CN108171160A - A kind of task result recognition methods, device, storage medium and electronic equipment - Google Patents
A kind of task result recognition methods, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108171160A CN108171160A CN201711448937.5A CN201711448937A CN108171160A CN 108171160 A CN108171160 A CN 108171160A CN 201711448937 A CN201711448937 A CN 201711448937A CN 108171160 A CN108171160 A CN 108171160A
- Authority
- CN
- China
- Prior art keywords
- client
- main broadcaster
- information
- goal task
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application provides a kind of task result recognition methods, device, storage medium and electronic equipment.This method includes:Goal task data are issued into client;Image identification is carried out to the picture frame that client is sent, is identified and the relevant object content data of the goal task data;According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.It is intended to reduce the cost of task result identification.
Description
Technical field
This application involves internet arena more particularly to live streaming in task result recognition methods, device, storage medium and
Electronic equipment.
Background technology
With the development of internet live streaming industry, the form of internet live streaming is more and more, wherein game live streaming is by wide
Large user's likes, task is a kind of mode for guiding main broadcaster that specified live content is presented, and still, issues task to main broadcaster at present
Afterwards, since live content data can not be directly obtained, so needing through the manually opened side settled accounts manually of official operation personnel
Formula is completed, and operating cost is very high, and efficiency is very low.
Invention content
This application provides a kind of task result recognition methods, device, storage medium and electronic equipments.It is intended to reduction task
As a result the cost identified.
Specifically, the application is achieved by the following technical solution:
A kind of task result recognition methods, the method includes:
Goal task data are issued into client;
To client send picture frame carry out image identification, identify in the relevant target of goal task data
Hold data;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
In some instances, the target live content data include following any:The motion characteristic of target critical object
Data and attribute data;
The target critical object includes main broadcaster's image or virtual role image.
In some instances, image identification is carried out to the picture frame that client is sent, identified and the goal task number
According to relevant object content data, including:
The picture frame that client is sent inputs neural network model, obtains the output result of the neural network model;
Object content data are obtained according to the output result;
The neural network model includes:The full convolutional Neural of convolutional neural networks model, deep neural network model, depth
Network model, Recognition with Recurrent Neural Network model, full convolutional neural networks model and depth convolutional neural networks model.
In some instances, image identification is carried out to the picture frame that client is sent, identified and the goal task number
According to relevant object content data, including:
According to the goal task data, characteristic is obtained;
According to the characteristic, image identification is carried out to the picture frame that client is sent, obtains key images frame;
It is identified from the key images frame and the relevant object content data of the goal task data.
In some instances, the method is performed by direct broadcast service end, and client is broadcast based on the client;
Main broadcaster's information and/or the audience information generation of online main broadcaster of the goal task based on main broadcaster's client;
Main broadcaster's information includes following any:The popularity value of main broadcaster, the performance of main broadcaster's historic task, main broadcaster body
The positioning by sharing information, the live streaming duration information, main broadcaster's client of main broadcaster of part information, the subscribed information of main broadcaster, main broadcaster
Information and main broadcaster's client start broadcasting pattern information;
The audience information includes following at least any:Viewer preference information, spectators watch the record information of live streaming, spectators
Identity information and spectators gender information.
In some instances, the method is performed by direct broadcast service end, and client is broadcast based on the client;
After obtaining to the completion result of goal task, including:
According to described as a result, the corresponding resource of goal task data is issued to corresponding spectator client;
Corresponding spectator client generates or is determined or preset by main broadcaster's client at random.
A kind of task result identification device, including:
Sending module, for goal task data to be issued client;
Processing module, the picture frame for being sent to client carry out image identification, identify and the goal task number
According to relevant object content data;According to the object content data and the matching degree of goal task data, obtain and target is appointed
The completion result of business.
A kind of electronic equipment, including:
Processor;For storing the memory of the processor-executable instruction;
Wherein, the processor is configured as performing following operation:
Goal task data are issued into client;
To client send picture frame carry out image identification, identify in the relevant target of goal task data
Hold data;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
A kind of storage medium, is stored thereon with computer program, which is executed by processor following operation:
Goal task data are issued into client;
To client send picture frame carry out image identification, identify in the relevant target of goal task data
Hold data;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
The application by goal task data by issuing client;Image identification is carried out to the picture frame that client is sent,
It identifies and the relevant object content data of the goal task data;According to the object content data and goal task data
Matching degree, obtain the completion result to goal task.Since picture frame can reflect content-data, pass through the side of image identification
Formula can largely liberate the human cost of operation personnel.
