature, background characteristics in live scene sectional drawing
And/or stage property feature etc..It, in practice, can also be from straight of course it is to be understood that above-mentioned key feature uses by way of example only
It broadcasts and other are extracted in scene sectional drawing may characterize the feature of live content, the embodiment of the present application is not limited.
Optionally, key feature is extracted from live scene sectional drawing, at least one feature extraction algorithm, such as base can be used
Feature extraction algorithm, Hough change algorithm in color histogram, feature extraction algorithm based on template matches etc..Due to above-mentioned calculation
Method is ripe existing algorithm, and the present embodiment repeats no more.
In step 203, optionally, the identification of key feature can be real based on direct broadcasting room feature recognition model trained in advance
It is existing., can be using the key feature as the input parameter of direct broadcasting room feature recognition model after key feature is extracted, and will export
As a result it is used as recognition result.
Optionally, direct broadcasting room feature recognition model can be trained to obtain according to the key feature of substantial amounts of direct broadcasting room.
During training, a certain number of, corresponding different room property live scene sectional drawings are collected, and are known from these live scene sectional drawings
Not corresponding key feature.Then, can be used based on neutral net, linear/logistic regression, naive Bayesian or KNN (k-
Nearest Neighbor, K arest neighbors sorting algorithm) etc. machine learning methods, will multiple passes corresponding from different room properties
Key feature is broadcast live a training for feature recognition model, does not repeat herein as training sample.
In step 204, optionally, after recognition result is obtained, can be determined according to recognition result in the broadcasting of direct broadcasting room
Hold.For example, special identification live scene sectional drawing of color characteristic, personage's posture feature and stage property in live scene includes
One football pitch, sportsman and football can then determine that the broadcasting content of the direct broadcasting room corresponds to a foot according to above-mentioned recognition result
Ball moves.
After the broadcasting content of direct broadcasting room is determined, the correspondence of broadcasting content and room features label can be inquired about, into
And determine the corresponding room features label of the direct broadcasting room.Optionally, in the present embodiment, broadcasting content and room features label
Correspondence is pre-established and is stored in designated memory space, after the broadcasting content of direct broadcasting room is determined, is deposited specifying
Storage is inquired about in space, you can determines the corresponding room features label of the direct broadcasting room.For example, the broadcasting content of direct broadcasting room is foot
When ball moves, can inquire the corresponding room features label of direct broadcasting room is：Physical culture, football, confrontation, world cup, open air etc..
In step 205, after the corresponding room features label of definite direct broadcasting room, for a user to be recommended, can count
Calculate the similarity between the corresponding room features label of direct broadcasting room feature tag corresponding with the interest of the user.Optionally, should
The corresponding feature tag of interest of user can make that User Defined sets or live streaming platform is according to the browsing of user
It records and analyzes what is obtained, does not repeat herein.
Optionally, Euclidean distance algorithm (Eucledian Distance) can be used in similarity, manhatton distance is calculated
Method (Manhattan Distance) or the realization of cosine similarity (Cosine Similarity) algorithm, the embodiment of the present application pair
Which kind of it is not limited using above-mentioned algorithm.
By taking cosine similarity algorithm as an example, when calculating similarity, by the collection cooperation of the corresponding feature tag of the interest of user
For vectorial X, X=(x1, x2 ... xn), using the set of the corresponding room features label of direct broadcasting room as vector Y, Y=(y1, y2 ...
yn)；Wherein, x1, x2 ... xn are the feature tag included in vector X, and y1, y2 ... yn are the feature tag included in vector Y.Its
In, n is characterized the total number of label, and n is positive integer.Then the corresponding room features label of direct broadcasting room is corresponding with the interest of the user
Feature tag between similarity sim (X, Y) can be used equation below calculating：
In above-mentioned formula, X*Y represents feature vector, X and the Inner products of Y, | | X | | and | | Y | | feature vector, X is represented respectively
With the mould of Y.The value of sim (X, Y) is bigger, illustrates the corresponding room features label of direct broadcasting room feature corresponding with the interest of the user
Similarity between label is higher.
In step 206, the corresponding room features label of direct broadcasting room feature corresponding with the interest of the user is calculated
After similarity between label, when judging whether the similarity is more than default similarity threshold, if it has, then this is straight
The user is recommended between broadcasting, and then realizes and precisely recommends.
Optionally, when which being recommended user, it can show that this is recommended straight in the recommendation channel of live streaming platform
Recommend the direct broadcasting room between broadcasting or in the form of sending out notice message, and then user can easily see that possibility is interested
Direct broadcasting room further increases the usage rate of the user of live streaming platform.
