CN113301376A - Live broadcast interaction mode and system based on virtual reality technology - Google Patents
Live broadcast interaction mode and system based on virtual reality technology Download PDFInfo
- Publication number
- CN113301376A CN113301376A CN202110567183.5A CN202110567183A CN113301376A CN 113301376 A CN113301376 A CN 113301376A CN 202110567183 A CN202110567183 A CN 202110567183A CN 113301376 A CN113301376 A CN 113301376A
- Authority
- CN
- China
- Prior art keywords
- bullet screen
- information
- classification
- result
- screen information
- 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
Images
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
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/485—End-user interface for client configuration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4884—Data services, e.g. news ticker for displaying subtitles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
本发明公开了一种基于虚拟现实技术的直播交互方式及系统，其中，所述方式应用于一信息中转平台，所述方式包括：根据信息处理平台收集第一直播间内的弹幕信息集合；根据大数据获得多个弹幕分类特征；根据多个弹幕分类特征对弹幕信息集合进行分类，并进行信息论编码运算，获得多个信息熵；根据多个信息熵，构建弹幕分类决策树；根据弹幕分类决策树，获得第一分类结果；构建自动回复特征库；判断第一分类结果中是否存在属于自动回复特征库的弹幕信息，若存在，则根据自动回复特征库对属于自动回复特征库的弹幕信息进行自动回复，解决了直播观众数量庞大时主播方无法全面且及时对弹幕信息进行反馈导致观众体验不佳的技术问题。
The invention discloses a live broadcast interaction method and system based on virtual reality technology, wherein the method is applied to an information transfer platform, and the method includes: collecting the bullet screen information set in the first live broadcast room according to the information processing platform; Obtain multiple bullet screen classification features according to the big data; classify the bullet screen information set according to the multiple bullet screen classification features, and perform information theory coding operations to obtain multiple information entropies; build the bullet screen classification decision tree according to the multiple information entropies ;According to the bullet screen classification decision tree, obtain the first classification result; build an automatic reply feature library; judge whether there is bullet screen information belonging to the automatic reply feature library in the first classification result, if so, according to the automatic reply feature library Reply to the bullet screen information in the feature database to automatically reply, which solves the technical problem that the broadcaster cannot comprehensively and timely feedback the bullet screen information when the number of live viewers is large, resulting in poor audience experience.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a live broadcast interaction mode and system based on a virtual reality technology.
Background
With the rapid development of internet technology in recent years, a lot of convenient and attractive network entertainment ways are derived. The network live broadcast is a new industry, absorbs and continues the advantages of the internet, carries out online live broadcast in a video mode, can release contents such as product display, related meetings, background introduction, scheme evaluation, online investigation, conversation interview, online training and the like to the internet on site, and enhances the popularization effect of an activity site by utilizing the characteristics of intuition, quickness, good expression form, rich contents, strong interactivity, unlimited region, divisible audience and the like of the internet. After the live broadcast is finished, the live broadcast can also continuously provide rebroadcast and on-demand for readers at any time, effectively prolongs the live broadcast time and space, and exerts the maximum value of the live broadcast content.
In the process of implementing the technical scheme of the invention in the embodiment of the present application, the inventor of the present application finds that the above-mentioned technology has at least the following technical problems:
the form of the network live broadcast limits the 'one-to-many' characteristic, namely, the number of people on one side of the live broadcast display is limited, and in most cases, the number of people is a main broadcast or a main broadcast team, and the number of audiences watching the live broadcast is not limited. In the prior art, communication interaction is often carried out between anchor and audience through barrage information sent by the audience, and when the cardinal number of the audience is huge, the number of barrages is increased greatly, the anchor party can neglect partial barrage information inevitably, and the watching messages of partial audience can not obtain the feedback of the anchor party, so that the impression of the audience can be indirectly influenced, the viscosity of the audience is reduced, and the live broadcast effect is influenced.
Disclosure of Invention
The embodiment of the application provides a live broadcast interactive mode and system based on virtual reality technology, the technical problem that in the prior art, when the number of live broadcast audiences is huge, the anchor can not feed back the barrage information comprehensively and timely, so that the audiences experience is not good is solved, the technical purpose of feeding back the barrage information timely is achieved by constructing an automatic reply feature library and intelligently replying the live broadcast barrage, the technical effects of improving the live broadcast impression and audience satisfaction are achieved, the audience viscosity is further improved, and the good development of the network live broadcast industry is guaranteed.
In view of the foregoing problems, embodiments of the present application provide a live broadcast interaction method and system based on a virtual reality technology.
In a first aspect, the present application provides a live broadcast interaction mode based on a virtual reality technology, wherein the mode is applied to an information transfer platform, and the mode includes: collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform; obtaining a plurality of bullet screen classification characteristics according to the big data; classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies; constructing a bullet screen classification decision tree according to the plurality of information entropies; obtaining a first classification result according to the bullet screen classification decision tree; constructing an automatic reply feature library; judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; and if the bullet screen information belonging to the automatic reply feature library exists in the first classification result, automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library.