Description of the drawings
Attached drawing herein is incorporated into specification and forms the part of this specification, shows the implementation for meeting the application
Example, and for explaining the principle of the application together with specification.
Fig. 1 is a kind of partial process view for task result recognition methods that one exemplary embodiment of the application provides;
Fig. 2 is a kind of live scene schematic diagram shown in one exemplary embodiment of the application;
Fig. 3 is the part flow of task result recognition methods during the another kind shown in one exemplary embodiment of the application is broadcast live
Figure;
Fig. 4 is the partial process view of another task result recognition methods shown in one exemplary embodiment of the application;
Fig. 5 is a kind of schematic diagram of main broadcaster's client end interface shown in one exemplary embodiment of the application;
Fig. 6 is the partial process view of another task result recognition methods shown in one exemplary embodiment of the application;
Fig. 7 is the schematic diagram of another main broadcaster's client end interface shown in one exemplary embodiment of the application;
Fig. 8 is the logic diagram of a kind of electronic equipment shown in one exemplary embodiment of the application;
Fig. 9 is a kind of logic diagram of task result identification device shown in one exemplary embodiment of the application;
Figure 10 is the logic diagram of another task result identification device shown in one exemplary embodiment of the application.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, example is illustrated in the accompanying drawings.Following description is related to
During attached drawing, unless otherwise indicated, the same numbers in different attached drawings represent the same or similar element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
It is only merely for the purpose of description specific embodiment in term used in this application, and is not intended to be limiting the application.
It is also intended in the application and " one kind " of singulative used in the attached claims, " described " and "the" including majority
Form, unless context clearly shows that other meanings.It is also understood that term "and/or" used herein refers to and wraps
Containing one or more associated list items purposes, any or all may be combined.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, not departing from
In the case of the application range, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
It is a kind of partial process view for task result recognition methods that one exemplary embodiment of the application provides with reference to Fig. 1,
Part steps are as follows:
S110:Goal task data are issued into client;
S120:Image identification is carried out to the picture frame that client is sent, is identified relevant with the goal task data
Object content data;
S130:According to the object content data and the matching degree of goal task data, the completion to goal task is obtained
As a result.
In some instances, the method can be applied to internet live streaming and game etc. in fields, and the method can be with
The server-side for being broadcast live by internet or being played performs, and " server-side " that the embodiment of the present application proposes can be that a server is set
Standby or server system general designation or at least one software on server apparatus.The application is real
" client " for applying example proposition can be the software run on electronic equipment.
The equipment that " electronic equipment " that the embodiment of the present application proposes both had included wireless signal receiver, only has non-emissive
The equipment of the wireless signal receiver of ability, and the equipment including receiving and emitting hardware, having can be in two-way communication chain
On the road, it carries out the reception of two-way communication and emits the equipment of hardware.This equipment can include:Honeycomb or other communication equipments,
Its honeycomb or other communication equipments with single line display or multi-line display or without multi-line display;PCS
(Personal Communications Service, PCS Personal Communications System), can be with combine voice, data processing, fax
And/or communication ability;PDA (Personal Digital Assistant, personal digital assistant), can include radio frequency
Receiver, pager, the Internet/intranet access, web browser, notepad, calendar and/or GPS (Global
Positioning System, global positioning system) receiver;Conventional laptop and/or palmtop computer or other equipment,
It has and/or the conventional laptop including radio frequency receiver and/or palmtop computer or other equipment.It is used herein above
" terminal ", " terminal device " can be portable, can transport, in the vehicles (aviation, sea-freight and/or land),
Or be suitable for and/or be configured in local runtime and/or with distribution form, operate in any other of the earth and/or space
Position is run." electronic equipment " used herein above can also be communication terminal, access terminals, music/video playback terminal, example
It such as can be PDA, MID (Mobile Internet Device, mobile internet device) and/or be played with music/video
The equipment such as the mobile phone or smart television of function, set-top box.