It should be noted that the executive agent of each step of above-described embodiment institute providing method may each be same equipment,
Alternatively, this method is also by distinct device as executive agent.For example, the executive agent of step 201 to step 203 can be equipment
A；For another example, step 201 and 202 executive agent can be device A, and the executive agent of step 203 can be equipment B；Etc..
In addition, in some flows of description in above-described embodiment and attached drawing, contain what is occurred according to particular order
Multiple operations, but it should be clearly understood that these operations can not perform or parallel according to the order that it occurs herein
It performs, the sequence number such as 101,102 etc. of operation is only used for distinguishing each different operation, and sequence number does not represent any in itself
Execution sequence.In addition, these flows can include more or fewer operations, and these operation can perform in order or
It is parallel to perform.
The foregoing describe the optional embodiment that direct broadcasting room recommends method, as shown in figure 3, in practice, which recommends
Method can be realized by direct broadcasting room recommendation apparatus, as shown in figure 3, the equipment includes：Memory 31 and processor 32, input dress
Put 33 and output device 34.
Memory 31 and processor 32, input unit 33 and output device 34 can be connected by bus or other modes
It connects, in Fig. 3 by taking bus connects as an example.
Wherein, memory 31 is for storing one or more computer instruction, and can be configured as storing other various numbers
The operation on direct broadcasting room recommendation apparatus is supported according to this.The example of these data includes operating on direct broadcasting room recommendation apparatus
Any application program or method instruction.
Memory 31 can realize by any kind of volatibility or non-volatile memory device or combination thereof, such as
Static RAM (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable is read-only to be deposited
Reservoir (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or
CD.
In some embodiments, memory 31 is optional including compared with the remotely located memory of processor 32, these are remote
Journey memory can pass through network connection to direct broadcasting room recommendation apparatus.The example of above-mentioned network includes but not limited to internet, enterprise
Industry in-house network, LAN, mobile radio communication and combinations thereof.
Memory 32 is coupled with memory 31, for perform one or more computer instruction for：It obtains straight
Corresponding live scene sectional drawing between broadcasting；The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；
The direct broadcasting room is recommended and the matched user of the room property.
Still optionally further, memory 32 is specifically used for：To set the room surface plot that the cycle captures the direct broadcasting room；It will
Live scene sectional drawing of the room surface plot as the direct broadcasting room.
Still optionally further, memory 32 is specifically used for：Extract the key feature that the live scene sectional drawing includes；According to
Trained direct broadcasting room feature recognition model in advance, is identified the key feature；According to the identification as a result, determining institute
State the corresponding room features label of direct broadcasting room, the room property as the direct broadcasting room.
Still optionally further, memory 32 is specifically used for：According to the recognition result, in the broadcasting for determining the direct broadcasting room
Hold；According to the broadcasting content of the direct broadcasting room, inquiry broadcasting content and the correspondence of room features label are described straight to determine
Corresponding room features label between broadcasting；By the corresponding room features label of the direct broadcasting room, the room as the direct broadcasting room
Between attribute.
Still optionally further, memory 32 is specifically used for：Calculate the corresponding room features label of the direct broadcasting room and user
The corresponding feature tag of interest between similarity；It, will be described straight when the similarity is more than default similarity threshold
The user is recommended between broadcasting.
Input unit 33 can receive the number of input or character information and generate and the user of direct broadcasting room recommendation apparatus sets
It puts and the input of key signals that function control is related.Output device 34 may include the display devices such as display screen.
Further, as shown in figure 3, the direct broadcasting room recommendation apparatus further includes：Power supply module 35.Power supply module 35 is power supply
The various assemblies of equipment provide electric power where component.Power supply module can include power-supply management system, one or more power supplys and
Other with for equipment generation where power supply module, management and the associated component of distribution electric power.
Above-mentioned direct broadcasting room recommendation apparatus can perform the direct broadcasting room that the embodiment of the present application is provided and recommend method, possess the side of execution
The corresponding function module of method and advantageous effect.The not technical detail of detailed description in the present embodiment, reference can be made to the application is implemented
The method that example is provided, repeats no more.
This application is with reference to the stream according to the method for the embodiment of the present application, equipment (system) and computer program product
Journey figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions each in flowchart and/or the block diagram
The combination of flow and/or box in flow and/or box and flowchart and/or the block diagram.These computer journeys can be provided
Sequence instruct to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor with
Generate a machine so that the instruction generation performed by computer or the processor of other programmable data processing devices is used for
Realize the dress for the function of being specified in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
It puts.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only memory (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.It defines, calculates according to herein
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of elements are not only including those elements, but also wrap
Include other elements that are not explicitly listed or further include for this process, method, commodity or equipment it is intrinsic will
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
Also there are other identical elements in the process of element, method, commodity or equipment.