On the other hand, this application still provides a live interactive system based on virtual reality technique, wherein, the system includes: the first collecting unit is used for collecting a barrage information set in a first direct broadcasting room according to the information processing platform; the first obtaining unit is used for obtaining a plurality of bullet screen classification features according to the big data; a second obtaining unit, configured to classify the bullet screen information set according to the multiple bullet screen classification features, and perform information theory coding operation to obtain multiple information entropies; the first construction unit is used for constructing a bullet screen classification decision tree according to the plurality of information entropies; a third obtaining unit, configured to obtain a first classification result according to the bullet screen classification decision tree; the second construction unit is used for constructing an automatic reply feature library; the first judging unit is used for judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; and the first execution unit is used for automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library when the bullet screen information belonging to the automatic reply feature library exists in the first classification result.
On the other hand, an embodiment of the present application further provides a live broadcast interaction system based on a virtual reality technology, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the embodiment of the application provides a live broadcast interaction mode based on a virtual reality technology, and a barrage information set in a first live broadcast room is collected according to an information processing platform; obtaining a plurality of bullet screen classification characteristics according to the big data; classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies; constructing a bullet screen classification decision tree according to the plurality of information entropies; obtaining a first classification result according to the bullet screen classification decision tree; constructing an automatic reply feature library; judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; if exist in the first classification result and belong to the bullet screen information of auto-response characteristic storehouse, according to auto-response characteristic storehouse is to belonging to the bullet screen information of auto-response characteristic storehouse carries out the auto-response, the technical problem that the broadcasters can't be comprehensive and in time feed back bullet screen information when having solved among the prior art live broadcast audience quantity huge and result in audience to experience the not good is replied, through constructing the auto-response characteristic storehouse and carry out intelligent reply to the live broadcast bullet screen, the technical purpose of in time feeding back bullet screen information has been reached, the technological effect of improving live broadcast impression and audience satisfaction has been realized, audience's stickness has further been improved, the good development of the network live broadcast trade has been ensured.
The foregoing is a summary of the present disclosure, and embodiments of the present disclosure are described below to make the technical means of the present disclosure more clearly understood.
Drawings
Fig. 1 is a schematic flow chart of a live broadcast interaction mode based on a virtual reality technology according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a live broadcast interaction system based on a virtual reality technology according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first collecting unit 11, a first obtaining unit, a second obtaining unit 13, a first constructing unit 14, a third obtaining unit 15, a second constructing unit 16, a first judging unit 17, a first executing unit 18, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.
Detailed Description
The embodiment of the application provides a live broadcast interactive mode and system based on virtual reality technology, the technical problem that in the prior art, when the number of live broadcast audiences is huge, the anchor can not feed back the barrage information comprehensively and timely, so that the audiences experience is not good is solved, the technical purpose of feeding back the barrage information timely is achieved by constructing an automatic reply feature library and intelligently replying the live broadcast barrage, the technical effects of improving the live broadcast impression and audience satisfaction are achieved, the audience viscosity is further improved, and the good development of the network live broadcast industry is guaranteed.
Hereinafter, example embodiments of the present application will be described in detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it is to be understood that the present application is not limited by the example embodiments described herein.
Summary of the application
With the rapid development of internet technology in recent years, a lot of convenient and attractive network entertainment ways are derived. The network live broadcast is a new industry, absorbs and continues the advantages of the internet, carries out online live broadcast in a video mode, can release contents such as product display, related meetings, background introduction, scheme evaluation, online investigation, conversation interview, online training and the like to the internet on site, and enhances the popularization effect of an activity site by utilizing the characteristics of intuition, quickness, good expression form, rich contents, strong interactivity, unlimited region, divisible audience and the like of the internet. After the live broadcast is finished, the live broadcast can also continuously provide rebroadcast and on-demand for readers at any time, effectively prolongs the live broadcast time and space, and exerts the maximum value of the live broadcast content. The form of the network live broadcast limits the 'one-to-many' characteristic, namely, the number of people on one side of the live broadcast display is limited, and in most cases, the number of people is a main broadcast or a main broadcast team, and the number of audiences watching the live broadcast is not limited. In the prior art, communication interaction is often carried out between anchor and audience through barrage information sent by the audience, and when the cardinal number of the audience is huge, the number of barrages is increased greatly, the anchor party can neglect partial barrage information inevitably, and the watching messages of partial audience can not obtain the feedback of the anchor party, so that the impression of the audience can be indirectly influenced, the viscosity of the audience is reduced, and the live broadcast effect is influenced.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the application provides a live broadcast interaction mode and system based on virtual reality technology, wherein, the mode is applied to an information transfer platform, the mode includes: collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform; obtaining a plurality of bullet screen classification characteristics according to the big data; classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies; constructing a bullet screen classification decision tree according to the plurality of information entropies; obtaining a first classification result according to the bullet screen classification decision tree; constructing an automatic reply feature library; judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; and if the bullet screen information belonging to the automatic reply feature library exists in the first classification result, automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a live broadcast interaction method based on a virtual reality technology, where the method includes:
step S100: collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform;
specifically, a bullet screen refers to a comment directly appearing on a video, which can appear on the video in a scrolling, staying or even more motion-specific manner, and is a brief comment sent by a person watching the video. In the live broadcast process of the network, the barrage has the characteristic of real-time performance, anyone can issue own opinions through barrage messages, and the anchor can answer questions and solve puzzles for audiences through the live broadcast barrage, so that the distance between the anchor and the audiences is shortened. The barrage information set in the first live broadcast room is all barrage messages sent by audiences in the live broadcast of the field, and the barrage information set comprises the evaluation of the audiences on the live broadcast, the suggestion on the anchor broadcast, the question in the live broadcast process and the like. The collection of barrage information is not limited to speech related to live broadcasting, and includes, for example, use of a viewer's headless speech and a web-cast. By obtaining the bullet screen information set, a foundation can be laid for realizing the comprehensive interaction between the anchor and the audience.