The action that " the object content data " that the embodiment of the present application proposes can include target critical object in picture frame is special
Data are levied, such as singing and dancing etc. can also include the attribute data of target critical object, such as the identity of target critical object
And state (such as survival and death) etc.;The target critical object can be main broadcaster, personage or virtual role in picture frame
Deng the virtual role can be the hero in game picture.For example, the object content data can be:Main broadcaster (close by target
Key object) in the behavioral datas such as dancing in picture frame or singing or game the triumph of virtual role or dead data or
It is incremental data of target critical object etc. in picture frame.It is appreciated that the application is not intended to limit the class of the object content data
Type.
In some instances, in above-mentioned steps S120, the technology of machine learning can be utilized to obtain target from picture frame
Content-data;Specifically, described image frame can be inputted neural network model, obtains the output knot of the neural network model
Fruit;Object content data are obtained according to the output result;The neural network model is formed by sample training.The nerve
Network model includes:The full convolutional neural networks model of convolutional neural networks model, deep neural network model, depth, cycle god
Through network model, full convolutional neural networks model and depth convolutional neural networks model etc..
In some instances, in step S120, can also be believed according to goal task data acquisition characteristic information according to feature
Breath obtains target image frame, and object content data are obtained from target image frame.For example, goal task is:Obtain a game
Triumph, can to picture frame carry out image identification, can the type of game be identified according to the picture of video image frame, adjust
Corresponding characteristic information when taking the game victory or defeat, then when there are during the characteristic information in picture frame, it is believed that the video
Picture frame is target image frame, if the object content data identified in the target image frame are triumpies, it is believed that played
Triumph.The application is not intended to limit image and knows otherwise.
It is the embodiment of the present application with reference to Fig. 2 so that the method that the embodiment of the present application proposes is used in internet live streaming as an example
One application scenarios schematic diagram of live streaming, the first spectator client 211, the second spectator client 221 and main broadcaster's client 231 are divided
It is not installed on electronic equipment 210,220 and 230, main broadcaster's client 231 can call camera recorded video, and shooting is shone
Piece makes live video stream by other modes such as screen captures, is then sent to server-side 200 by network.Server-side
200 for provide internet live streaming background service, such as preserve each main broadcaster's client and spectator client correspondence and
It is broadcast live distribution of video flowing etc..When the first spectator client 211, the second spectator client 221 exist with main broadcaster's client 231
In same direct broadcasting room, main broadcaster's client can be shown on the interface of the first spectator client 211 and the second spectator client 221
231 video image frames made, the video image frame can reflect live content.The method application that the embodiment of the present application proposes
When field is broadcast live in internet, picture frame can be referred to as video image frame.
" direct broadcasting room " that the embodiment of the present application proposes refers to social network-i i-platform, Instant Messenger that numerous users condense together
Platform etc. is interrogated, user enters direct broadcasting room by way of logging in client, and user exists in direct broadcasting room with the identity of member, together
The member there are many identity, such as spectators and main broadcaster etc. are included in one direct broadcasting room.User arbitrarily can login or publish direct broadcasting room.
For having the user of certain permission (such as main broadcaster), direct broadcasting room member can be added or deleted, also can create or dismiss live streaming
Between.In direct broadcasting room, any number of members can utilize chat (such as utilizing barrage messaging chat), call, video or push electricity
The interactions such as sub- present." direct broadcasting room " can also be a label, which can be associated with the ID of main broadcaster.
" main broadcaster's client " " spectator client " can refer to the software of installation on an electronic device, in certain situations
Under, main broadcaster's client is integrated in spectator client on a software, and when the identity of user is main sowing time, which can
To be referred to as main broadcaster's client, when the identity of user is spectators, which is referred to as spectator client.
It is a kind of partial process view for live broadcasting method that one exemplary embodiment of the application provides with reference to Fig. 3, the live streaming
Method can be performed by server-side, and part steps are as follows:
S310:Goal task data are issued into main broadcaster's client;
S320:Image identification is carried out to the video image frame that main broadcaster's client is sent, is identified and the goal task number
According to relevant object content data;
S330:According to the object content data and the matching degree of goal task data, the completion to goal task is obtained
As a result.
The application obtains the object content data in live streaming by the technology that image identifies, can largely liberate fortune
The human cost of staff is sought, and the completion of any type of goal task can be obtained as a result, dramatically enriching
The type of task in live streaming increases the interest of live streaming.
In some instances, goal task data can be based on the online main broadcaster of main broadcaster's client main broadcaster's information and/or
Audience information generates, and is the partial process view for another live broadcasting method that one exemplary embodiment of the application provides with reference to Fig. 4,
Before step S310, step S410 can also be performed:Main broadcaster's information of online main broadcaster based on main broadcaster's client and/or spectators
Information generates goal task data.In some instances, main broadcaster's information can include following at least any:The history of main broadcaster
Live information, the popularity value of main broadcaster, the performance of main broadcaster's historic task, the identity information of main broadcaster, main broadcaster subscribed information,
Live streaming duration information, the location information of main broadcaster's client and the main broadcaster's client by sharing information, main broadcaster of main broadcaster starts broadcasting pattern
Information etc.;Live streaming has the positioning of many forms, and the location information of main broadcaster's client can be the live streaming shape of main broadcaster's client
Formula positions, such as intelligence and art displaying, game live streaming and outdoor live streaming.The audience information can include following at least any:Spectators
Preference information, spectators watch gender information of the record information of live streaming, the identity information of spectators and spectators etc..
In some instances, can task data be generated according to audience information, further according to main broadcaster's information from the number of tasks
Goal task data are picked out in.Since audience information can reflect the hobby of spectators, according to the task of audience information generation
Data can guide main broadcaster to perform the favorite behavior of spectators or make popular live content, further according to main broadcaster's data
The goal task data of suitable main broadcaster can be selected from task data, to ensure the reasonability of the distribution of task.For example, according to
Audience information generates several task datas, and " today uses angle for task one " today jumps one section of dancing a in live streaming " and task two
Color b completes the triumph of game c ", according to main broadcaster's information of online main broadcaster, such as main broadcaster's history live information, if the main broadcaster is
One game main broadcaster, then can distribute to the main broadcaster by task two;Certainly can also according to the location information where main broadcaster, based on
Distribution goal task is broadcast, if the positioning of the main broadcaster is in song and dance class, then can task one be distributed to the main broadcaster.
In some instances, the goal task may be displayed on the interface of main broadcaster's client, can also be illustrated in correspondence
Spectator client interface on;In some instances, the selection of main broadcaster can be responded, task is illustrated in spectator client
On interface, such as:When showing goal task on the interface of main broadcaster's client, " selection " control can be shown, when main broadcaster's point
It sends to instruct to server-side when hitting described " selection " control, after server-side receives described instruction, goal task data is sent
To corresponding spectator client.In some instances, main broadcaster can select every ten minutes interface displays one in spectator client
Secondary goal task.It is the interface schematic diagram of main broadcaster's client shown in one illustrative examples of the application referring for example to Fig. 5, it is main
It broadcasts client to run on electronic equipment 510, interface 520 can show the goal task data 521 that server-side is sent, can be with
The control 523 of displaying " showing goal task in spectator client ", can be in corresponding spectators when main broadcaster clicks the control
The goal task data are shown on the interface of client.The mode of the displaying can be Dynamic Display or static display.
The Dynamic Display can roll displaying.The relative clients end can be the spectators client that the main broadcaster of main broadcaster's client specifies
All spectator clients in end or direct broadcasting room.
With reference to Fig. 6, in order to further increase interactivity, in some instances, after step S330, step can be performed
S340:According to described as a result, the corresponding resource of goal task data is issued to corresponding spectator client.Corresponding sight
Many clients generate or are determined or preset by main broadcaster's client at random.It is described determined by main broadcaster's client can be:It is main
It broadcasts after completion task, the corresponding resource of the goal task can be issued to the spectators that main broadcaster's client is selected;It is described pre-
First make a reservation for after being main broadcaster's completion task, the arbitrary sight corresponding resource of the goal task being issued in direct broadcasting room
Crowd, to increase the enthusiasm that spectators participate in direct broadcasting room.It is a kind of master shown in one exemplary embodiment of the application with reference to Fig. 7
The schematic diagram of client end interface is broadcast, main broadcaster's client is run on electronic equipment 510, and interface 520 can show that server-side is sent
Goal task data 521, the control 522 of " provide reward " when goal task is completed, can be shown on interface, so that phase
The spectator client answered obtains the corresponding resource of goal task.After the embodiment of the present application is by main broadcaster's completion task, by task pair
The resource answered is issued to spectators, has been thusly-formed the interaction mode of " main broadcaster → spectators ", increases interest and the interaction of live streaming
Property.
In some instances, the corresponding resource of goal task data can be issued to corresponding spectator client by described
When, the information for the spectator client for obtaining corresponding resource can also be illustrated in direct broadcasting room.