The foregoing is merely embodiments herein, are not limited to the application.For those skilled in the art
For, the application can have various modifications and variations.All any modifications made within spirit herein and principle are equal
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (10)
1. a kind of direct broadcasting room recommends method, which is characterized in that including：
Obtain the corresponding live scene sectional drawing of direct broadcasting room；
The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；
The direct broadcasting room is recommended and the matched user of the room property.
2. according to the method described in claim 1, it is characterized in that, obtain the corresponding live scene sectional drawing of direct broadcasting room, including：
To set the room surface plot that the cycle captures the direct broadcasting room；
Using the room surface plot as the live scene sectional drawing of the direct broadcasting room.
3. according to the method described in claim 1, it is characterized in that, the live scene sectional drawing is identified, to determine institute
The room property of direct broadcasting room is stated, including：
Extract the key feature that the live scene sectional drawing includes；
According to direct broadcasting room feature recognition model trained in advance, the key feature is identified；
According to the identification as a result, determining the corresponding room features label of the direct broadcasting room, the room as the direct broadcasting room
Attribute.
4. the method according to any one of claim 3, which is characterized in that according to the identification as a result, determining
The corresponding room features label of direct broadcasting room, as the room property of the direct broadcasting room, including：
According to the recognition result, the broadcasting content of the direct broadcasting room is determined；
According to the broadcasting content of the direct broadcasting room, inquiry broadcasting content and the correspondence of room features label are described to determine
The corresponding room features label of direct broadcasting room；
By the corresponding room features label of the direct broadcasting room, the room property as the direct broadcasting room.
5. the method according to claim 3 or 4, which is characterized in that recommend the direct broadcasting room and the room property
Matched user, including：
Calculate the similarity between the corresponding room features label of direct broadcasting room feature tag corresponding with the interest of user；
When the similarity is more than default similarity threshold, the direct broadcasting room is recommended into the user.
6. according to the method described in claim 5, it is characterized in that, the corresponding feature tag of the interest of the user, including：
The feature tag that the user is set according to own interests；And/or recording gauge is watched according to the history of the user and is calculated
It is arriving with the user matched feature tag of interest.
7. a kind of direct broadcasting room recommendation apparatus, which is characterized in that including：Memory and processor；
Wherein, the memory is for one or more computer instruction of storage；
The processor is used for：Perform one or more computer instruction for：
Obtain the corresponding live scene sectional drawing of direct broadcasting room；
The live scene sectional drawing is identified, to determine the room property of the direct broadcasting room；
The direct broadcasting room is recommended and the matched user of the room property.
8. equipment according to claim 7, which is characterized in that the processor is specifically used for：
To set the room surface plot that the cycle captures the direct broadcasting room；
Using the room surface plot as the live scene sectional drawing of the direct broadcasting room.
9. equipment according to claim 7, which is characterized in that the processor is specifically used for：
Extract the key feature that the live scene sectional drawing includes；
According to direct broadcasting room feature recognition model trained in advance, the key feature is identified；
According to the identification as a result, determining the corresponding room features label of the direct broadcasting room, the room as the direct broadcasting room
Attribute.
10. equipment according to claim 9, which is characterized in that the processor is specifically used for：
Calculate the similarity between the corresponding room features label of direct broadcasting room feature tag corresponding with the interest of user；
When the similarity is more than default similarity threshold, the direct broadcasting room is recommended into the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711387616.9A CN108076354A (en) | 2017-12-20 | 2017-12-20 | Direct broadcasting room recommends method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711387616.9A CN108076354A (en) | 2017-12-20 | 2017-12-20 | Direct broadcasting room recommends method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108076354A true CN108076354A (en) | 2018-05-25 |
Family
ID=62159027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711387616.9A Pending CN108076354A (en) | 2017-12-20 | 2017-12-20 | Direct broadcasting room recommends method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108076354A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034049A (en) * | 2018-07-23 | 2018-12-18 | 北京密境和风科技有限公司 | The recognition methods of dancing video and device |
| CN109086822A (en) * | 2018-08-01 | 2018-12-25 | 广州虎牙信息科技有限公司 | A kind of main broadcaster's user classification method, device, equipment and storage medium |
| CN109151488A (en) * | 2018-07-06 | 2019-01-04 | 武汉斗鱼网络科技有限公司 | According to the method and system of user behavior real-time recommendation direct broadcasting room |
| CN109246451A (en) * | 2018-08-23 | 2019-01-18 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, server and storage medium |
| CN109286821A (en) * | 2018-09-30 | 2019-01-29 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, server and storage medium |
| CN109413483A (en) * | 2018-11-29 | 2019-03-01 | 北京字节跳动网络技术有限公司 | Method for previewing, device, equipment and the medium of live content |
| CN109462778A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of live streaming mark |
| CN110196921A (en) * | 2018-08-08 | 2019-09-03 | 腾讯科技（深圳）有限公司 | Main broadcaster's classification method and device, storage medium and electronic device |
| CN110267057A (en) * | 2019-07-16 | 2019-09-20 | 北京达佳互联信息技术有限公司 | A kind of method and device of the classification of live data |
| CN110475132A (en) * | 2019-08-21 | 2019-11-19 | 广州虎牙科技有限公司 | Direct broadcasting room kind identification method, device and data processing equipment |
| WO2019228268A1 (en) * | 2018-05-28 | 2019-12-05 | 广州虎牙信息科技有限公司 | Method for displaying live broadcast room, apparatus, device, and storage medium |
| CN110827073A (en) * | 2019-10-31 | 2020-02-21 | 北京达佳互联信息技术有限公司 | Data processing method and device |
| CN110876088A (en) * | 2018-09-03 | 2020-03-10 | 广州虎牙信息科技有限公司 | Live broadcast room recommendation method, device, equipment and storage medium |
| CN111291666A (en) * | 2020-01-21 | 2020-06-16 | 北京达佳互联信息技术有限公司 | Game live video identification method and device, electronic equipment and storage medium |
| CN112348649A (en) * | 2020-12-07 | 2021-02-09 | 福州市长乐区三互信息科技有限公司 | Live broadcast category recommendation method |
| 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 |
| CN112579801A (en) * | 2020-12-28 | 2021-03-30 | 浙江口碑网络技术有限公司 | Live broadcast room classification method and device, storage medium and computer equipment |
| CN113395537A (en) * | 2021-06-16 | 2021-09-14 | 北京百度网讯科技有限公司 | Method and device for recommending live broadcast room |
| CN114650429A (en) * | 2022-02-24 | 2022-06-21 | 北京达佳互联信息技术有限公司 | Information display method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245937A (en) * | 2015-09-30 | 2016-01-13 | 武汉科优达科技有限公司 | Video scene control system and method |
| CN106162248A (en) * | 2016-06-27 | 2016-11-23 | 武汉斗鱼网络科技有限公司 | Management method and the system of position promoted by live platform |
| CN106550252A (en) * | 2016-12-08 | 2017-03-29 | 北京小米移动软件有限公司 | The method for pushing of information, device and equipment |
| CN107404656A (en) * | 2017-06-26 | 2017-11-28 | 武汉斗鱼网络科技有限公司 | Live video recommends method, apparatus and server |
-
2017
- 2017-12-20 CN CN201711387616.9A patent/CN108076354A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245937A (en) * | 2015-09-30 | 2016-01-13 | 武汉科优达科技有限公司 | Video scene control system and method |
| CN106162248A (en) * | 2016-06-27 | 2016-11-23 | 武汉斗鱼网络科技有限公司 | Management method and the system of position promoted by live platform |
| CN106550252A (en) * | 2016-12-08 | 2017-03-29 | 北京小米移动软件有限公司 | The method for pushing of information, device and equipment |
| CN107404656A (en) * | 2017-06-26 | 2017-11-28 | 武汉斗鱼网络科技有限公司 | Live video recommends method, apparatus and server |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019228268A1 (en) * | 2018-05-28 | 2019-12-05 | 广州虎牙信息科技有限公司 | Method for displaying live broadcast room, apparatus, device, and storage medium |
| US11153652B2 (en) | 2018-05-28 | 2021-10-19 | Guangzhou Huya Information Technology Co., Ltd. | Method for displaying live broadcast room, apparatus, device, and storage medium |
| CN109151488A (en) * | 2018-07-06 | 2019-01-04 | 武汉斗鱼网络科技有限公司 | According to the method and system of user behavior real-time recommendation direct broadcasting room |
| CN109034049A (en) * | 2018-07-23 | 2018-12-18 | 北京密境和风科技有限公司 | The recognition methods of dancing video and device |
| CN109086822A (en) * | 2018-08-01 | 2018-12-25 | 广州虎牙信息科技有限公司 | A kind of main broadcaster's user classification method, device, equipment and storage medium |
| CN110196921B (en) * | 2018-08-08 | 2023-04-14 | 腾讯科技（深圳）有限公司 | Anchor classification method and device, storage medium and electronic device |
| CN110196921A (en) * | 2018-08-08 | 2019-09-03 | 腾讯科技（深圳）有限公司 | Main broadcaster's classification method and device, storage medium and electronic device |
| CN109246451A (en) * | 2018-08-23 | 2019-01-18 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, server and storage medium |
| CN110876088A (en) * | 2018-09-03 | 2020-03-10 | 广州虎牙信息科技有限公司 | Live broadcast room recommendation method, device, equipment and storage medium |
| CN109286821A (en) * | 2018-09-30 | 2019-01-29 | 武汉斗鱼网络科技有限公司 | A kind of direct broadcasting room recommended method, device, server and storage medium |
| CN109462778A (en) * | 2018-11-15 | 2019-03-12 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of live streaming mark |
| CN109462778B (en) * | 2018-11-15 | 2020-10-16 | 武汉斗鱼网络科技有限公司 | Live broadcast identification recommendation method and related equipment |
| CN109413483B (en) * | 2018-11-29 | 2020-01-14 | 北京字节跳动网络技术有限公司 | Live content preview method, device, equipment and medium |
| CN109413483A (en) * | 2018-11-29 | 2019-03-01 | 北京字节跳动网络技术有限公司 | Method for previewing, device, equipment and the medium of live content |
| CN110267057A (en) * | 2019-07-16 | 2019-09-20 | 北京达佳互联信息技术有限公司 | A kind of method and device of the classification of live data |
| CN110475132A (en) * | 2019-08-21 | 2019-11-19 | 广州虎牙科技有限公司 | Direct broadcasting room kind identification method, device and data processing equipment |
| CN110827073A (en) * | 2019-10-31 | 2020-02-21 | 北京达佳互联信息技术有限公司 | Data processing method and device |
| CN111291666A (en) * | 2020-01-21 | 2020-06-16 | 北京达佳互联信息技术有限公司 | Game live video identification method and device, electronic 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 |
| CN112348649A (en) * | 2020-12-07 | 2021-02-09 | 福州市长乐区三互信息科技有限公司 | Live broadcast category recommendation method |
| CN112579801A (en) * | 2020-12-28 | 2021-03-30 | 浙江口碑网络技术有限公司 | Live broadcast room classification method and device, storage medium and computer equipment |
| CN113395537A (en) * | 2021-06-16 | 2021-09-14 | 北京百度网讯科技有限公司 | Method and device for recommending live broadcast room |
| CN113395537B (en) * | 2021-06-16 | 2023-05-16 | 北京百度网讯科技有限公司 | Method and device for recommending live broadcasting room |
| CN114650429A (en) * | 2022-02-24 | 2022-06-21 | 北京达佳互联信息技术有限公司 | Information display method and device, electronic equipment and storage medium |
| CN114650429B (en) * | 2022-02-24 | 2024-04-16 | 北京达佳互联信息技术有限公司 | Information display method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108076354A (en) | Direct broadcasting room recommends method and apparatus | |
| CN104247441B (en) | Automatic content recommendation | |
| CN108197330B (en) | Data digging method and device based on social platform | |
| CN107404656B (en) | Live video recommended method, device and server | |
| Baluja et al. | Video suggestion and discovery for youtube: taking random walks through the view graph | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN110232403A (en) | A kind of Tag Estimation method, apparatus, electronic equipment and medium | |
| WO2017181612A1 (en) | Personalized video recommendation method and device | |
| CN103365936A (en) | Video recommendation system and method thereof | |
| CN107894998B (en) | Video recommendation method and device | |
| CN108920577A (en) | Television set intelligently recommended method | |
| CN109409928A (en) | A kind of material recommended method, device, storage medium, terminal | |
| CN109657100A (en) | Video Roundup generation method and device, electronic equipment and storage medium | |
| EP3047392A1 (en) | System and method for actively obtaining social data | |
| CN102780920A (en) | Television program recommending method and system | |
| CN106649316A (en) | Video pushing method and device | |
| CN105045818A (en) | Picture recommending method, apparatus and system | |
| CN106168980A (en) | Multimedia resource recommends sort method and device | |
| CN104123315A (en) | Multi-media file recommendation method and recommendation server | |
| CN104199872A (en) | Information recommendation method and device | |
| CN111400546B (en) | Video recall method and video recommendation method and device | |
| CN105809275A (en) | Item scoring prediction method and apparatus | |
| US11651450B2 (en) | Simulated network system and method for relating users of real-world e-commerce and other user network systems to information | |
| CN103886003A (en) | Collaborative filtering processor | |
| CN106294483A (en) | For mating data processing method and the device of mouthpiece for product brand |
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 |
Application publication date: 20180525 |
|
| RJ01 | Rejection of invention patent application after publication |