Step S200: obtaining a plurality of bullet screen classification characteristics according to the big data;
specifically, the bullet screen classification feature is a reference for classifying the live bullet screen, for example, the bullet screen may be classified according to whether the bullet screen information is related to the live content, or the bullet screen information may be subdivided according to the "bullet screen information is related to the live content". Through a plurality of bullet screen classification characteristics that obtain, can be divided into different categories with bullet screen information, concentrate the reply to it according to different categories bullet screen information, can improve reply efficiency, improve the comprehensiveness that the message replied.
Step S300: classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies;
step S400: constructing a bullet screen classification decision tree according to the plurality of information entropies;
specifically, the bullet screen information sets are classified through the bullet screen classification features, a statistical method is applied to obtain a common rule of information transmission and information processing in a communication system, information theory coding operation is performed, and a plurality of information entropies are obtained. The entropy of information, i.e., the expression of a quantitative measure of information, is used to describe the uncertainty of the source, and the greater the entropy of a data set, the higher the "purity" of the data classification. By obtaining a plurality of information entropies, a bullet screen classification decision tree can be constructed according to bullet screen classification conditions. Decision trees are common algorithms for machine learning, and are classified into classification trees, which are used when predicting the classification of a sample, and regression trees. The classification decision tree is to construct a tree-like classification decision model according to the training data set, and then use the model to assist decision making. The information gain is used as a basis for dividing the data set. The entropy of the whole data set is called original entropy, the entropy after the data set is divided according to a certain characteristic is conditional entropy, and the information gain is original entropy-conditional entropy. The specific method of dividing by using the information gain is as follows: and calculating the information gain corresponding to each type of feature, and then selecting the feature with the minimum information gain for division. The bullet screen information can be accurately divided by constructing the bullet screen classification decision tree, and accurate reply is facilitated.
Step S500: obtaining a first classification result according to the bullet screen classification decision tree;
specifically, the first classification result is obtained according to a bullet screen classification decision tree, and is a result of reasonably dividing the bullet screen information set based on bullet screen classification features, and an intelligent analysis result of the bullet screen information set based on big data. The first classification result can be used for classifying products promoted by a main broadcasting and can also be used for classifying the impression evaluation of the live broadcasting, and the classification condition of the bullet screen information set can be determined by obtaining the first classification result, so that the identification efficiency of the bullet screen information is improved, and the response speed of the bullet screen information is further accelerated.
Step S600: constructing an automatic reply feature library;
specifically, the automatic reply feature library is a set constructed by extracting key features from the first classification result, each feature in the automatic reply feature library has a corresponding automatic reply sentence, and it should be noted that, because the Chinese vocabulary has synonyms, that is, the meanings and effects expressed by different words are the same, the features and the automatic reply sentences are not in a one-to-one correspondence relationship, but a plurality of features can all correspond to one sentence of automatic reply sentences. By constructing the automatic reply feature library, the first classification result is associated with the automatic reply sentence, and accurate reply of the bullet screen message is facilitated.
Step S700: judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not;
step S800: and if the bullet screen information belonging to the automatic reply feature library exists in the first classification result, automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library.
Specifically, after a first classification result is obtained and an automatic reply feature library is constructed, whether bullet screen information belonging to the automatic reply feature library exists in the first classification result can be judged through the automatic reply feature library. If the bullet screen information belonging to the automatic reply feature library exists in the first classification result, the bullet screen information belonging to the automatic reply feature library can be directly and automatically replied according to the automatic reply feature library. Through feature recognition and information processing, the purpose of intelligently replying the bullet screen information is achieved, the technical problem that in the prior art, when the number of live broadcast audiences is huge, the anchor can not comprehensively and timely feed back the bullet screen information to cause the audiences to experience a poor experience is solved, the technical purpose of timely feeding back the bullet screen information is achieved, the technical effect of improving the live broadcast impression and the audience satisfaction is achieved, the audience viscosity is further improved, and the good development of the network live broadcast industry is guaranteed.