Corresponding with the embodiment of foregoing task result recognition methods, present invention also provides task result identification devices
Embodiment.
The embodiment of the application task result identification device can be applied on an electronic device.Device embodiment can pass through
Software is realized, can also be realized by way of hardware or software and hardware combining.For implemented in software, anticipate as a logic
Device in justice is by computer program instructions corresponding in nonvolatile memory by the processor of electronic equipment where it
Read what operation in memory was formed.For hardware view, as shown in figure 8, where the application task result identification device
A kind of hardware structure diagram of electronic equipment, in addition to processor shown in Fig. 8, memory, network interface and nonvolatile memory
Except, the electronic equipment in embodiment where device can also be wrapped generally according to the actual functional capability of the task result identification device
Other hardware are included, this is repeated no more.Fig. 8 is please referred to, disclosed herein as well is a kind of electronic equipment, including:Store processor
The memory of executable instruction;Wherein, the processor is coupled in the memory, for reading the journey of the memory storage
Sequence instructs, and in response, performs following operation:
Goal task data are issued into client;
To client send picture frame carry out image identification, identify in the relevant target of goal task data
Hold data;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
It is a kind of task result identification device 900 disclosed in the present application with reference to Fig. 9, including:
Sending module 910, for goal task data to be issued client;
Processing module 920, the picture frame for being sent to client carry out image identification, identify and the goal task
The relevant object content data of data;According to the object content data and the matching degree of goal task data, obtain to target
The completion result of task.
In some instances, the object content data include:The behavioral data of target critical object in described image frame.
In some instances, the picture frame that processing module 920 sends client carries out image identification, identify with it is described
The relevant object content data of goal task data, the picture frame that can also be processing module 920 for client to be sent are defeated
Enter neural network model, obtain the output result of the neural network model;
Object content data are obtained according to the output result;
The neural network model includes:The full convolutional Neural of convolutional neural networks model, deep neural network model, depth
Network model, Recognition with Recurrent Neural Network model, full convolutional neural networks model and depth convolutional neural networks model.
In some instances, the picture frame that processing module 920 sends client carries out image identification, identify with it is described
The relevant object content data of goal task data can also be processing module 920 for according to the goal task data, obtaining
Take characteristic;
According to the characteristic, image identification is carried out to the picture frame that client is sent, obtains key images frame;
It is identified from the key images frame and the relevant object content data of the goal task data.
With reference to Figure 10, in some instances, the client can broadcast client based on;Described device 900, which further includes, appoints
Business generation module 930 generates goal task for the main broadcaster's information and/or audience information of the online main broadcaster based on main broadcaster's client
Data;
Main broadcaster's information includes following any:The popularity value of main broadcaster, the performance of main broadcaster's historic task, main broadcaster body
The positioning by sharing information, the live streaming duration information, main broadcaster's client of main broadcaster of part information, the subscribed information of main broadcaster, main broadcaster
Information and main broadcaster's client start broadcasting pattern information;
The audience information includes following at least any:Viewer preference information, spectators watch the record information of live streaming, spectators
Identity information and spectators gender information.
In some instances, the client can broadcast client based on;Processing module 920 is obtained to the complete of goal task
Into after result, processing module 920 is used for according to described as a result, the corresponding resource of goal task data is issued to corresponding sight
Many clients;
Corresponding spectator client generates or is determined or preset by main broadcaster's client at random.
The embodiment of the present application can be used one or more wherein include program code storage medium (including but it is unlimited
In magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer can use storage
Medium includes permanent and non-permanent, removable and non-removable media, can realize information by any method or technique
Storage.Information can be computer-readable instruction, data structure, the module of program or other data.The storage medium of computer
Example include but not limited to:Phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory
(DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), fast flash memory bank or other memory techniques, CD-ROM 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-biography
Defeated medium, available for storing the information that can be accessed by a computing device.
Those skilled in the art will readily occur to the application its after considering specification and putting into practice the invention applied here
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and the common knowledge in the art do not applied including the application
Or conventional techniques.Description and embodiments are considered only as illustratively, and the true scope and spirit of the application are by following
Claim is pointed out.
It should be understood that the precision architecture that the application is not limited to be described above and be shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by appended claim.
The foregoing is merely the preferred embodiment of the application, not limiting the application, all essences in the application
God and any modification, equivalent substitution, improvement and etc. within principle, done, should be included within the scope of the application protection.
Claims (10)
1. a kind of task result recognition methods, which is characterized in that the method includes:
Goal task data are issued into client;
Image identification is carried out to the picture frame that client is sent, is identified and the relevant object content number of the goal task data
According to;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
2. according to the method described in claim 1, it is characterized in that, the target live content data are including following any:Mesh
Mark the motion characteristic data and attribute data of key object;
The target critical object includes main broadcaster's image or virtual role image.
3. according to the method described in claim 1, it is characterized in that, image identification, knowledge are carried out to the picture frame that client is sent
Do not go out with the relevant object content data of the goal task data, including:
The picture frame that client is sent inputs neural network model, obtains the output result of the neural network model;
Object content data are obtained according to the output result;
The neural network model includes following any:The full convolution of convolutional neural networks model, deep neural network model, depth
Neural network model, Recognition with Recurrent Neural Network model, full convolutional neural networks model and depth convolutional neural networks model.
4. according to the method described in claim 1, it is characterized in that, image identification, knowledge are carried out to the picture frame that client is sent
Do not go out with the relevant object content data of the goal task data, including:
According to the goal task data, characteristic is obtained;
According to the characteristic, image identification is carried out to the picture frame that client is sent, obtains key images frame;
It is identified from the key images frame and the relevant object content data of the goal task data.
5. according to the method described in claim 1, it is characterized in that, the method is performed by direct broadcast service end, the client
Based on broadcast client;
Main broadcaster's information and/or the audience information generation of online main broadcaster of the goal task based on main broadcaster's client;
Main broadcaster's information includes following at least any:The popularity value of main broadcaster, the performance of main broadcaster's historic task, main broadcaster body
The positioning by sharing information, the live streaming duration information, main broadcaster's client of main broadcaster of part information, the subscribed information of main broadcaster, main broadcaster
Information and main broadcaster's client start broadcasting pattern information;
The audience information includes following at least any:Viewer preference information, spectators watch the record information being broadcast live, the body of spectators
Part information and the gender information of spectators.
6. according to the method described in claim 1, it is characterized in that, the method is performed by direct broadcast service end, the client
Based on broadcast client;
After obtaining to the completion result of goal task, including:
According to described as a result, the corresponding resource of goal task data is issued to corresponding spectator client;
Corresponding spectator client generates or is determined or preset by main broadcaster's client at random.
7. a kind of task result identification device, which is characterized in that including:
Sending module, for goal task data to be issued client;
Processing module, the picture frame for being sent to client carry out image identification, identify and the goal task data phase
The object content data of pass;According to the object content data and the matching degree of goal task data, obtain to goal task
Complete result.
8. device according to claim 7, which is characterized in that broadcast client based on the client;Described device is also wrapped
It includes:
Task generation module generates target for the main broadcaster's information and/or audience information of the online main broadcaster based on main broadcaster's client
Task data;
Main broadcaster's information includes following any:The popularity value of main broadcaster, the performance of main broadcaster's historic task, the identity of main broadcaster letter
Breath, the subscribed information of main broadcaster, main broadcaster by sharing information, main broadcaster live streaming duration information, main broadcaster's client location information
And main broadcaster's client starts broadcasting pattern information;
The audience information includes following at least any:Viewer preference information, spectators watch the record information being broadcast live, the body of spectators
Part information and the gender information of spectators.
9. a kind of electronic equipment, which is characterized in that including:
Processor;For storing the memory of the processor-executable instruction;
Wherein, the processor is configured as performing following operation:
Goal task data are issued into client;
Image identification is carried out to the picture frame that client is sent, is identified and the relevant object content number of the goal task data
According to;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that the program is executed by processor following behaviour
Make:
Goal task data are issued into client;
Image identification is carried out to the picture frame that client is sent, is identified and the relevant object content number of the goal task data
According to;
According to the object content data and the matching degree of goal task data, the completion result to goal task is obtained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711448937.5A CN108171160B (en) | 2017-12-27 | 2017-12-27 | Task result identification method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711448937.5A CN108171160B (en) | 2017-12-27 | 2017-12-27 | Task result identification method and device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108171160A true CN108171160A (en) | 2018-06-15 |
CN108171160B CN108171160B (en) | 2021-03-23 |
Family
ID=62518545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711448937.5A Active CN108171160B (en) | 2017-12-27 | 2017-12-27 | Task result identification method and device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108171160B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109286822A (en) * | 2018-10-19 | 2019-01-29 | 广州虎牙科技有限公司 | Interactive approach, device, equipment and storage medium based on live video identification |
CN109446349A (en) * | 2018-09-28 | 2019-03-08 | 传线网络科技(上海)有限公司 | The checking method and device of multimedia content |
CN109561348A (en) * | 2018-12-27 | 2019-04-02 | 广州虎牙信息科技有限公司 | A kind of method for processing business based on live streaming, device, equipment and storage medium |
CN111757131A (en) * | 2020-04-03 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Task target setting method, device and system applied to live broadcast and electronic equipment |
CN112307299A (en) * | 2019-08-20 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information publishing method and device, computer equipment and storage medium |
CN114245223A (en) * | 2022-01-27 | 2022-03-25 | 广州方硅信息技术有限公司 | Live broadcast room task loading method, system and device and computer equipment |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020026512A1 (en) * | 2000-08-31 | 2002-02-28 | Sony Corporation | Content distribution notification method, reservation control apparatus and program storage medium |
CN103475908A (en) * | 2013-07-23 | 2013-12-25 | 北京九华互联科技有限公司 | Multi-screen synchronization play method and device |
CN103763113A (en) * | 2013-12-31 | 2014-04-30 | 广州华多网络科技有限公司 | Live network broadcast method and device and server |
US20140282200A1 (en) * | 2013-03-15 | 2014-09-18 | Mitel Networks Corporation | Method and system for automatically displaying information based on task context |
CN104168271A (en) * | 2014-08-01 | 2014-11-26 | 广州华多网络科技有限公司 | Interactive system, server, clients and interactive method |
CN105872640A (en) * | 2015-12-07 | 2016-08-17 | 乐视云计算有限公司 | Live broadcast video obtaining method, device and system |
CN105933738A (en) * | 2016-06-27 | 2016-09-07 | 徐文波 | Live video streaming method, device and system |
US20160337426A1 (en) * | 2015-05-14 | 2016-11-17 | Hola Networks Ltd. | System and Method for Streaming Content from Multiple Servers |
CN106231349A (en) * | 2015-12-30 | 2016-12-14 | 深圳超多维科技有限公司 | Main broadcaster's class interaction platform server method for changing scenes and device, server |
CN106303658A (en) * | 2016-08-19 | 2017-01-04 | 百度在线网络技术(北京)有限公司 | It is applied to exchange method and the device of net cast |
CN106604049A (en) * | 2016-12-19 | 2017-04-26 | 天脉聚源(北京)传媒科技有限公司 | Direct broadcast video obtaining method and device |
CN107105315A (en) * | 2017-05-11 | 2017-08-29 | 广州华多网络科技有限公司 | Live broadcasting method, the live broadcasting method of main broadcaster's client, main broadcaster's client and equipment |
CN107360442A (en) * | 2017-08-29 | 2017-11-17 | 广州华多网络科技有限公司 | A kind of live broadcasting method, device and electronic 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
- 2017-12-27 CN CN201711448937.5A patent/CN108171160B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020026512A1 (en) * | 2000-08-31 | 2002-02-28 | Sony Corporation | Content distribution notification method, reservation control apparatus and program storage medium |
US20140282200A1 (en) * | 2013-03-15 | 2014-09-18 | Mitel Networks Corporation | Method and system for automatically displaying information based on task context |
CN103475908A (en) * | 2013-07-23 | 2013-12-25 | 北京九华互联科技有限公司 | Multi-screen synchronization play method and device |
CN103763113A (en) * | 2013-12-31 | 2014-04-30 | 广州华多网络科技有限公司 | Live network broadcast method and device and server |
CN104168271A (en) * | 2014-08-01 | 2014-11-26 | 广州华多网络科技有限公司 | Interactive system, server, clients and interactive method |
US20160337426A1 (en) * | 2015-05-14 | 2016-11-17 | Hola Networks Ltd. | System and Method for Streaming Content from Multiple Servers |
CN105872640A (en) * | 2015-12-07 | 2016-08-17 | 乐视云计算有限公司 | Live broadcast video obtaining method, device and system |
CN106231349A (en) * | 2015-12-30 | 2016-12-14 | 深圳超多维科技有限公司 | Main broadcaster's class interaction platform server method for changing scenes and device, server |
CN105933738A (en) * | 2016-06-27 | 2016-09-07 | 徐文波 | Live video streaming method, device and system |
CN106303658A (en) * | 2016-08-19 | 2017-01-04 | 百度在线网络技术(北京)有限公司 | It is applied to exchange method and the device of net cast |
CN106604049A (en) * | 2016-12-19 | 2017-04-26 | 天脉聚源(北京)传媒科技有限公司 | Direct broadcast video obtaining method and device |
CN107105315A (en) * | 2017-05-11 | 2017-08-29 | 广州华多网络科技有限公司 | Live broadcasting method, the live broadcasting method of main broadcaster's client, main broadcaster's client 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 |
CN107360442A (en) * | 2017-08-29 | 2017-11-17 | 广州华多网络科技有限公司 | A kind of live broadcasting method, device and electronic equipment |
Non-Patent Citations (2)
Title |
---|
BESACIER L等: "Voice Biometrics over the Internet in the Framework of COST Action 275", 《EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING》 * |
吕凝: "基于内容的视频数据库多模式检索方法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109446349A (en) * | 2018-09-28 | 2019-03-08 | 传线网络科技(上海)有限公司 | The checking method and device of multimedia content |
CN109286822A (en) * | 2018-10-19 | 2019-01-29 | 广州虎牙科技有限公司 | Interactive approach, device, equipment and storage medium based on live video identification |
CN109561348A (en) * | 2018-12-27 | 2019-04-02 | 广州虎牙信息科技有限公司 | A kind of method for processing business based on live streaming, device, equipment and storage medium |
CN109561348B (en) * | 2018-12-27 | 2021-12-07 | 广州虎牙信息科技有限公司 | Service processing method, device, equipment and storage medium based on live broadcast |
CN112307299A (en) * | 2019-08-20 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information publishing method and device, computer equipment and storage medium |
CN111757131A (en) * | 2020-04-03 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Task target setting method, device and system applied to live broadcast and electronic equipment |
CN111757131B (en) * | 2020-04-03 | 2021-06-11 | 北京达佳互联信息技术有限公司 | Task target setting method, device and system applied to live broadcast and electronic equipment |
CN114245223A (en) * | 2022-01-27 | 2022-03-25 | 广州方硅信息技术有限公司 | Live broadcast room task loading method, system and device and computer equipment |
Also Published As
Publication number | Publication date |
---|---|
CN108171160B (en) | 2021-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108184144B (en) | Live broadcast method and device, storage medium and electronic equipment | |
CN108171160A (en) | A kind of task result recognition methods, device, storage medium and electronic equipment | |
Uricchio | The future of a medium once known as television | |
CN106210808B (en) | Media information put-on method, terminal, server and system | |
Creeber et al. | Digital culture: Understanding new media: Understanding new media | |
US20110113444A1 (en) | Index of video objects | |
US20130249948A1 (en) | Providing interactive travel content at a display device | |
US20130222371A1 (en) | Enhancing a sensory perception in a field of view of a real-time source within a display screen through augmented reality | |
US20130226758A1 (en) | Delivering aggregated social media with third party apis | |
US20190104325A1 (en) | Event streaming with added content and context | |
CN110139162A (en) | The sharing method and device of media content, storage medium, electronic device | |
CN108174272A (en) | Method, apparatus, storage medium and the electronic equipment that interactive information is shown in live streaming | |
CN108347653A (en) | A kind of interactive approach, device, equipment and storage medium | |
CN108347650A (en) | A kind of method, apparatus, storage medium and the electronic equipment of determining interactive result | |
CN104050353A (en) | Effectuating Modifications Within An Instance Of Virtual Space Responsive To Detection Of A Token | |
Tripp | From TVTV to YouTube: A genealogy of participatory practices in video | |
Crick | Power, Surveillance, and Culture in YouTube™'s Digital Sphere | |
CN109379639A (en) | Method for pushing and device, the electronic equipment of video content object | |
CN107077507A (en) | A kind of information-pushing method, device and system | |
Pardo | Digital Hollywood: How Internet and Social media are changing the movie business | |
Rich | Ultimate Guide to YouTube for Business | |
Oppermann et al. | Pervasive games | |
Barker | Social TV: Multi-screen content and ephemeral culture | |
CN113301362B (en) | Video element display method and device | |
Botev et al. | CollaTrEx–collaborative context-aware mobile training and exploration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |