CN113873274A - Live broadcast heat prediction method, device, equipment and storage medium - Google Patents
Live broadcast heat prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113873274A CN113873274A CN202111058592.9A CN202111058592A CN113873274A CN 113873274 A CN113873274 A CN 113873274A CN 202111058592 A CN202111058592 A CN 202111058592A CN 113873274 A CN113873274 A CN 113873274A
- Authority
- CN
- China
- Prior art keywords
- live broadcast
- historical
- heat
- target
- 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.)
- Withdrawn
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- 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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Fuzzy Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of big data, and discloses a live broadcast heat prediction method, a live broadcast heat prediction device, live broadcast heat prediction equipment and a storage medium, wherein the method comprises the following steps: extracting identification information of room parameters of a target live broadcast room; searching for historical user activity, historical bullet screen information and historical appreciation information on the big data platform according to the identification information; calculating the historical user activity, the historical bullet screen information and the historical appreciation information by a preset LDA algorithm to obtain a historical live broadcast heat time sequence; training a historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model; predicting current live broadcast information through a target DTPM prediction model to obtain corresponding live broadcast heat so as to realize prediction of target live broadcast room heat; compared with the prior art that the live broadcast heat is determined only through single gifts and flow support, the accuracy of predicting the live broadcast heat can be effectively improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a live broadcast heat prediction method, a live broadcast heat prediction device, live broadcast heat prediction equipment and a storage medium.
Background
With the rapid development of the live broadcast industry, a batch of high-quality live broadcast platforms emerge, each anchor can show talent bloom, transfer positive energy, debasing and help farmers and the like to audiences through the high-quality live broadcast platforms, in order to increase the enthusiasm of live broadcast of each anchor, the platform recommends a series of recommendation activities, the recommendation standard is based on the heat degree of a live broadcast room, and the recommendation position is planned in advance, namely the recommendation position is more likely to be set up when the heat degree of the live broadcast room is higher, therefore, the heat degree of the live broadcast room is important for the anchor and is related to die cutting of a bullet screen, the number of people, gifts and the like of the live broadcast room, in order to facilitate prediction of the heat degree, the currently common live broadcast room heat prediction mode is measured by paying gifts, namely the higher the amount of the paying gifts, the higher the heat degree of the live broadcast room is, but the paying gifts are only one side of heat prediction, if the heat degree is directly predicted by the paying gifts, resulting in a lower accuracy of the predicted live broadcast heat.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a live broadcast heat prediction method, a live broadcast heat prediction device, live broadcast heat prediction equipment and a storage medium, and aims to solve the technical problem that the accuracy of live broadcast heat prediction in the prior art is low.
In order to achieve the purpose, the invention provides a live broadcast heat prediction method, which comprises the following steps:
acquiring room parameters of a target live broadcast room, and extracting identification information of the room parameters;
searching for historical user activity, historical bullet screen information and historical appreciation information on a big data platform according to the identification information;
calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence;
training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model;
and predicting the current live broadcast information through the target DTPM prediction model to obtain the corresponding live broadcast heat so as to realize prediction of the heat of the live broadcast room.
Optionally, the calculating the historical user activity, the historical bullet screen information and the historical appreciation information by using a preset LDA algorithm to obtain a historical live broadcast heat time sequence includes:
determining corresponding historical interaction information according to the historical user activity and the historical bullet screen information;
acquiring online nobility, user riding and live broadcast guard in a target live broadcast room;
determining corresponding heat addition information according to the historical reward information, the online nobility, the user ride and the live broadcast daemon;
and calculating the historical interaction information and the heat addition information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
Optionally, the determining, according to the historical user activity and the historical bullet screen information, corresponding historical interaction information includes:
extracting the historical active number and the target online number of the historical user activity;
obtaining the average online number within a preset time according to the historical active number and the target online number;
extracting the bullet screen speech number and the bullet screen speech number of the historical bullet screen information;
obtaining the average bullet screen number within a preset time according to the bullet screen speech number and the bullet screen speech number;
and determining corresponding historical interaction information according to the average online number of people and the average bullet screen number.
Optionally, the training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model includes:
performing discrete decomposition on the historical live broadcast heat time sequence according to a target EEMD strategy to obtain the historical live broadcast heat of each time sequence;
dividing the historical live broadcast heat of each time sequence into a first test set and a second test set;
training a preset neural network model through the first test set and the second test set respectively to obtain a hidden layer output matrix and a connection weight;
and constructing a target DTPM prediction model according to the hidden layer output matrix and the connection weight.
Optionally, the predicting current live broadcast information by the target DTPM prediction model further includes, before obtaining the corresponding live broadcast heat:
acquiring the live broadcast days and live broadcast duration of each day of a target live broadcast room;
inquiring in a preset live broadcast platform according to the live broadcast days and the identification information to obtain target live broadcast days;
calculating the target live broadcast days and live broadcast time of each day to obtain the total target live broadcast time;
and obtaining the basic heat of the target live broadcast room according to the target live broadcast total duration, and executing the step of predicting the current live broadcast information through the target DTPM prediction model based on the basic heat to obtain the corresponding live broadcast heat.
Optionally, the predicting current live broadcast information by the target DTPM prediction model to obtain a corresponding live broadcast heat includes:
extracting live broadcast content, online number of people, watching duration and current barrage information of the current live broadcast information;
determining the corresponding people retention rate according to the online people number and the watching duration;
determining a corresponding bullet screen label according to the live broadcast content and the current bullet screen information;
and predicting the current live broadcast information through the target DTPM prediction model, the number retention rate and the bullet screen label to obtain the corresponding live broadcast heat.
Optionally, the predicting current live broadcast information through the target DTPM prediction model and the people remaining rate to obtain a corresponding live broadcast heat includes:
predicting the current live broadcast information through the target DTPM prediction model and the people number retention rate to obtain the current live broadcast heat;
and obtaining the corresponding live broadcast heat according to the current live broadcast heat and the basic heat.
In addition, to achieve the above object, the present invention further provides a live broadcast popularity prediction apparatus, including:
the extraction module is used for acquiring room parameters of a target live broadcast room and extracting identification information of the room parameters;
the searching module is used for searching the historical user liveness, the historical bullet screen information and the historical appreciation information on the big data platform according to the identification information;
the calculation module is used for calculating the historical user activity, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence;
the training module is used for training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model;
and the prediction module is used for predicting the current live broadcast information through the target DTPM prediction model to obtain the corresponding live broadcast heat so as to realize prediction of the heat of the live broadcast room.
In addition, in order to achieve the above object, the present invention further provides a live broadcast popularity prediction apparatus, including: a memory, a processor, and a live heat prediction program stored on the memory and executable on the processor, the live heat prediction program configured to implement a live heat prediction method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having a live broadcast popularity prediction program stored thereon, where the live broadcast popularity prediction program, when executed by a processor, implements the live broadcast popularity prediction method as described above.
According to the live broadcast heat prediction method provided by the invention, the identification information of the room parameters is extracted by acquiring the room parameters of a target live broadcast room; searching for historical user activity, historical bullet screen information and historical appreciation information on a big data platform according to the identification information; calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence; training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model; predicting the current live broadcast information through the target DTPM prediction model to obtain corresponding live broadcast heat so as to realize prediction of the heat of a live broadcast room; compared with the prior art that the live broadcast heat is determined only through single gifts and flow support, the accuracy of predicting the live broadcast heat can be effectively improved.
Drawings
Fig. 1 is a schematic structural diagram of a live broadcast heat prediction device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a live broadcast popularity prediction method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a live broadcast popularity prediction method according to a second embodiment of the present invention;
FIG. 4 is a flowchart illustrating a live broadcast popularity prediction method according to a third embodiment of the present invention;
fig. 5 is a functional block diagram of a live broadcast heat prediction apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a live broadcast heat prediction device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the live popularity prediction apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the live heat prediction apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a live heat prediction program.
In the live popularity prediction apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the live broadcast heat prediction device of the present invention may be arranged in the live broadcast heat prediction device, and the live broadcast heat prediction device calls the live broadcast heat prediction program stored in the memory 1005 through the processor 1001 and executes the live broadcast heat prediction method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the live broadcast heat prediction method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a live broadcast heat prediction method according to a first embodiment of the present invention.
In a first embodiment, the live broadcast popularity prediction method includes the following steps:
and step S10, acquiring room parameters of the target live broadcast room, and extracting identification information of the room parameters.
It should be noted that, the execution subject of this embodiment is a live broadcast popularity prediction device, and may also be other devices that can implement the same or similar functions, such as a live broadcast popularity prediction platform.
It should be understood that the room parameter may be a parameter of a room corresponding to the target live broadcast room, the room parameter may be any parameter of the target live broadcast room, including definition, line, room number, live broadcast link, and the like when the room is live broadcast, and the identification information is identification information capable of uniquely identifying the target live broadcast room, the target live broadcast room may be directly searched on the network live broadcast platform through the identification information, the identification information may be a room number of the target live broadcast room, and may also be other identification information.
In the specific implementation, the live broadcast heat prediction platform acquires room parameters of a target live broadcast room, and extracts identification information capable of uniquely identifying the target live broadcast room from the room parameters.
And step S20, searching the historical user liveness, the historical bullet screen information and the historical appreciation information on the big data platform according to the identification information.
It should be understood that the historical user activity may be activity of the user in the target live broadcast room, specifically, frequency of the user entering the target live broadcast room when logging in the account and duration of the user staying in the target live broadcast room, the historical barrage information may be all barrage information sent by the user in the target live broadcast room, including the number of barrages, the quality of barrages, the frequency of barrages, and the like, and the historical reward information may be gift information sent by the user in the target live broadcast room, including the number of gifts, the value of gifts, and the like.
It can be understood that after the identification information is obtained, the historical user liveness, the historical bullet screen information, and the historical reward information corresponding to the identification information are obtained by searching in the big data platform through the identification information, and the big data platform may be a live broadcast data query platform in the whole network, or may be other big data platforms, which is not limited in this embodiment.
And step S30, calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
It should be understood that the preset LDA algorithm may be an algorithm for calculating a heat time sequence, before calculation, the preset LDA algorithm needs to define a calculation strategy that better conforms to an actual heat time sequence, and the preset LDA algorithm is used to calculate the historical user liveness, the historical bullet screen information and the historical appreciation information to obtain a historical live broadcast heat time sequence, and the historical live broadcast heat time sequence may be a sequence in which heat values are arranged according to the time sequence of occurrence of the heat values.
In the specific implementation, after obtaining the historical user activity, the historical bullet screen information and the historical appreciation information, the live broadcast heat prediction platform respectively obtains a plurality of distribution parameters of the activity of the historical user relative to the heat of the target live broadcast room, a plurality of distribution parameters of the historical bullet screen information relative to the heat of the target live broadcast room and a plurality of distribution parameters of the historical appreciation information relative to the heat of the target live broadcast room, and calculates the plurality of distribution parameters of the historical user activity, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
And step S40, training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model.
It can be understood that the target EEMD strategy can be a strategy for decomposing and training a historical live broadcast time sequence, the historical live broadcast heat time sequence is decomposed through the target EEMD strategy, after decomposition is finished, the decomposed historical live broadcast heat time sequence is trained through a preset neural network model, and a target DTPM prediction model is obtained, wherein the target DTPM prediction model is an optimal prediction model obtained based on training of the historical live broadcast heat time sequence.
In order to improve the accuracy of predicting the heat of the live broadcast room, it is necessary to determine an optimal prediction model according to the historical live broadcast heat time sequence, and predict the heat of the live broadcast room based on the optimal prediction model, and further, step S40 includes: performing discrete decomposition on the historical live broadcast heat time sequence according to a target EEMD strategy to obtain the historical live broadcast heat of each time sequence; dividing the historical live broadcast heat of each time sequence into a first test set and a second test set; training a preset neural network model through the first test set and the second test set respectively to obtain a hidden layer output matrix and a connection weight; and constructing a target DTPM prediction model according to the hidden layer output matrix and the connection weight.
It should be understood that the first test set and the second test set are used as training sets to perform model training, specifically, 1/N of the historical live broadcast heat of each time sequence is used as the first test set, the rest is used as the second test set, N is a positive integer greater than 1, this embodiment does not limit this, N is 2 as an example, the first test set is trained through a preset neural network model to obtain a hidden layer output matrix, the second test set is trained through the preset neural network model to obtain a connection weight, and a target DTPM prediction model can be constructed according to the hidden layer output matrix and the connection weight.
It can be understood that after obtaining the target DTPM prediction model, the target DTPM prediction model needs to be detected, specifically, by Mean Absolute Percentage Error (MAPE), which specifically is:
where MAPE is the mean absolute percent error, xiFor the historical live broadcast heat of each time series,
in order to predict the heat of live broadcast,
and step S50, predicting the current live broadcast information through the target DTPM prediction model to obtain the corresponding live broadcast heat so as to realize prediction of the heat of the live broadcast room.
It should be understood that the current live broadcast information may be live broadcast information of a main broadcast in a target live broadcast room, including live broadcast content, current barrage information, online number of people, and the like, and after the target DTPM prediction model is obtained, the current live broadcast information is predicted through the target DTPM prediction model, so that the live broadcast heat of the target live broadcast room can be obtained.
In the embodiment, identification information of the room parameters is extracted by acquiring the room parameters of a target live broadcast room; searching for historical user activity, historical bullet screen information and historical appreciation information on a big data platform according to the identification information; calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence; training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model; predicting the current live broadcast information through the target DTPM prediction model to obtain corresponding live broadcast heat so as to realize prediction of the heat of a live broadcast room; compared with the prior art that the live broadcast heat is determined only through single gifts and flow support, the accuracy of predicting the live broadcast heat can be effectively improved.
In an embodiment, as shown in fig. 3, a second embodiment of the live broadcast popularity prediction method according to the present invention is provided based on the first embodiment, and the step S30 includes:
and S301, determining corresponding historical interaction information according to the historical user activity and the historical bullet screen information.
It should be understood that the historical interaction information can be information for interaction between a user and a main broadcast, the historical interaction information is divided into user activity and historical bullet screen information, the interaction of the user activity is represented by reminding when the user enters a target live broadcast room, the interaction of the historical bullet screen information is represented by characters sent by the user in the target live broadcast room, and the historical interaction information between the main broadcast and the user in the target live broadcast room is determined according to the historical user activity and the historical bullet screen information.
In order to effectively improve the accuracy of determining the historical interaction information, step S301 further includes: extracting the historical active number and the target online number of the historical user activity; obtaining the average online number within a preset time according to the historical active number and the target online number; extracting the bullet screen speech number and the bullet screen speech number of the historical bullet screen information; obtaining the average bullet screen number within a preset time according to the bullet screen speech number and the bullet screen speech number; and determining corresponding historical interaction information according to the average online number of people and the average bullet screen number.
In specific implementation, the target online number can be the highest number of users entering a target live broadcast room, an average online number within a preset time is obtained according to the target online number and the historical active number, the preset time period can be the total time length of the live broadcast of the target live broadcast room, or can be a partial time period in the total time length, similarly, the average bullet screen number within the preset time is determined according to the bullet screen speech number and the bullet screen speech number, and the historical interaction information of the main broadcast in the target live broadcast room is determined according to the average online number and the average bullet screen number.
Step S302, obtaining online nobility, user riding and live broadcast guard in a target live broadcast room.
It can be understood that online nobility, user riding and live broadcast guard can be achievements of users in a target live broadcast room, online nobility can be noble authority opened by the users in the target live broadcast room, nobility levels set by different network live broadcast platforms are different, the user riding can be exclusive riding of the users in the target live broadcast room, after the user having the riding, the user can enter the live broadcast room together with the riding after entering the field, and the live broadcast guard can be obtained by checking the user in the target live broadcast room for preset days, namely, the live broadcast guard vermicelli in the target live broadcast room is formed.
And step S303, determining corresponding heat addition information according to the historical reward information, the online nobility, the user ride and the live broadcast daemon.
It should be understood that since the history appreciation information, the online nobility, the user ride and the live broadcast guard all affect the heat of the target live broadcast room, the heat is the addition heat of the target live broadcast room, the heat of the target live broadcast room is composed of the basic heat and the heat addition, and the heat addition of the target live broadcast room is obtained according to the history appreciation information, the online nobility, the user ride and the live broadcast guard.
And step S304, calculating the historical interaction information and the heat addition information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
It can be understood that after the historical interaction information and the heat addition information are obtained, the historical interaction information and the heat addition information are calculated through a preset LDA algorithm, and a historical live broadcast heat time sequence is obtained.
In the embodiment, corresponding historical interaction information is determined according to the historical user activity and the historical bullet screen information; acquiring online nobility, user riding and live broadcast guard in a target live broadcast room; determining corresponding heat addition information according to the historical reward information, the online nobility, the user ride and the live broadcast daemon; calculating the historical interaction information and the heat addition information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence; according to the embodiment, the heat addition information is obtained through historical reward information, online nobility, user riding and live broadcast guard, corresponding historical interaction information is determined according to historical user liveness and historical bullet screen information, and the historical interaction information and the heat addition information are calculated based on the preset LDA algorithm to obtain the historical live broadcast heat time sequence, so that the accuracy of obtaining the historical live broadcast heat time sequence can be effectively improved.
In an embodiment, as shown in fig. 4, a third embodiment of the live broadcast popularity prediction method according to the present invention is provided based on the first embodiment, and the step S50 includes:
step S501, extracting the live broadcast content, the online number of people, the watching time and the current barrage information of the current live broadcast information.
It can be understood that the live broadcast content can be live broadcast content of a main broadcast in a target live broadcast room, the live broadcast content can be talent and talent, popular science chat, debeaval and agriculture assistance and other content, the number of online people is the number of users entering the target live broadcast room, the watching duration can be the time when the users enter the target live broadcast room to watch the live broadcast content, and the current barrage information can be barrage information sent by the users in the target live broadcast room.
In order to effectively improve the accuracy of predicting the hotness of the live broadcast room, before step S501, the method further includes: acquiring the live broadcast days and live broadcast duration of each day of a target live broadcast room; inquiring in a preset live broadcast platform according to the live broadcast days and the identification information to obtain target live broadcast days; calculating the target live broadcast days and live broadcast time of each day to obtain the total target live broadcast time; and obtaining the basic heat of the target live broadcast room according to the target live broadcast total duration, and executing the step of predicting the current live broadcast information through the target DTPM prediction model based on the basic heat to obtain the corresponding live broadcast heat.
It should be understood that the target live broadcast total duration is obtained according to the live broadcast days of the target live broadcast room and the live broadcast duration of each day, the corresponding heat is inquired in the duration and heat relation mapping table according to the target live broadcast total duration, and the heat at this time is the basic heat of the target live broadcast room, namely the live broadcast heat of the target live broadcast room in a state without audiences and gifts.
And step S502, determining the corresponding people number retention rate according to the online people number and the watching duration.
It can be understood that the number retention rate can be a probability that the user stays in the target live broadcast room, and the probability that the user stays is determined according to the number of online users and the watching time length, for example, the number of online users is a, the number of users whose watching time length does not reach the preset time length is B, and the number retention rate at this time is (a-B)/B.
And S503, determining a corresponding bullet screen label according to the live broadcast content and the current bullet screen information.
It should be understood that after the live content and the current barrage information are obtained, the barrage label of the target live room is determined according to the live content and the current barrage information, for example, the live content of the target live room is music, the current barrage information is lyrics, tones and an evaluation of the live content, and then the barrage label at this time is # lyrics, # live content evaluation and so on.
And S504, predicting the current live broadcast information through the target DTPM prediction model, the number retention rate and the bullet screen label to obtain the corresponding live broadcast heat.
It can be understood that after the number retention rate and the bullet screen label are obtained, the current live broadcast information is predicted through the target DTPM prediction model, specifically:
wherein the content of the first and second substances,
the amplification factor is set for the live broadcast heat of the target live broadcast room rho and DtIs a bullet screen label theta in a current window t in a target live broadcast roomd,jThe retention rate of the number of people in the jth window in the d-th time period,
is the heat weight of the bullet screen label.
Further, after step S504, the method further includes: predicting the current live broadcast information through the target DTPM prediction model and the people number retention rate to obtain the current live broadcast heat; and obtaining the corresponding live broadcast heat according to the current live broadcast heat and the basic heat.
It should be understood that the live broadcast heat of the target live broadcast room is composed of the current live broadcast heat and the basic heat, and the current live broadcast heat is obtained by predicting the current live broadcast information through the target DTPM prediction model and the people remaining rate, for example, the current live broadcast heat is C, the basic heat is D, and the live broadcast heat of the target live broadcast room is C + D.
In the embodiment, live broadcast content, online number of people, watching duration and current barrage information of the current live broadcast information are extracted; determining the corresponding people retention rate according to the online people number and the watching duration; determining a corresponding bullet screen label according to the live broadcast content and the current bullet screen information; predicting the current live broadcast information through the target DTPM prediction model, the number retention rate and the bullet screen label to obtain corresponding live broadcast heat; because this embodiment is through live content, online number, watch length and the current barrage information confirm corresponding number retention rate and barrage label, based on number retention rate and barrage label predict current live information through target DTPM prediction model, obtain corresponding live broadcast heat to can effectively improve the rate of accuracy that obtains the live broadcast heat in the target live broadcast room.
In addition, an embodiment of the present invention further provides a storage medium, where a live broadcast popularity prediction program is stored on the storage medium, and when being executed by a processor, the live broadcast popularity prediction program implements the steps of the live broadcast popularity prediction method described above.
Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.
In addition, referring to fig. 5, an embodiment of the present invention further provides a live broadcast popularity prediction apparatus, where the live broadcast popularity prediction apparatus includes:
the extraction module 10 is configured to acquire room parameters of a target live broadcast room, and extract identification information of the room parameters.
It should be understood that the room parameter may be a parameter of a room corresponding to the target live broadcast room, the room parameter may be any parameter of the target live broadcast room, including definition, line, room number, live broadcast link, and the like when the room is live broadcast, and the identification information is identification information capable of uniquely identifying the target live broadcast room, the target live broadcast room may be directly searched on the network live broadcast platform through the identification information, the identification information may be a room number of the target live broadcast room, and may also be other identification information.
In the specific implementation, the live broadcast heat prediction platform acquires room parameters of a target live broadcast room, and extracts identification information capable of uniquely identifying the target live broadcast room from the room parameters.
And the searching module 20 is configured to search the historical user liveness, the historical bullet screen information and the historical reward information on the big data platform according to the identification information.
It should be understood that the historical user activity may be activity of the user in the target live broadcast room, specifically, frequency of the user entering the target live broadcast room when logging in the account and duration of the user staying in the target live broadcast room, the historical barrage information may be all barrage information sent by the user in the target live broadcast room, including the number of barrages, the quality of barrages, the frequency of barrages, and the like, and the historical reward information may be gift information sent by the user in the target live broadcast room, including the number of gifts, the value of gifts, and the like.
It can be understood that after the identification information is obtained, the historical user liveness, the historical bullet screen information, and the historical reward information corresponding to the identification information are obtained by searching in the big data platform through the identification information, and the big data platform may be a live broadcast data query platform in the whole network, or may be other big data platforms, which is not limited in this embodiment.
And the calculating module 30 is configured to calculate the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
It should be understood that the preset LDA algorithm may be an algorithm for calculating a heat time sequence, before calculation, the preset LDA algorithm needs to define a calculation strategy that better conforms to an actual heat time sequence, and the preset LDA algorithm is used to calculate the historical user liveness, the historical bullet screen information and the historical appreciation information to obtain a historical live broadcast heat time sequence, and the historical live broadcast heat time sequence may be a sequence in which heat values are arranged according to the time sequence of occurrence of the heat values.
In the specific implementation, after obtaining the historical user activity, the historical bullet screen information and the historical appreciation information, the live broadcast heat prediction platform respectively obtains a plurality of distribution parameters of the activity of the historical user relative to the heat of the target live broadcast room, a plurality of distribution parameters of the historical bullet screen information relative to the heat of the target live broadcast room and a plurality of distribution parameters of the historical appreciation information relative to the heat of the target live broadcast room, and calculates the plurality of distribution parameters of the historical user activity, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
And the training module 40 is used for training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model.
It can be understood that the target EEMD strategy can be a strategy for decomposing and training a historical live broadcast time sequence, the historical live broadcast heat time sequence is decomposed through the target EEMD strategy, after decomposition is finished, the decomposed historical live broadcast heat time sequence is trained through a preset neural network model, and a target DTPM prediction model is obtained, wherein the target DTPM prediction model is an optimal prediction model obtained based on training of the historical live broadcast heat time sequence.
In order to improve the accuracy of predicting the heat of the live broadcast room, an optimal prediction model needs to be determined according to a historical live broadcast heat time sequence, the heat of the live broadcast room is predicted based on the optimal prediction model, and further, the training module 40 is further used for performing discrete decomposition on the historical live broadcast heat time sequence according to a target EEMD strategy to obtain the historical live broadcast heat of each time sequence; dividing the historical live broadcast heat of each time sequence into a first test set and a second test set; training a preset neural network model through the first test set and the second test set respectively to obtain a hidden layer output matrix and a connection weight; and constructing a target DTPM prediction model according to the hidden layer output matrix and the connection weight.
It should be understood that the first test set and the second test set are used as training sets to perform model training, specifically, 1/N of the historical live broadcast heat of each time sequence is used as the first test set, the rest is used as the second test set, N is a positive integer greater than 1, this embodiment does not limit this, N is 2 as an example, the first test set is trained through a preset neural network model to obtain a hidden layer output matrix, the second test set is trained through the preset neural network model to obtain a connection weight, and a target DTPM prediction model can be constructed according to the hidden layer output matrix and the connection weight.
It can be understood that after obtaining the target DTPM prediction model, the target DTPM prediction model needs to be detected, specifically, by Mean Absolute Percentage Error (MAPE), which specifically is:
where MAPE is the mean absolute percent error, xiFor the historical live broadcast heat of each time series,
in order to predict the heat of live broadcast,
and the prediction module 50 is configured to predict current live broadcast information through the target DTPM prediction model to obtain a corresponding live broadcast heat, so as to predict the heat of the live broadcast room.
It should be understood that the current live broadcast information may be live broadcast information of a main broadcast in a target live broadcast room, including live broadcast content, current barrage information, online number of people, and the like, and after the target DTPM prediction model is obtained, the current live broadcast information is predicted through the target DTPM prediction model, so that the live broadcast heat of the target live broadcast room can be obtained.
In the embodiment, identification information of the room parameters is extracted by acquiring the room parameters of a target live broadcast room; searching for historical user activity, historical bullet screen information and historical appreciation information on a big data platform according to the identification information; calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence; training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model; predicting the current live broadcast information through the target DTPM prediction model to obtain corresponding live broadcast heat so as to realize prediction of the heat of a live broadcast room; compared with the prior art that the live broadcast heat is determined only through single gifts and flow support, the accuracy of predicting the live broadcast heat can be effectively improved.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the live broadcast heat prediction method provided in any embodiment of the present invention, and are not described herein again.
In an embodiment, the calculating module 30 is further configured to determine corresponding historical interaction information according to the historical user activity and the historical bullet screen information; acquiring online nobility, user riding and live broadcast guard in a target live broadcast room; determining corresponding heat addition information according to the historical reward information, the online nobility, the user ride and the live broadcast daemon; and calculating the historical interaction information and the heat addition information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
In an embodiment, the calculation module 30 is further configured to extract a historical active population and a target online population of the historical user activity; obtaining the average online number within a preset time according to the historical active number and the target online number; extracting the bullet screen speech number and the bullet screen speech number of the historical bullet screen information; obtaining the average bullet screen number within a preset time according to the bullet screen speech number and the bullet screen speech number; and determining corresponding historical interaction information according to the average online number of people and the average bullet screen number.
In an embodiment, the training module 40 is further configured to perform discrete decomposition on the historical live broadcast heat time sequence according to a target EEMD policy to obtain historical live broadcast heat of each time sequence; dividing the historical live broadcast heat of each time sequence into a first test set and a second test set; training a preset neural network model through the first test set and the second test set respectively to obtain a hidden layer output matrix and a connection weight; and constructing a target DTPM prediction model according to the hidden layer output matrix and the connection weight.
In an embodiment, the prediction module 50 is further configured to obtain live broadcast days and live broadcast durations of each day of a target live broadcast room; inquiring in a preset live broadcast platform according to the live broadcast days and the identification information to obtain target live broadcast days; calculating the target live broadcast days and live broadcast time of each day to obtain the total target live broadcast time; and obtaining the basic heat of the target live broadcast room according to the target live broadcast total duration, and executing the step of predicting the current live broadcast information through the target DTPM prediction model based on the basic heat to obtain the corresponding live broadcast heat.
In an embodiment, the prediction module 50 is further configured to extract live content, online number of people, watching duration and current barrage information of the current live information; determining the corresponding people retention rate according to the online people number and the watching duration; determining a corresponding bullet screen label according to the live broadcast content and the current bullet screen information; and predicting the current live broadcast information through the target DTPM prediction model, the number retention rate and the bullet screen label to obtain the corresponding live broadcast heat.
In an embodiment, the prediction module 50 is further configured to predict current live broadcast information through the target DTPM prediction model and the people remaining rate to obtain a current live broadcast heat; and obtaining the corresponding live broadcast heat according to the current live broadcast heat and the basic heat.
Other embodiments or implementations of the live broadcast heat prediction apparatus of the present invention can refer to the above method embodiments, and are not intended to be exhaustive.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. Read Only Memory (ROM)/RAM, magnetic disk, optical disk), and includes several instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A live broadcast heat prediction method is characterized by comprising the following steps:
acquiring room parameters of a target live broadcast room, and extracting identification information of the room parameters;
searching for historical user activity, historical bullet screen information and historical appreciation information on a big data platform according to the identification information;
calculating the historical user liveness, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence;
training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model;
and predicting the current live broadcast information through the target DTPM prediction model to obtain the corresponding live broadcast heat so as to realize prediction of the heat of the live broadcast room.
2. The live broadcast heat prediction method of claim 1, wherein the step of calculating the historical user activity, the historical bullet screen information and the historical reward information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence comprises the steps of:
determining corresponding historical interaction information according to the historical user activity and the historical bullet screen information;
acquiring online nobility, user riding and live broadcast guard in a target live broadcast room;
determining corresponding heat addition information according to the historical reward information, the online nobility, the user ride and the live broadcast daemon;
and calculating the historical interaction information and the heat addition information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence.
3. The live broadcast heat prediction method of claim 2, wherein the determining corresponding historical interaction information according to the historical user activity and the historical bullet screen information comprises:
extracting the historical active number and the target online number of the historical user activity;
obtaining the average online number within a preset time according to the historical active number and the target online number;
extracting the bullet screen speech number and the bullet screen speech number of the historical bullet screen information;
obtaining the average bullet screen number within a preset time according to the bullet screen speech number and the bullet screen speech number;
and determining corresponding historical interaction information according to the average online number of people and the average bullet screen number.
4. The live broadcast heat prediction method of claim 1, wherein the training of the historical live broadcast heat time series according to a target EEMD strategy to obtain a target DTPM prediction model comprises:
performing discrete decomposition on the historical live broadcast heat time sequence according to a target EEMD strategy to obtain the historical live broadcast heat of each time sequence;
dividing the historical live broadcast heat of each time sequence into a first test set and a second test set;
training a preset neural network model through the first test set and the second test set respectively to obtain a hidden layer output matrix and a connection weight;
and constructing a target DTPM prediction model according to the hidden layer output matrix and the connection weight.
5. The live broadcast heat prediction method according to claim 1, wherein before predicting current live broadcast information by the target DTPM prediction model and obtaining corresponding live broadcast heat, the live broadcast heat prediction method further comprises:
acquiring the live broadcast days and live broadcast duration of each day of a target live broadcast room;
inquiring in a preset live broadcast platform according to the live broadcast days and the identification information to obtain target live broadcast days;
calculating the target live broadcast days and live broadcast time of each day to obtain the total target live broadcast time;
and obtaining the basic heat of the target live broadcast room according to the target live broadcast total duration, and executing the step of predicting the current live broadcast information through the target DTPM prediction model based on the basic heat to obtain the corresponding live broadcast heat.
6. The live broadcast heat prediction method of claim 1, wherein predicting current live broadcast information through the target DTPM prediction model to obtain a corresponding live broadcast heat comprises:
extracting live broadcast content, online number of people, watching duration and current barrage information of the current live broadcast information;
determining the corresponding people retention rate according to the online people number and the watching duration;
determining a corresponding bullet screen label according to the live broadcast content and the current bullet screen information;
and predicting the current live broadcast information through the target DTPM prediction model, the number retention rate and the bullet screen label to obtain the corresponding live broadcast heat.
7. The live broadcast heat prediction method of any one of claims 1 to 6, wherein the predicting current live broadcast information through the target DTPM prediction model and the people retention rate to obtain the corresponding live broadcast heat comprises:
predicting the current live broadcast information through the target DTPM prediction model and the people number retention rate to obtain the current live broadcast heat;
and obtaining the corresponding live broadcast heat according to the current live broadcast heat and the basic heat.
8. A live broadcast heat prediction apparatus, comprising:
the extraction module is used for acquiring room parameters of a target live broadcast room and extracting identification information of the room parameters;
the searching module is used for searching the historical user liveness, the historical bullet screen information and the historical appreciation information on the big data platform according to the identification information;
the calculation module is used for calculating the historical user activity, the historical bullet screen information and the historical appreciation information through a preset LDA algorithm to obtain a historical live broadcast heat time sequence;
the training module is used for training the historical live broadcast heat time sequence according to a target EEMD strategy to obtain a target DTPM prediction model;
and the prediction module is used for predicting the current live broadcast information through the target DTPM prediction model to obtain the corresponding live broadcast heat so as to realize prediction of the heat of the live broadcast room.
9. A live broadcast heat prediction apparatus characterized by comprising: a memory, a processor, and a live heat prediction program stored on the memory and executable on the processor, the live heat prediction program configured to implement the live heat prediction method of any of claims 1-7.
10. A storage medium having stored thereon a live popularity prediction program that, when executed by a processor, implements a live popularity prediction method as recited in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111058592.9A CN113873274A (en) | 2021-09-08 | 2021-09-08 | Live broadcast heat prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111058592.9A CN113873274A (en) | 2021-09-08 | 2021-09-08 | Live broadcast heat prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113873274A true CN113873274A (en) | 2021-12-31 |
Family
ID=78995316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111058592.9A Withdrawn CN113873274A (en) | 2021-09-08 | 2021-09-08 | Live broadcast heat prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113873274A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115190321A (en) * | 2022-05-13 | 2022-10-14 | 广州博冠信息科技有限公司 | Switching method and device of live broadcast room and electronic equipment |
| CN116886998A (en) * | 2023-07-19 | 2023-10-13 | 中教畅享(北京)科技有限公司 | Interactive processing method for simulating live broadcast environment |
-
2021
- 2021-09-08 CN CN202111058592.9A patent/CN113873274A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115190321A (en) * | 2022-05-13 | 2022-10-14 | 广州博冠信息科技有限公司 | Switching method and device of live broadcast room and electronic equipment |
| CN115190321B (en) * | 2022-05-13 | 2024-06-04 | 广州博冠信息科技有限公司 | Live broadcast room switching method and device and electronic equipment |
| CN116886998A (en) * | 2023-07-19 | 2023-10-13 | 中教畅享(北京)科技有限公司 | Interactive processing method for simulating live broadcast environment |
| CN116886998B (en) * | 2023-07-19 | 2023-12-22 | 中教畅享(北京)科技有限公司 | Interactive processing method for simulating live broadcast environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178705B (en) | Item evaluation method, item evaluation device, item evaluation apparatus, and storage medium | |
| CN113873274A (en) | Live broadcast heat prediction method, device, equipment and storage medium | |
| Kell et al. | Evaluation of the prediction skill of stock assessment using hindcasting | |
| CN109410675B (en) | Exercise recommendation method based on student portrait and family education equipment | |
| US9152919B2 (en) | Method and system for recommending tasks to crowdworker | |
| CN105608179A (en) | Method and device for determining relevance of user identification | |
| CN110490651B (en) | Information pushing method, device, equipment and computer readable storage medium | |
| CN113641767B (en) | Entity relation extraction method, device, equipment and storage medium | |
| US20150309962A1 (en) | Method and apparatus for modeling a population to predict individual behavior using location data from social network messages | |
| CN107818491A (en) | Electronic installation, Products Show method and storage medium based on user's Internet data | |
| KR102163412B1 (en) | Method for providing business establishing information report | |
| CN107679166B (en) | Fragmentation reading method, device and system for online payment and storage medium | |
| CN112990702A (en) | Construction team matching method, device and equipment based on construction task and storage medium | |
| CN117252564A (en) | Resource scheduling method, device, computer equipment and storage medium | |
| CN115191002A (en) | Matching system, matching method, and matching program | |
| CN114385876B (en) | Model search space generation method, device and system | |
| CN113448876B (en) | Service testing method, device, computer equipment and storage medium | |
| CN115905862A (en) | Missing data processing method and system based on generation countermeasure network | |
| CN115221452A (en) | Portal construction method, system, electronic equipment and medium based on visual configuration | |
| CN113095890A (en) | Electronic coupon issuing method and device, computer equipment and storage medium | |
| CN114676940A (en) | Method and device for predicting electricity purchasing quantity in commercial tourist area, electronic equipment and storage medium | |
| CN110766047A (en) | Data matching method, system, computer device and computer readable storage medium | |
| Eyvindson et al. | Using a compromise programming framework to integrating spatially specific preference information for forest management problems | |
| US9532165B2 (en) | Method and apparatus for location prediction using short text | |
| CN113449184A (en) | Recommendation method and device of reach channel, computer equipment and storage medium |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211231 |
|
| WW01 | Invention patent application withdrawn after publication |