Further, step S400 in the embodiment of the present application further includes:
step S410: comparing the information entropy input values with a model to obtain first root node characteristic information;
step S420: and calculating the first root node characteristic information and the bullet screen information set based on a recursive algorithm to construct the bullet screen classification decision tree.
Specifically, the value size comparison model is used for comparing the value sizes of a plurality of information entropies, and the larger the information entropy is, the more reasonable the data classification is. The tree structure in the decision tree is a data structure with hierarchical relationships among elements, an inverted tree is often used to represent the logical relationship, and the root node is the topmost node of the tree. And infinitely calling a recursive function through a recursive algorithm to calculate the first root node characteristic information and the bullet screen information set. And calling and changing a key variable each time until the key variable reaches the boundary, and constructing the bullet screen classification decision tree through a result value after the recursion is finished. Based on the recursive algorithm, the method can achieve the effects of clear overall structure, strong readability and easy use of a mathematical induction method to prove the correctness of the algorithm, thereby bringing great convenience for designing the algorithm and debugging programs.
Further, step S500 in the embodiment of the present application further includes:
step S510: acquiring first bullet screen information, wherein the first bullet screen information belongs to the bullet screen information set;
step S520: and inputting the first bullet screen information into the bullet screen classification decision tree, classifying the bullet screen information set, and obtaining the first classification result.
Specifically, the process of classifying the bullet screens is performed one by one according to the number of the information, and the bullet screen information set is classified by obtaining first bullet screen information and inputting the first bullet screen information into the bullet screen classification decision tree. First bullet screen information belongs to bullet screen information set can be the bullet screen information of arbitrary content at any moment, and categorised result represents the content characteristic of first bullet screen information is categorised through this kind of mode with all bullet screen information, can obtain rather than the categorised result that corresponds, according to this categorised result, can match suitable answer sentence, is convenient for carry out intelligent answer.
Further, the embodiment of the present application further includes step S900, where step S900 includes:
step S910: obtaining node information according to the decision tree;
step S920: acquiring node functional characteristics according to the node information;
step S930: partitioning the human-computer interaction interface according to the node functional characteristics to obtain a first partitioning result;
step S940: performing feature matching according to the first classification result and the first partition result to obtain a first matching result;
step S950: and according to the first matching result, displaying the first classification result in a partition mode.
In particular, the decision tree analysis method has a limited application range, and when the data is too large or the data is updated too fast, the speed of the decision tree analysis is reduced and even hysteresis is shown. The nodes are branch points in the data structure tree, and different classes of data are introduced into corresponding classification sets through connection and distribution of the nodes. The node functional characteristics represent the designated characteristics of the data to be classified, and the human-computer interaction interface is partitioned through the node functional characteristics to obtain a first partition result. And performing feature matching on the first classification result and the first partition result to obtain a first matching result, wherein the first matching result is obtained by matching classification information of a human-computer interaction interface with a decision tree analysis result, and the purpose of reducing the workload of the decision tree is achieved. The process of partitioning the man-machine interaction interface is substantially the process of carrying out prepositive deployment on decision tree analysis, and the first partitioning result is obtained by partitioning the man-machine interaction interface, so that the workload of the decision tree can be effectively reduced, the working efficiency is improved, and the result of bullet screen information classification is more accurate.
Further, step S940 in the embodiment of the present application further includes:
step S941: obtaining a functional convolution comparison feature set according to the node functional features, wherein each functional convolution comparison feature in the functional convolution comparison features is matched with each partition in the first partition result;
step S942: performing characteristic traversal comparison on the bullet screen information of each category in the first classification result according to each functional convolution comparison characteristic in the functional convolution comparison characteristic set to obtain a first comparison result;
step S943: and matching each category in the first classification result with each partition in the first partition result according to the first comparison result to obtain a first matching result.
Specifically, the convolutional neural network is a deep feedforward neural network with the characteristics of local connection, weight sharing and the like, has a remarkable effect in the field of image and video analysis, such as various visual tasks of image classification, target detection, image segmentation and the like, and is one of the most widely applied models at present. A convolutional neural network, literally comprising two parts: convolution + neural network. The convolution is a feature extractor, and the neural network can be regarded as a classifier. A convolutional neural network is trained, namely a feature extractor (convolution) and a subsequent classifier (neural network) are trained simultaneously. And respectively performing characteristic traversal comparison on the bullet screen information of each category in the first classification result according to each functional convolution comparison characteristic in the functional convolution comparison characteristic set to obtain a corresponding first comparison result, and matching each category in the first classification result with each partition in the first partition result according to the first comparison result to obtain a first matching result. The first matching result is a result obtained after feature training by a convolutional neural network and is used for judging the coincidence degree of the first classification result and the first partition result.
Further, step S700 in the embodiment of the present application further includes:
step S710: if the bullet screen information belonging to the automatic reply feature library does not exist in the first classification result, a first reminding instruction is obtained, and the first reminding instruction is used for reminding a main broadcaster to reply the bullet screen information;
step S720: acquiring first reply information according to the first reminding information;
step S730: and after the first reply information is obtained, second reminding information is obtained, and the second reminding information is used for reminding the first fan of receiving the first reply information.
Specifically, the large number of viewers also leads to various bullet screen information, some viewers can present a novel problem, the first classification result does not include related features, the problem is not suitable for automatic reply, the anchor is reminded to pay attention and reply through the first reminding instruction, and the first reply information is content of the anchor which directly replies to the bullet screen sender through the live broadcast platform. In order to improve the watching experience of the audience, the audience is timely informed to check the reply information, after the first reply information is obtained, second reminding information is obtained, and the second reminding information is used for reminding the first fan to receive the first reply information. The mode through automatic reply and anchor direct reply combines together, has reached the effect that improves live barrage reply rate.
Further, step S730 in the embodiment of the present application further includes:
step S731: judging whether the first vermicelli is on-line or not;
step S732: and if the first fan is not on line, recording the first reply content to obtain a first recorded content, and sending the first recorded content to the first fan.
Specifically, the network is real-time, so that a viewer sometimes misses part of live broadcast content due to switching of a mobile phone interface and the like, the online condition of the first fan is judged in order to avoid the viewer missing the first reply information, when the first fan is in an offline state, the first reply content is recorded in time to obtain first recorded content, and the first recorded content is sent to the first fan, so that the first fan can receive the first reply information when the first fan is online next time. By tracking the online state of the first fan and timely sending the reply content, the first fan can be prevented from missing the content to be known, and the satisfaction degree of the audience is indirectly improved.
To sum up, the live broadcast interaction mode based on the virtual reality technology provided by the embodiment of the application has the following technical effects:
1. the embodiment of the application provides a live broadcast interaction mode based on a virtual reality technology, wherein the mode is applied to an information transfer platform, and the mode comprises the following steps: collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform; obtaining a plurality of bullet screen classification characteristics according to the big data; classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies; constructing a bullet screen classification decision tree according to the plurality of information entropies; obtaining a first classification result according to the bullet screen classification decision tree; constructing an automatic reply feature library; judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; if exist in the first classification result and belong to the bullet screen information of auto-response characteristic storehouse, according to auto-response characteristic storehouse is to belonging to the bullet screen information of auto-response characteristic storehouse carries out the auto-response, the technical problem that the broadcasters can't be comprehensive and in time feed back bullet screen information when having solved among the prior art live broadcast audience quantity huge and result in audience to experience the not good is replied, through constructing the auto-response characteristic storehouse and carry out intelligent reply to the live broadcast bullet screen, the technical purpose of in time feeding back bullet screen information has been reached, the technological effect of improving live broadcast impression and audience satisfaction has been realized, audience's stickness has further been improved, the good development of the network live broadcast trade has been ensured.
2. And performing feature traversal comparison on the bullet screen information of each category in the first classification result according to each function convolution comparison feature in the function convolution comparison feature set to obtain a first matching result, wherein the first matching result is a result obtained after feature training is performed on the bullet screen information through a convolutional neural network and is used for judging the matching degree of the first classification result and the first partition result. The first matching result is obtained by using a convolutional neural network, so that the matching accuracy of the first partition result and the first classification result is improved.
Example two
Based on the same inventive concept as the live broadcast interaction mode based on the virtual reality technology in the foregoing embodiment, the present invention further provides a live broadcast interaction system based on the virtual reality technology, as shown in fig. 2, the system includes:
the first collecting unit 11 is used for collecting a barrage information set in a first direct broadcasting room according to the information processing platform;
a first obtaining unit 12, where the first obtaining unit 12 is configured to obtain a plurality of bullet screen classification features according to big data;
a second obtaining unit 13, where the second obtaining unit 13 is configured to classify the bullet screen information set according to the multiple bullet screen classification features, and perform information theory coding operation to obtain multiple information entropies;
a first constructing unit 14, where the first constructing unit 14 is configured to construct a bullet screen classification decision tree according to the plurality of information entropies;
a third obtaining unit 15, where the third obtaining unit 15 is configured to obtain a first classification result according to the bullet screen classification decision tree;
a second building unit 16, wherein the second building unit 16 is used for building an automatic reply feature library;
a first judging unit 17, where the first judging unit 17 is configured to judge whether bullet screen information belonging to the automatic reply feature library exists in the first classification result;
a first executing unit 18, where the first executing unit 18 is configured to, when the bullet screen information belonging to the auto-answer feature library exists in the first classification result, automatically answer the bullet screen information belonging to the auto-answer feature library according to the auto-answer feature library.
Further, the system further comprises:
a fourth obtaining unit, configured to compare the information entropy input values with a model to obtain first root node feature information;
and the third construction unit is used for calculating the first root node characteristic information and the bullet screen information set based on a recursive algorithm to construct the bullet screen classification decision tree.
Further, the apparatus further comprises:
a fifth obtaining unit, configured to obtain first bullet screen information, where the first bullet screen information belongs to the bullet screen information set;
a sixth obtaining unit, configured to input the first barrage information into the barrage classification decision tree, classify the barrage information set, and obtain the first classification result.
Further, the apparatus further comprises:
a seventh obtaining unit, configured to obtain node information according to the decision tree;
an eighth obtaining unit, configured to obtain a node function characteristic according to the node information;
a ninth obtaining unit, configured to partition the human-computer interaction interface according to the node function characteristics, and obtain a first partition result;
a tenth obtaining unit, configured to perform feature matching according to the first classification result and the first partition result, and obtain a first matching result;
and the second execution unit is used for displaying the first classification result in a partitioning manner according to the first matching result.
Further, the apparatus further comprises:
an eleventh obtaining unit, configured to obtain a functional convolution comparison feature set according to the node functional features, where each functional convolution comparison feature in the functional convolution comparison features is matched with each partition in the first partition result;
a twelfth obtaining unit, configured to perform feature traversal comparison on the bullet screen information of each category in the first classification result according to each functional convolution comparison feature in the functional convolution comparison feature set, so as to obtain a first comparison result;
a thirteenth obtaining unit, configured to match, according to the first comparison result, each category in the first classification result with each partition in the first partition result, so as to obtain a first matching result.
Further, the apparatus further comprises:
a fourteenth obtaining unit, configured to obtain a first prompting instruction if the first classification result does not include the bullet screen information belonging to the auto-answer feature library, where the first prompting instruction is used to prompt a host to answer the bullet screen information;
a fifteenth obtaining unit, configured to obtain first reply information according to the first reminding information;
a sixteenth obtaining unit, configured to obtain second reminding information after obtaining the first reply information, where the second reminding information is used to remind a first fan of receiving the first reply information.
Further, the apparatus further comprises:
the second judging unit is used for judging whether the first vermicelli is online or not;
a seventeenth obtaining unit, configured to record the first reply content if the first fan is not online, obtain a first recorded content, and send the first recorded content to the first fan.
The virtual reality technology-based live broadcast interaction method and the specific example in the first embodiment of fig. 1 are also applicable to the virtual reality technology-based live broadcast interaction system in this embodiment, and through the foregoing detailed description of the virtual reality technology-based live broadcast interaction method, those skilled in the art can clearly know the virtual reality technology-based live broadcast interaction system in this embodiment, so for the sake of brevity of the description, detailed description is not given here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the live broadcast interaction mode based on the virtual reality technology in the foregoing embodiments, the present invention further provides a live broadcast interaction system based on the virtual reality technology, in which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods of the live broadcast interaction mode based on the virtual reality technology described above are implemented.
Where in fig. 3 a bus architecture (represented by bus 300) is shown, bus 300 may include any number of interconnected buses and bridges, with bus 300 connecting together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The application provides a live broadcast interaction mode based on virtual reality technology, wherein, the mode is applied to an information transfer platform, the mode includes: collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform; obtaining a plurality of bullet screen classification characteristics according to the big data; classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies; constructing a bullet screen classification decision tree according to the plurality of information entropies; obtaining a first classification result according to the bullet screen classification decision tree; constructing an automatic reply feature library; judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not; and if the bullet screen information belonging to the automatic reply feature library exists in the first classification result, automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A live broadcast interaction mode based on a virtual reality technology is applied to an information transfer platform, and the method comprises the following steps:
collecting a bullet screen information set in the first direct broadcasting room according to the information processing platform;
obtaining a plurality of bullet screen classification characteristics according to the big data;
classifying the bullet screen information set according to the bullet screen classification characteristics, and performing information theory coding operation to obtain a plurality of information entropies;
constructing a bullet screen classification decision tree according to the plurality of information entropies;
obtaining a first classification result according to the bullet screen classification decision tree;
constructing an automatic reply feature library;
judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not;
and if the bullet screen information belonging to the automatic reply feature library exists in the first classification result, automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library.
2. The method of claim 1, wherein constructing a bullet screen classification decision tree according to the plurality of information entropies comprises:
comparing the information entropy input values with a model to obtain first root node characteristic information;
and calculating the first root node characteristic information and the bullet screen information set based on a recursive algorithm to construct the bullet screen classification decision tree.
3. The method of claim 1, wherein the obtaining a first classification result from the bullet screen classification decision tree comprises:
acquiring first bullet screen information, wherein the first bullet screen information belongs to the bullet screen information set;
and inputting the first bullet screen information into the bullet screen classification decision tree, classifying the bullet screen information set, and obtaining the first classification result.
4. The method of claim 1, wherein the method comprises;
obtaining node information according to the decision tree;
acquiring node functional characteristics according to the node information;
partitioning the human-computer interaction interface according to the node functional characteristics to obtain a first partitioning result;
performing feature matching according to the first classification result and the first partition result to obtain a first matching result;
and according to the first matching result, displaying the first classification result in a partition mode.
5. The method of claim 4, wherein said performing feature matching according to the first classification result and the first partition result to obtain a first matching result comprises:
obtaining a functional convolution comparison feature set according to the node functional features, wherein each functional convolution comparison feature in the functional convolution comparison features is matched with each partition in the first partition result;
performing characteristic traversal comparison on the bullet screen information of each category in the first classification result according to each functional convolution comparison characteristic in the functional convolution comparison characteristic set to obtain a first comparison result;
and matching each category in the first classification result with each partition in the first partition result according to the first comparison result to obtain a first matching result.
6. The method of claim 1, wherein after determining whether the bullet screen information belonging to the auto-reply feature library exists in the first classification result, the method comprises:
if the bullet screen information belonging to the automatic reply feature library does not exist in the first classification result, a first reminding instruction is obtained, and the first reminding instruction is used for reminding a main broadcaster to reply the bullet screen information;
acquiring first reply information according to the first reminding information;
and after the first reply information is obtained, second reminding information is obtained, and the second reminding information is used for reminding the first fan of receiving the first reply information.
7. The method of claim 6, wherein obtaining the second reminder information comprises:
judging whether the first vermicelli is on-line or not;
and if the first fan is not on line, recording the first reply content to obtain a first recorded content, and sending the first recorded content to the first fan.
8. A live broadcast interactive system based on virtual reality technology, which is applied to the method of any one of claims 1-7, wherein the system comprises:
the first collecting unit is used for collecting a barrage information set in a first direct broadcasting room according to the information processing platform;
the first obtaining unit is used for obtaining a plurality of bullet screen classification features according to the big data;
a second obtaining unit, configured to classify the bullet screen information set according to the multiple bullet screen classification features, and perform information theory coding operation to obtain multiple information entropies;
the first construction unit is used for constructing a bullet screen classification decision tree according to the plurality of information entropies;
a third obtaining unit, configured to obtain a first classification result according to the bullet screen classification decision tree;
the second construction unit is used for constructing an automatic reply feature library;
the first judging unit is used for judging whether bullet screen information belonging to the automatic reply feature library exists in the first classification result or not;
and the first execution unit is used for automatically replying the bullet screen information belonging to the automatic reply feature library according to the automatic reply feature library when the bullet screen information belonging to the automatic reply feature library exists in the first classification result.
9. A live interactive system based on virtual reality technology, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567183.5A CN113301376B (en) | 2021-05-24 | 2021-05-24 | Live broadcast interaction method and system based on virtual reality technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567183.5A CN113301376B (en) | 2021-05-24 | 2021-05-24 | Live broadcast interaction method and system based on virtual reality technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113301376A true CN113301376A (en) | 2021-08-24 |
| CN113301376B CN113301376B (en) | 2023-04-07 |
Family
ID=77324455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567183.5A Expired - Fee Related CN113301376B (en) | 2021-05-24 | 2021-05-24 | Live broadcast interaction method and system based on virtual reality technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113301376B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113641937A (en) * | 2021-08-17 | 2021-11-12 | 杭州时趣信息技术有限公司 | Comment automatic reply method, system and storage medium |
| CN113923839A (en) * | 2021-10-19 | 2022-01-11 | 苏州爱果乐科技有限公司 | Light adjusting method and system |
| CN115515016A (en) * | 2022-11-04 | 2022-12-23 | 广东玄润数字信息科技股份有限公司 | Virtual live broadcast method, system and storage medium capable of realizing self-cross reply |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8744891B1 (en) * | 2007-07-26 | 2014-06-03 | United Services Automobile Association (Usaa) | Systems and methods for dynamic business decision making |
| CN105435453A (en) * | 2015-12-22 | 2016-03-30 | 网易（杭州）网络有限公司 | Bullet screen information processing method, device and system |
| CN107608964A (en) * | 2017-09-13 | 2018-01-19 | 上海六界信息技术有限公司 | Screening technique, device, equipment and the storage medium of live content based on barrage |
| CN108536787A (en) * | 2018-03-29 | 2018-09-14 | 优酷网络技术（北京）有限公司 | content identification method and device |
| US20200044996A1 (en) * | 2014-05-06 | 2020-02-06 | Google Inc. | Automatic identification and extraction of sub-conversations within a live chat session |
| US20200184339A1 (en) * | 2018-12-10 | 2020-06-11 | Baidu Usa Llc | Representation learning for input classification via topic sparse autoencoder and entity embedding |
| CN111460221A (en) * | 2020-06-17 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Comment information processing method and device and electronic equipment |
| CN112165639A (en) * | 2020-09-23 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Content distribution method, content distribution device, electronic equipment and storage medium |
| WO2021036876A1 (en) * | 2019-08-30 | 2021-03-04 | 北京字节跳动网络技术有限公司 | Method and device for providing live stream auxiliary data, apparatus, and readable medium |
| CN112765336A (en) * | 2021-01-29 | 2021-05-07 | 中国平安人寿保险股份有限公司 | Bullet screen management method and device, terminal equipment and storage medium |
-
2021
- 2021-05-24 CN CN202110567183.5A patent/CN113301376B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8744891B1 (en) * | 2007-07-26 | 2014-06-03 | United Services Automobile Association (Usaa) | Systems and methods for dynamic business decision making |
| US20200044996A1 (en) * | 2014-05-06 | 2020-02-06 | Google Inc. | Automatic identification and extraction of sub-conversations within a live chat session |
| CN105435453A (en) * | 2015-12-22 | 2016-03-30 | 网易（杭州）网络有限公司 | Bullet screen information processing method, device and system |
| CN107608964A (en) * | 2017-09-13 | 2018-01-19 | 上海六界信息技术有限公司 | Screening technique, device, equipment and the storage medium of live content based on barrage |
| CN108536787A (en) * | 2018-03-29 | 2018-09-14 | 优酷网络技术（北京）有限公司 | content identification method and device |
| US20200184339A1 (en) * | 2018-12-10 | 2020-06-11 | Baidu Usa Llc | Representation learning for input classification via topic sparse autoencoder and entity embedding |
| WO2021036876A1 (en) * | 2019-08-30 | 2021-03-04 | 北京字节跳动网络技术有限公司 | Method and device for providing live stream auxiliary data, apparatus, and readable medium |
| CN111460221A (en) * | 2020-06-17 | 2020-07-28 | 腾讯科技（深圳）有限公司 | Comment information processing method and device and electronic equipment |
| CN112165639A (en) * | 2020-09-23 | 2021-01-01 | 腾讯科技（深圳）有限公司 | Content distribution method, content distribution device, electronic equipment and storage medium |
| CN112765336A (en) * | 2021-01-29 | 2021-05-07 | 中国平安人寿保险股份有限公司 | Bullet screen management method and device, terminal equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113641937A (en) * | 2021-08-17 | 2021-11-12 | 杭州时趣信息技术有限公司 | Comment automatic reply method, system and storage medium |
| CN113923839A (en) * | 2021-10-19 | 2022-01-11 | 苏州爱果乐科技有限公司 | Light adjusting method and system |
| CN115515016A (en) * | 2022-11-04 | 2022-12-23 | 广东玄润数字信息科技股份有限公司 | Virtual live broadcast method, system and storage medium capable of realizing self-cross reply |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113301376B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291266B (en) | Artificial intelligence based recommendation method and device, electronic equipment and storage medium | |
| CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
| CN111597446A (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| CN113010702A (en) | Interactive processing method and device for multimedia information, electronic equipment and storage medium | |
| CN113301376A (en) | Live broadcast interaction mode and system based on virtual reality technology | |
| CN114330752B (en) | Sorting model training methods and sorting methods | |
| CN109271509B (en) | Method, apparatus, computer equipment and storage medium for generating topic in live room | |
| CN113988954A (en) | Financing product marketing method and device | |
| CN112163614A (en) | Anchor classification method and device, electronic equipment and storage medium | |
| CN110929169A (en) | Job recommendation method based on improved Canopy clustering collaborative filtering algorithm | |
| CN117216362A (en) | Content recommends methods, apparatus, equipment, media and program products | |
| CN118349812A (en) | Model determination method, apparatus, device, storage medium, and program product | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| CN117574883A (en) | Text processing method and related equipment | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| CN116150470A (en) | Content recommendation method, device, equipment, storage medium and program product | |
| CN113741930A (en) | Application upgrading method and device, electronic equipment and computer readable storage medium | |
| CN111899728B (en) | Training method and device for intelligent voice assistant decision strategy | |
| CN111597361B (en) | Multimedia data processing method, device, storage medium and equipment | |
| CN117998151B (en) | Method and system for automatically generating integrated media questionnaire based on sentiment analysis | |
| CN118568297B (en) | Construction method and application of cognitive warfare system based on Wensheng video | |
| CN115713539A (en) | Image processing method, device, equipment and computer readable storage medium | |
| CN119357479A (en) | Digital works display method based on the combination of artificial intelligence and mixed reality technology | |
| CN111954017A (en) | Live broadcast room searching method and device, server and storage medium | |
| CN117473148A (en) | Content pushing method, device, electronic equipment, storage medium and program product |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230407 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |